CVPR2019论文列表（中英对照）

2.5D Visual Sound2.5D 视觉音效
3D Appearance Super-Resolution With Deep Learning具有深度学习的 3D 外观超分辨率
3D Guided Fine-Grained Face Manipulation3D 引导细粒度面部操作
3D Hand Shape and Pose Estimation From a Single RGB Image来自单个 RGB 图像的 3D 手形和姿势估计
3D Hand Shape and Pose From Images in the Wild来自野外图像的 3D 手形和姿势
3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training具有时间卷积和半监督训练的视频中的 3D 人体姿态估计
3D Local Features for Direct Pairwise Registration直接成对配准的 3D 局部特征
3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis用于 RGBD 未来动态场景合成的 3D 运动分解
3D Point Capsule Networks3D 点胶囊网络
3D Shape Reconstruction From Images in the Frequency Domain从频域中的图像重建 3D 形状
3DN_3D Deformation Network3DN_3D变形网络
3D-SIS_3D Semantic Instance Segmentation of RGB-D ScansRGB-D 扫描的 3D-SIS_3D 语义实例分割
4D Spatio-Temporal ConvNets_Minkowski Convolutional Neural Networks4D 时空卷积网络_Minkowski 卷积神经网络
A Bayesian Perspective on the Deep Image Prior深度图像先验的贝叶斯视角
A Compact Embedding for Facial Expression Similarity面部表情相似性的紧凑嵌入
A Content Transformation Block for Image Style Transfer用于图像风格转移的内容转换块
A Convex Relaxation for Multi-Graph Matching多图匹配的凸松弛
A Cross-Season Correspondence Dataset for Robust Semantic Segmentation用于鲁棒语义分割的跨季节对应数据集
A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing大规模多模态人脸反欺骗的数据集和基准
A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem稀疏广义特征值问题的一种分解算法
A Flexible Convolutional Solver for Fast Style Transfers用于快速风格转移的灵活卷积求解器
A General and Adaptive Robust Loss Function通用和自适应鲁棒损失函数
A Generative Adversarial Density Estimator生成对抗密度估计器
A Generative Appearance Model for End-To-End Video Object Segmentation端到端视频对象分割的生成外观模型
A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations减少对抗性扰动影响的核化流形映射
A Late Fusion CNN for Digital Matting用于数字抠图的后期融合 CNN
A Local Block Coordinate Descent Algorithm for the CSC ModelCSC模型的局部块坐标下降算法
A Main_Subsidiary Network Framework for Simplifying Binary Neural Networks用于简化二元神经网络的 Main_Subsidiary 网络框架
A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision一种相互学习的多监督显着目标检测方法
A Neural Network Based on SPD Manifold Learning for Skeleton-Based Hand Gesture Recognition一种基于 SPD 流形学习的神经网络用于基于骨架的手势识别
A Neural Temporal Model for Human Motion Prediction人体运动预测的神经时间模型
A Neurobiological Evaluation Metric for Neural Network Model Search神经网络模型搜索的神经生物学评价指标
A Parametric Top-View Representation of Complex Road Scenes复杂道路场景的参数化顶视图表示
A Perceptual Prediction Framework for Self Supervised Event Segmentation自监督事件分割的感知预测框架
A Poisson-Gaussian Denoising Dataset With Real Fluorescence Microscopy Images具有真实荧光显微镜图像的泊松高斯去噪数据集
A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes用于航空场景语义分割的关系增强全卷积网络
A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures用于匹配具有不兼容形状结构的非刚性形状的鲁棒局部光谱描述符
A Simple Baseline for Audio-Visual Scene-Aware Dialog视听场景感知对话的简单基线
A Simple Pooling-Based Design for Real-Time Salient Object Detection一种简单的基于池的实时显着目标检测设计
A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images从单个 RGB 图像生成复杂拓扑网格的骨架桥接深度学习方法
A Structured Model for Action Detection动作检测的结构化模型
A Style-Based Generator Architecture for Generative Adversarial Networks用于生成对抗网络的基于样式的生成器架构
A Sufficient Condition for Convergences of Adam and RMSPropAdam 和 RMSProp 收敛的一个充分条件
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning用于提高深度距离度量学习效率的 Triplet Loss 的理论上合理的上限
A Theory of Fermat Paths for Non-Line-Of-Sight Shape Reconstruction非视线形状重建的费马路径理论
A Variational Auto-Encoder Model for Stochastic Point Processes随机点过程的变分自动编码器模型
A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring用于盲运动去模糊的具有自适应边缘选择的变分 EM 框架
A Variational Pan-Sharpening With Local Gradient Constraints具有局部梯度约束的变分泛锐化
AANet_Attribute Attention Network for Person Re-IdentificationsAANet_Attribute Attention Network for Person Re-Identifications
ABC_A Big CAD Model Dataset for Geometric Deep LearningABC_用于几何深度学习的大型 CAD 模型数据集
Accel_A Corrective Fusion Network for Efficient Semantic Segmentation on VideoAccel_A Corrective Fusion Network for Efficient Semantic Segmentation on Video
Accelerating Convolutional Neural Networks via Activation Map Compression通过激活图压缩加速卷积神经网络
A-CNN_Annularly Convolutional Neural Networks on Point CloudsA-CNN_点云上的环形卷积神经网络
Acoustic Non-Line-Of-Sight Imaging声学非视距成像
Action Recognition From Single Timestamp Supervision in Untrimmed Videos未修剪视频中单时间戳监督的动作识别
Action4D_Online Action Recognition in the Crowd and ClutterAction4D_人群中的在线动作识别
Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition用于基于骨架的动作识别的动作结构图卷积网络
Actively Seeking and Learning From Live Data积极寻求和学习实时数据
Activity Driven Weakly Supervised Object Detection活动驱动的弱监督目标检测
Actor-Critic Instance SegmentationActor-Critic 实例分割
AdaCos_Adaptively Scaling Cosine Logits for Effectively Learning Deep Face RepresentationsAdaCos_自适应缩放余弦逻辑以有效学习深度人脸表示
AdaFrame_Adaptive Frame Selection for Fast Video Recognition用于快速视频识别的 AdaFrame_Adaptive 帧选择
AdaGraph_Unifying Predictive and Continuous Domain Adaptation Through GraphsAdaGraph_通过图统一预测和连续域自适应
Adapting Object Detectors via Selective Cross-Domain Alignment通过选择性跨域对齐调整对象检测器
Adaptive Confidence Smoothing for Generalized Zero-Shot Learning广义零样本学习的自适应置信平滑
Adaptive NMS_Refining Pedestrian Detection in a Crowd人群中的自适应 NMS_Refining 行人检测
Adaptive Pyramid Context Network for Semantic Segmentation用于语义分割的自适应金字塔上下文网络
Adaptive Transfer Network for Cross-Domain Person Re-Identification用于跨域人员重新识别的自适应传输网络
Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology用于病理学语义分割的自适应加权多视场 CNN
AdaptiveFace_ Adaptive Margin and Sampling for Face RecognitionAdaptiveFace_人脸识别的自适应边距和采样
Adaptively Connected Neural Networks自适应连接的神经网络
ADCrowdNet_ An Attention-Injective Deformable Convolutional Network for Crowd UnderstandingADCrowdNet_一种用于人群理解的注意力注入可变形卷积网络
Additive Adversarial Learning for Unbiased Authentication用于无偏见身份验证的加法对抗学习
ADVENT_ Adversarial Entropy Minimization for Domain Adaptation in Semantic SegmentationADVENT_语义分割中域自适应的对抗熵最小化
Adversarial Attacks Beyond the Image Space超越图像空间的对抗性攻击
Adversarial Defense by Stratified Convolutional Sparse Coding分层卷积稀疏编码的对抗性防御
Adversarial Defense Through Network Profiling Based Path Extraction通过基于网络分析的路径提取进行对抗性防御
Adversarial Inference for Multi-Sentence Video Description多句视频描述的对抗推理
Adversarial Semantic Alignment for Improved Image Captions改进图像标题的对抗语义对齐
Adversarial Structure Matching for Structured Prediction Tasks结构化预测任务的对抗性结构匹配
AE2-Nets_ Autoencoder in Autoencoder NetworksAE2-Nets_自动编码器网络中的自动编码器
AET vs. AED_ Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than DataAET vs. AED_通过自动编码转换而不是数据进行无监督表示学习
Aggregation Cross-Entropy for Sequence Recognition用于序列识别的聚合交叉熵
AIRD_ Adversarial Learning Framework for Image Repurposing DetectionAIRD_ 用于图像再利用检测的对抗性学习框架
All About Structure_ Adapting Structural Information Across Domains for Boosting Semantic Segmentation所有关于结构_跨域调整结构信息以促进语义分割
All You Need Is a Few Shifts_ Designing Efficient Convolutional Neural Networks for Image Classification所有你需要的是几个转变_设计用于图像分类的高效卷积神经网络
All-Weather Deep Outdoor Lighting Estimation全天候深度户外照明估计
Amodal Instance Segmentation With KINS Dataset使用 KINS 数据集进行 Amodal 实例分割
An Alternative Deep Feature Approach to Line Level Keyword Spotting行级关键字发现的另一种深度特征方法
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition用于基于骨架的动作识别的注意力增强图卷积 LSTM 网络
An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM用于 3D 视觉惯性 SLAM 的高效 Schmidt-EKF
An End-To-End Network for Generating Social Relationship Graphs用于生成社会关系图的端到端网络
An End-To-End Network for Panoptic Segmentation用于全景分割的端到端网络
An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection用于显着目标检测的迭代协作自上而下和自下而上的推理网络
Analysis of Feature Visibility in Non-Line-Of-Sight Measurements非视线测量中的特征可见性分析
Animating Arbitrary Objects via Deep Motion Transfer通过深度运动传输为任意对象设置动画
Answer Them All! Toward Universal Visual Question Answering Models全部回答！迈向通用视觉问答模型
AOGNets_ Compositional Grammatical Architectures for Deep LearningAOGNets_ 用于深度学习的组合语法架构
APDrawingGAN_ Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANsAPDrawingGAN_ 使用分层 GAN 从人脸照片生成艺术肖像画
ApolloCar3D_ A Large 3D Car Instance Understanding Benchmark for Autonomous DrivingApolloCar3D_ 大型 3D 汽车实例了解自动驾驶基准
Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation具有自适应文本区域表示的任意形状场景文本检测
Arbitrary Style Transfer With Style-Attentional Networks风格注意网络的任意风格转移
ArcFace_ Additive Angular Margin Loss for Deep Face RecognitionArcFace_ 用于深度人脸识别的加性角边距损失
Argoverse_ 3D Tracking and Forecasting With Rich MapsArgoverse_ 使用丰富的地图进行 3D 跟踪和预测
Art2Real_ Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image TranslationArt2Real_通过语义感知图像到图像的翻译展现艺术品的真实性
Assessing Personally Perceived Image Quality via Image Features and Collaborative Filtering通过图像特征和协同过滤评估个人感知的图像质量
Assessment of Faster R-CNN in Man-Machine Collaborative Search人机协同搜索中 Faster R-CNN 的评估
Assisted Excitation of Activations_ A Learning Technique to Improve Object Detectors激活的辅助激发_一种改进对象检测器的学习技术
Associatively Segmenting Instances and Semantics in Point Clouds在点云中关联分割实例和语义
Atlas of Digital Pathology_ A Generalized Hierarchical Histological Tissue Type-Annotated Database for Deep LearningAtlas of Digital Pathology_A Generalized Hierarchical Histological Tissue Type-Annotated Database for Deep Learning
ATOM_ Accurate Tracking by Overlap MaximizationATOM_通过重叠最大化进行准确跟踪
Attending to Discriminative Certainty for Domain Adaptation关注域适应的判别确定性
Attention Based Glaucoma Detection_ A Large-Scale Database and CNN Model基于注意力的青光眼检测_大规模数据库和CNN模型
Attention Branch Network_ Learning of Attention Mechanism for Visual Explanation注意力分支网络_视觉解释的注意力机制学习
Attention-Aware Multi-Stroke Style Transfer注意力感知多笔画风格转移
Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions未知组合失真下图像恢复的基于注意力的自适应操作选择
Attention-Based Dropout Layer for Weakly Supervised Object Localization用于弱监督目标定位的基于注意力的 Dropout 层
Attention-Guided Network for Ghost-Free High Dynamic Range Imaging用于无鬼高动态范围成像的注意力引导网络
Attention-Guided Unified Network for Panoptic Segmentation用于全景分割的注意力引导统一网络
Attentive Feedback Network for Boundary-Aware Salient Object Detection用于边界感知显着目标检测的注意反馈网络
Attentive Region Embedding Network for Zero-Shot Learning用于零样本学习的注意力区域嵌入网络
Attentive Relational Networks for Mapping Images to Scene Graphs用于将图像映射到场景图的注意力关系网络
Attentive Single-Tasking of Multiple Tasks多任务的细心单任务
Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks基于小波的生成对抗网络的属性感知人脸老化
Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification用于视频人物重新识别的属性驱动特征解开和时间聚合
Audio Visual Scene-Aware Dialog视听场景感知对话框
AutoAugment_ Learning Augmentation Strategies From DataAutoAugment_ 从数据中学习增强策略
Auto-DeepLab_ Hierarchical Neural Architecture Search for Semantic Image SegmentationAuto-DeepLab_ 用于语义图像分割的分层神经架构搜索
Auto-Encoding Scene Graphs for Image Captioning用于图像字幕的自动编码场景图
Automatic Adaptation of Object Detectors to New Domains Using Self-Training使用自我训练使目标检测器自动适应新领域
Automatic Face Aging in Videos via Deep Reinforcement Learning通过深度强化学习在视频中自动人脸老化
BAD SLAM_ Bundle Adjusted Direct RGB-D SLAMBAD SLAM_Bundle Adjusted Direct RGB-D SLAM
Bag of Tricks for Image Classification with Convolutional Neural Networks使用卷积神经网络进行图像分类的技巧包
Balanced Self-Paced Learning for Generative Adversarial Clustering Network生成对抗聚类网络的平衡自定进度学习
Barrage of Random Transforms for Adversarially Robust Defense对抗性鲁棒防御的随机变换弹幕
BASNet_ Boundary-Aware Salient Object DetectionBASNet_边界感知显着目标检测
Bayesian Hierarchical Dynamic Model for Human Action Recognition用于人类行为识别的贝叶斯分层动态模型
BeautyGlow_ On-Demand Makeup Transfer Framework With Reversible Generative NetworkBeautyGlow_具有可逆生成网络的按需化妆转移框架
Beyond Gradient Descent for Regularized Segmentation Losses超越正则化分割损失的梯度下降
Beyond Tracking_ Selecting Memory and Refining Poses for Deep Visual Odometry超越追踪_为深度视觉里程计选择记忆和优化姿势
Beyond Volumetric Albedo – A Surface Optimization Framework for Non-Line-Of-Sight Imaging超越体积反照率——非视距成像的表面优化框架
Bi-Directional Cascade Network for Perceptual Edge Detection用于感知边缘检测的双向级联网络
Bidirectional Learning for Domain Adaptation of Semantic Segmentation语义分割领域自适应的双向学习
Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction无监督单目深度预测的双边循环约束和自适应正则化
Binary Ensemble Neural Network_ More Bits per Network or More Networks per Bit_二元集成神经网络_每个网络更多比特或每比特更多网络_
Biologically-Constrained Graphs for Global Connectomics Reconstruction用于全局连接组学重建的生物约束图
Blending-Target Domain Adaptation by Adversarial Meta-Adaptation Networks对抗性元适应网络的混合目标域适应
Blind Geometric Distortion Correction on Images Through Deep Learning通过深度学习对图像进行盲几何失真校正
Blind Image Deblurring With Local Maximum Gradient Prior局部最大梯度先验的盲图像去模糊
Blind Super-Resolution With Iterative Kernel Correction具有迭代内核校正的盲超分辨率
Blind Visual Motif Removal From a Single Image从单个图像中去除盲目的视觉主题
Boosting Local Shape Matching for Dense 3D Face Correspondence促进密集 3D 人脸对应的局部形状匹配
Bottom-Up Object Detection by Grouping Extreme and Center Points通过对极值点和中心点进行分组来进行自下而上的对象检测
Bounding Box Regression With Uncertainty for Accurate Object Detection用于准确目标检测的不确定性边界框回归
Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation用于弱监督语义分割的框驱动分类区域掩蔽和填充率引导损失
BridgeNet_ A Continuity-Aware Probabilistic Network for Age EstimationBridgeNet_ 用于年龄估计的连续性感知概率网络
Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence通过时空对应桥接立体匹配和光流
Bringing a Blurry Frame Alive at High Frame-Rate With an Event Camera使用事件相机以高帧速率使模糊帧栩栩如生
Bringing Alive Blurred Moments使模糊的时刻栩栩如生
BubbleNets_ Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting FramesBubbleNets_Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames
Building Detail-Sensitive Semantic Segmentation Networks With Polynomial Pooling使用多项式池化构建细节敏感的语义分割网络
Building Efficient Deep Neural Networks With Unitary Group Convolutions使用酉群卷积构建高效的深度神经网络
C2AE_ Class Conditioned Auto-Encoder for Open-Set RecognitionC2AE_用于开放集识别的类条件自动编码器
C3AE_ Exploring the Limits of Compact Model for Age EstimationC3AE_探索年龄估计紧凑模型的极限
CAM-Convs_ Camera-Aware Multi-Scale Convolutions for Single-View DepthCAM-Convs_Camera-Aware Multi-Scale Convolutions for Single-View Depth
Camera Lens Super-Resolution相机镜头超分辨率
CANet_ Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot LearningCANet_ 具有迭代细化和细心的 Few-Shot 学习的与类别无关的分割网络
CapSal_ Leveraging Captioning to Boost Semantics for Salient Object DetectionCapSal_利用字幕增强语义以进行显着目标检测
Capture, Learning, and Synthesis of 3D Speaking Styles3D 口语风格的捕捉、学习和综合
Cascaded Generative and Discriminative Learning for Microcalcification Detection in Breast Mammograms用于乳腺 X 线照片中微钙化检测的级联生成和判别学习
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection级联部分解码器用于快速准确的显着目标检测
Cascaded Projection_ End-To-End Network Compression and Acceleration级联投影_端到端网络压缩与加速
Catastrophic Child’s Play_ Easy to Perform, Hard to Defend Adversarial Attacks灾难性的儿童游戏_易于执行，难以防御对抗性攻击
Causes and Corrections for Bimodal Multi-Path Scanning With Structured Light结构光双峰多径扫描的原因及修正
Centripetal SGD for Pruning Very Deep Convolutional Networks With Complicated Structure向心 SGD 用于修剪具有复杂结构的非常深的卷积网络
ChamNet_ Towards Efficient Network Design Through Platform-Aware Model AdaptationChamNet_通过平台感知模型适应实现高效网络设计
Character Region Awareness for Text Detection文本检测的字符区域感知
Characterizing and Avoiding Negative Transfer表征和避免负迁移
Circulant Binary Convolutional Networks_ Enhancing the Performance of 1-Bit DCNNs With Circulant Back Propagation循环二进制卷积网络_通过循环反向传播增强 1 位 DCNN 的性能
CityFlow_ A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-IdentificationCityFlow_多目标多摄像头车辆跟踪和重新识别的城市规模基准
Class-Balanced Loss Based on Effective Number of Samples基于有效样本数的类平衡损失
Classification-Reconstruction Learning for Open-Set Recognition开放集识别的分类重建学习
CLEVR-Ref+_ Diagnosing Visual Reasoning With Referring ExpressionsCLEVR-Ref+_ 用引用表达式诊断视觉推理
ClusterNet_ Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud AnalysisClusterNet_ 用于点云分析的具有严格旋转不变表示的深度层次聚类网络
C-MIL_ Continuation Multiple Instance Learning for Weakly Supervised Object DetectionC-MIL_弱监督目标检测的连续多实例学习
COIN_ A Large-Scale Dataset for Comprehensive Instructional Video AnalysisCOIN_ 用于综合教学视频分析的大规模数据集
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images用于超高分辨率图像的内存高效分割的协作全局-局部网络
Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images医学图像半监督分割与分类的协同学习
Collaborative Spatiotemporal Feature Learning for Video Action Recognition用于视频动作识别的协作时空特征学习
CollaGAN_ Collaborative GAN for Missing Image Data ImputationCollaGAN_ 用于缺失图像数据插补的协作 GAN
Coloring With Limited Data_ Few-Shot Colorization via Memory Augmented Networks使用有限数据着色_通过内存增强网络进行的少镜头着色
Combinatorial Persistency Criteria for Multicut and Max-Cut多剪辑和最大剪辑的组合持久性标准
Combining 3D Morphable Models_ A Large Scale Face-And-Head Model结合 3D Morphable Models_ 大型人脸和头部模型
ComDefend_ An Efficient Image Compression Model to Defend Adversarial ExamplesComDefend_防御对抗样本的高效图像压缩模型
Compact Feature Learning for Multi-Domain Image Classification用于多域图像分类的紧凑特征学习
Competitive Collaboration_ Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation竞争协作_深度、相机运动、光流和运动分割的联合无监督学习
Complete the Look_ Scene-Based Complementary Product Recommendation完成Look_基于场景的互补产品推荐
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization弱监督时间动作定位的完整性建模和上下文分离
Composing Text and Image for Image Retrieval - an Empirical Odyssey为图像检索组合文本和图像 - 经验奥德赛
Compressing Convolutional Neural Networks via Factorized Convolutional Filters通过分解卷积滤波器压缩卷积神经网络
Compressing Unknown Images With Product Quantizer for Efficient Zero-Shot Classification使用产品量化器压缩未知图像以实现高效的零样本分类
Conditional Adversarial Generative Flow for Controllable Image Synthesis用于可控图像合成的条件对抗生成流
Conditional Single-View Shape Generation for Multi-View Stereo Reconstruction用于多视图立体重建的条件单视图形状生成
Connecting the Dots_ Learning Representations for Active Monocular Depth Estimation连接点_主动单目深度估计的学习表示
Connecting Touch and Vision via Cross-Modal Prediction通过跨模态预测连接触摸和视觉
Constrained Generative Adversarial Networks for Interactive Image Generation用于交互式图像生成的约束生成对抗网络
ContactDB_ Analyzing and Predicting Grasp Contact via Thermal ImagingContactDB_通过热成像分析和预测抓握接触
Content Authentication for Neural Imaging Pipelines_ End-To-End Optimization of Photo Provenance in Complex Distribution Channels神经成像管道的内容认证_复杂分销渠道中照片来源的端到端优化
Content-Aware Multi-Level Guidance for Interactive Instance Segmentation交互式实例分割的内容感知多级指导
Context and Attribute Grounded Dense Captioning基于上下文和属性的密集字幕
Context-Aware Crowd Counting上下文感知人群计数
Context-Aware Spatio-Recurrent Curvilinear Structure Segmentation上下文感知空间循环曲线结构分割
Context-Aware Visual Compatibility Prediction上下文感知视觉兼容性预测
ContextDesc_ Local Descriptor Augmentation With Cross-Modality ContextContextDesc_ 具有跨模态上下文的局部描述符增强
Context-Reinforced Semantic Segmentation上下文强化语义分割
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection用于 RGBD 显着目标检测的对比先验和流体金字塔集成
Contrastive Adaptation Network for Unsupervised Domain Adaptation用于无监督域适应的对比适应网络
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction用于单图像人体形状重建的卷积网格回归
Convolutional Neural Networks Can Be Deceived by Visual Illusions视觉错觉可以欺骗卷积神经网络
Convolutional Recurrent Network for Road Boundary Extraction用于道路边界提取的卷积循环网络
Convolutional Relational Machine for Group Activity Recognition用于群体活动识别的卷积关系机
Co-Occurrence Neural Network共现神经网络
Co-Occurrent Features in Semantic Segmentation语义分割中的共现特征
Coordinate-Based Texture Inpainting for Pose-Guided Human Image Generation用于姿势引导的人体图像生成的基于坐标的纹理修复
Coordinate-Free Carlsson-Weinshall Duality and Relative Multi-View Geometry无坐标 Carlsson-Weinshall 对偶和相对多视图几何
Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing通过具有多尺度标签平滑的掩模引导全卷积网络进行共显着性检测
CRAVES_ Controlling Robotic Arm With a Vision-Based Economic SystemCRAVES_用基于视觉的经济系统控制机械臂
CrDoCo_ Pixel-Level Domain Transfer With Cross-Domain ConsistencyCrDoCo_具有跨域一致性的像素级域迁移
Creative Flow+ Dataset创意流+数据集
Cross Domain Model Compression by Structurally Weight Sharing通过结构权重共享进行跨域模型压缩
Cross-Atlas Convolution for Parameterization Invariant Learning on Textured Mesh Surface纹理网格表面参数化不变学习的跨图集卷积
Cross-Classification Clustering_ An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics跨分类聚类_一种高效的多对象跟踪技术，用于连接组学中的 3-D 实例分割
CrossInfoNet_ Multi-Task Information Sharing Based Hand Pose EstimationCrossInfoNet_基于多任务信息共享的手势估计
Cross-Modal Relationship Inference for Grounding Referring Expressions用于接地引用表达式的跨模态关系推断
Cross-Modal Self-Attention Network for Referring Image Segmentation用于参考图像分割的跨模态自注意力网络
Cross-Modality Personalization for Retrieval检索的跨模态个性化
Cross-Task Weakly Supervised Learning From Instructional Videos教学视频中的跨任务弱监督学习
Crowd Counting and Density Estimation by Trellis Encoder-Decoder NetworksTrellis 编码器-解码器网络的人群计数和密度估计
CrowdPose_ Efficient Crowded Scenes Pose Estimation and a New BenchmarkCrowdPose_高效的拥挤场景姿态估计和新基准
Curls & Whey_ Boosting Black-Box Adversarial AttacksCurls & Whey_ 提升黑盒对抗性攻击
Customizable Architecture Search for Semantic Segmentation用于语义分割的可定制架构搜索
Cycle-Consistency for Robust Visual Question Answering鲁棒视觉问答的循环一致性
Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation弱监督联合检测和分割的循环指导
D2-Net_ A Trainable CNN for Joint Description and Detection of Local FeaturesD2-Net_一种可训练的CNN，用于联合描述和检测局部特征
D3TW_ Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and SegmentationD3TW_ 用于弱监督动作对齐和分割的可区分动态时间扭曲
Dance With Flow_ Two-In-One Stream Action Detection随波逐流_二合一流动作检测
DARNet_ Deep Active Ray Network for Building SegmentationDARNet_ 用于构建分割的深度主动射线网络
Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation使用学习转换的数据增强用于一次性医学图像分割
Data Representation and Learning With Graph Diffusion-Embedding Networks图扩散嵌入网络的数据表示和学习
Data-Driven Neuron Allocation for Scale Aggregation Networks规模聚合网络的数据驱动神经元分配
DAVANet_ Stereo Deblurring With View AggregationDAVANet_ 带有视图聚合的立体去模糊
DDLSTM_ Dual-Domain LSTM for Cross-Dataset Action RecognitionDDLSTM_用于跨数据集动作识别的双域LSTM
Decoders Matter for Semantic Segmentation_ Data-Dependent Decoding Enables Flexible Feature Aggregation解码器对语义分割很重要_数据相关解码实现了灵活的特征聚合
Decorrelated Adversarial Learning for Age-Invariant Face Recognition用于年龄不变人脸识别的去相关对抗学习
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses高效基于梯度的 L2 对抗性攻击和防御的解耦方向和范数
Deep Asymmetric Metric Learning via Rich Relationship Mining通过丰富的关系挖掘进行深度非对称度量学习
Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence通过时间聚合和重复进行深度盲视频截取
Deep ChArUco_ Dark ChArUco Marker Pose EstimationDeep ChArUco_Dark ChArUco Marker Pose Estimation
Deep Defocus Map Estimation Using Domain Adaptation使用域自适应的深度散焦地图估计
Deep Dual Relation Modeling for Egocentric Interaction Recognition以自我为中心的交互识别的深度对偶关系建模
Deep Embedding Learning With Discriminative Sampling Policy带有判别采样策略的深度嵌入学习
Deep Exemplar-Based Video Colorization基于深度示例的视频着色
Deep Fitting Degree Scoring Network for Monocular 3D Object Detection用于单目 3D 目标检测的深度拟合度评分网络
Deep Flow-Guided Video Inpainting深度流引导的视频修复
Deep Geometric Prior for Surface Reconstruction表面重建的深度几何先验
Deep Global Generalized Gaussian Networks深度全局广义高斯网络
Deep High-Resolution Representation Learning for Human Pose Estimation用于人体姿势估计的深度高分辨率表示学习
Deep Incremental Hashing Network for Efficient Image Retrieval用于高效图像检索的深度增量散列网络
Deep Metric Learning Beyond Binary Supervision超越二元监督的深度度量学习
Deep Metric Learning to Rank深度度量学习排名
Deep Modular Co-Attention Networks for Visual Question Answering用于视觉问答的深度模块化共同注意网络
Deep Multimodal Clustering for Unsupervised Audiovisual Learning用于无监督视听学习的深度多模态聚类
Deep Network Interpolation for Continuous Imagery Effect Transition连续图像效果转换的深度网络插值
Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels任意模糊内核的深度即插即用超分辨率
Deep Reinforcement Learning of Volume-Guided Progressive View Inpainting for 3D Point Scene Completion From a Single Depth Image体积引导渐进式视图修复的深度强化学习，用于从单个深度图像完成 3D 点场景
Deep Rigid Instance Scene Flow深度刚性实例场景流
Deep RNN Framework for Visual Sequential Applications用于视觉序列应用的深度 RNN 框架
Deep Robust Subjective Visual Property Prediction in Crowdsourcing众包中深度鲁棒的主观视觉属性预测
Deep Single Image Camera Calibration With Radial Distortion具有径向失真的深度单图像相机校准
Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing具有分段 3D 随机查看的深度草图形状散列
Deep Sky Modeling for Single Image Outdoor Lighting Estimation单幅图像室外照明估计的深空建模
Deep Spectral Clustering Using Dual Autoencoder Network使用双自动编码器网络的深度谱聚类
Deep Spherical Quantization for Image Search图像搜索的深度球面量化
Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring用于图像去模糊的 Deep Stacked Hierarchical Multi-Patch Network
Deep Supervised Cross-Modal Retrieval深度监督跨模态检索
Deep Surface Normal Estimation With Hierarchical RGB-D Fusion使用分层 RGB-D 融合的深表面法线估计
Deep Transfer Learning for Multiple Class Novelty Detection用于多类新颖性检测的深度迁移学习
Deep Tree Learning for Zero-Shot Face Anti-Spoofing用于零镜头人脸反欺骗的深度树学习
Deep Video Inpainting深度视频修复
Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks用于多任务内存高效推理的深度虚拟网络
DeepCaps_ Going Deeper With Capsule NetworksDeepCaps_ 深入胶囊网络
DeepCO3_ Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency DetectionDeepCO3_通过共同峰值搜索和共同显着性检测进行深度实例共同分割
Deeper and Wider Siamese Networks for Real-Time Visual Tracking用于实时视觉跟踪的更深更广的连体网络
DeepFashion2_ A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing ImagesDeepFashion2_服装图像检测、姿态估计、分割和重新识别的多功能基准
DeepFlux for Skeletons in the Wild野外骷髅的 DeepFlux
DeepLiDAR_ Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color ImageDeepLiDAR_来自稀疏激光雷达数据和单色图像的户外场景深度表面法线引导深度预测
DeepLight_ Learning Illumination for Unconstrained Mobile Mixed RealityDeepLight_无约束移动混合现实的学习照明
Deeply-Supervised Knowledge Synergy深度监督的知识协同
DeepMapping_ Unsupervised Map Estimation From Multiple Point CloudsDeepMapping_来自多个点云的无监督地图估计
DeepSDF_ Learning Continuous Signed Distance Functions for Shape RepresentationDeepSDF_ 学习形状表示的连续符号距离函数
DeepView_ View Synthesis With Learned Gradient DescentDeepView_使用学习梯度下降的视图合成
DeepVoxels_ Learning Persistent 3D Feature EmbeddingsDeepVoxels_学习持久3D特征嵌入
Defending Against Adversarial Attacks by Randomized Diversification通过随机多样化防御对抗性攻击
Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search使用网络规模最近邻搜索防御对抗性图像
Deformable ConvNets V2_ More Deformable, Better ResultsDeformable ConvNets V2_ 更可变形，更好的结果
DeFusionNET_ Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep FeaturesDeFusionNET_通过循环融合和细化多尺度深度特征的散焦模糊检测
Dense 3D Face Decoding Over 2500FPS_ Joint Texture & Shape Convolutional Mesh Decoders超过 2500FPS 的密集 3D 人脸解码_ 联合纹理和形状卷积网格解码器
Dense Classification and Implanting for Few-Shot Learning用于 Few-Shot 学习的密集分类和植入
Dense Depth Posterior (DDP) From Single Image and Sparse Range来自单个图像和稀疏范围的密集深度后验 (DDP)
Dense Intrinsic Appearance Flow for Human Pose Transfer人体姿势转移的密集内在外观流
Dense Relational Captioning_ Triple-Stream Networks for Relationship-Based Captioning密集关系字幕_基于关系的字幕的三流网络
DenseFusion_ 6D Object Pose Estimation by Iterative Dense FusionDenseFusion_ 6D Object Pose Estimation by Iterative Dense Fusion
Densely Semantically Aligned Person Re-Identification密集语义对齐的人重新识别
Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization用于 RGB-D 人群计数和定位的密度图回归引导检测网络
Depth Coefficients for Depth Completion深度完成的深度系数
Depth From a Polarisation + RGB Stereo Pair偏振深度 + RGB 立体声对
Depth-Attentional Features for Single-Image Rain Removal单幅图像去雨的深度注意特征
Depth-Aware Video Frame Interpolation深度感知视频帧插值
Describing Like Humans_ On Diversity in Image Captioning像人类一样描述_图像字幕的多样性
Destruction and Construction Learning for Fine-Grained Image Recognition细粒度图像识别的破坏和构建学习
Detailed Human Shape Estimation From a Single Image by Hierarchical Mesh Deformation通过分层网格变形从单幅图像中进行详细的人体形状估计
Detecting Overfitting of Deep Generative Networks via Latent Recovery通过潜在恢复检测深度生成网络的过度拟合
Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View从隐写分析的角度基于检测的对抗性示例防御
Detect-To-Retrieve_ Efficient Regional Aggregation for Image SearchDetect-To-Retrieve_图像搜索的高效区域聚合
Devil Is in the Edges_ Learning Semantic Boundaries From Noisy Annotations魔鬼在边缘_从嘈杂的注释中学习语义边界
DFANet_ Deep Feature Aggregation for Real-Time Semantic SegmentationDFANet_ 用于实时语义分割的深度特征聚合
Dichromatic Model Based Temporal Color Constancy for AC Light Sources基于二色模型的交流光源时间颜色恒常性
Did It Change_ Learning to Detect Point-Of-Interest Changes for Proactive Map Updates改变了吗_学习检测兴趣点变化以进行主动地图更新
Direct Object Recognition Without Line-Of-Sight Using Optical Coherence使用光学相干直接识别无视距的物体
Discovering Fair Representations in the Data Domain发现数据域中的公平表示
Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning通过空间一致的特征学习发现艺术收藏品中的视觉模式
Disentangled Representation Learning for 3D Face Shape3D 人脸形状的解耦表示学习
Disentangling Adversarial Robustness and Generalization解开对抗性鲁棒性和泛化
Disentangling Latent Hands for Image Synthesis and Pose Estimation解开用于图像合成和姿势估计的潜在手
Disentangling Latent Space for VAE by Label Relevant_Irrelevant Dimensions通过标签 Relevant_Irrelevant 维度解开 VAE 的潜在空间
Dissecting Person Re-Identification From the Viewpoint of Viewpoint从视点剖析人物再识别
Dissimilarity Coefficient Based Weakly Supervised Object Detection基于相异系数的弱监督目标检测
Distant Supervised Centroid Shift_ A Simple and Efficient Approach to Visual Domain Adaptation远距离监督质心移位_一种简单有效的视觉域适应方法
Distilled Person Re-Identification_ Towards a More Scalable System蒸馏人员重新识别_迈向更具可扩展性的系统
DistillHash_ Unsupervised Deep Hashing by Distilling Data PairsDistillHash_通过提取数据对进行无监督深度哈希
Distilling Object Detectors With Fine-Grained Feature Imitation用细粒度特征模仿蒸馏目标检测器
Distraction-Aware Shadow Detection分心感知阴影检测
Divergence Prior and Vessel-Tree Reconstruction发散先验和血管树重建
Divergence Triangle for Joint Training of Generator Model, Energy-Based Model, and Inferential Model用于生成器模型、基于能量的模型和推理模型的联合训练的发散三角形
Diverse Generation for Multi-Agent Sports Games多智能体体育游戏的多样化生成
Diversify and Match_ A Domain Adaptive Representation Learning Paradigm for Object Detection多样化和匹配_对象检测的领域自适应表示学习范式
Divide and Conquer the Embedding Space for Metric Learning划分并征服度量学习的嵌入空间
DLOW_ Domain Flow for Adaptation and GeneralizationDLOW_ 适应和泛化的领域流
DMC-Net_ Generating Discriminative Motion Cues for Fast Compressed Video Action RecognitionDMC-Net_为快速压缩视频动作识别生成判别运动线索
DM-GAN_ Dynamic Memory Generative Adversarial Networks for Text-To-Image SynthesisDM-GAN_ 用于文本到图像合成的动态记忆生成对抗网络
Do Better ImageNet Models Transfer Better_做得更好 ImageNet 模型迁移得更好_
Does Learning Specific Features for Related Parts Help Human Pose Estimation_学习相关零件的特定特征是否有助于人体姿势估计_
Domain Generalization by Solving Jigsaw Puzzles通过解决拼图进行领域泛化
Domain-Specific Batch Normalization for Unsupervised Domain Adaptation用于无监督域适应的域特定批量标准化
Domain-Symmetric Networks for Adversarial Domain Adaptation用于对抗域自适应的域对称网络
Doodle to Search_ Practical Zero-Shot Sketch-Based Image RetrievalDoodle to Search_基于零镜头草图的实用图像检索
Double Nuclear Norm Based Low Rank Representation on Grassmann Manifolds for Clustering基于Grassmann流形聚类的双核范数低秩表示
Double-DIP_Unsupervised Image Decomposition via Coupled Deep-Image-Priors通过耦合深度图像先验进行双 DIP_无监督图像分解
Douglas-Rachford Networks_ Learning Both the Image Prior and Data Fidelity Terms for Blind Image DeconvolutionDouglas-Rachford Networks_ 学习盲图像反卷积的图像先验和数据保真度项
DrivingStereo_ A Large-Scale Dataset for Stereo Matching in Autonomous Driving ScenariosDrivingStereo_自动驾驶场景立体匹配的大规模数据集
DSFD_ Dual Shot Face DetectorDSFD_双镜头人脸检测器
d-SNE_ Domain Adaptation Using Stochastic Neighborhood Embeddingd-SNE_ 使用随机邻域嵌入的域自适应
Dual Attention Network for Scene Segmentation用于场景分割的双注意力网络
Dual Encoding for Zero-Example Video Retrieval用于零示例视频检索的双重编码
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration双残差网络利用配对操作的潜力进行图像恢复
DuDoNet_ Dual Domain Network for CT Metal Artifact ReductionDuDoNet_减少CT金属伪影的双域网络
DuLa-Net_ A Dual-Projection Network for Estimating Room Layouts From a Single RGB PanoramaDuLa-Net_ 用于从单个 RGB 全景图估计房间布局的双投影网络
DVC_ An End-To-End Deep Video Compression FrameworkDVC_端到端深度视频压缩框架
Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering用于视觉问答的模态内和模态间注意流的动态融合
Dynamic Recursive Neural Network动态递归神经网络
Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections具有参数选择性共享和嵌套跳过连接的动态场景去模糊
Dynamics Are Important for the Recognition of Equine Pain in Video动力学对于识别视频中的马疼痛很重要
DynTypo_ Example-Based Dynamic Text Effects TransferDynTypo_ 基于示例的动态文本效果传输
ECC_ Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression ModelECC_ 基于双线性回归模型的平台无关能量约束深度神经网络压缩
Edge-Labeling Graph Neural Network for Few-Shot Learning用于 Few-Shot 学习的边缘标记图神经网络
Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features具有多级空间合并特征的有效美学预测
Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition高效的基于决策的人脸识别黑盒对抗攻击
Efficient Featurized Image Pyramid Network for Single Shot Detector用于单次检测器的高效特征图像金字塔网络
Efficient Multi-Domain Learning by Covariance Normalization通过协方差归一化进行高效的多域学习
Efficient Neural Network Compression高效的神经网络压缩
Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity Fields具有循环时空亲和场的高效在线多人 2D 姿势跟踪
Efficient Parameter-Free Clustering Using First Neighbor Relations使用第一邻域关系的高效无参数聚类
Efficient Video Classification Using Fewer Frames使用更少的帧进行高效的视频分类
EIGEN_ Ecologically-Inspired GENetic Approach for Neural Network Structure Searching From ScratchEIGEN_ 从头开始搜索神经网络结构的受生态启发的遗传方法
Elastic Boundary Projection for 3D Medical Image Segmentation用于 3D 医学图像分割的弹性边界投影
ELASTIC_ Improving CNNs With Dynamic Scaling PoliciesELASTIC_ 使用动态缩放策略改进 CNN
Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking消除多目标跟踪中的曝光偏差和度量不匹配
Embedding Complementary Deep Networks for Image Classification嵌入互补深度网络进行图像分类
Embodied Question Answering in Photorealistic Environments With Point Cloud Perception具有点云感知的逼真环境中的具体问答
Emotion-Aware Human Attention Prediction情绪感知人类注意力预测
End-To-End Efficient Representation Learning via Cascading Combinatorial Optimization通过级联组合优化进行端到端的高效表示学习
End-To-End Interpretable Neural Motion Planner端到端可解释神经运动规划器
End-To-End Learned Random Walker for Seeded Image Segmentation用于种子图像分割的端到端学习随机游走器
End-To-End Multi-Task Learning With Attention带注意力的端到端多任务学习
End-To-End Projector Photometric Compensation端到端投影仪光度补偿
End-To-End Supervised Product Quantization for Image Search and Retrieval图像搜索和检索的端到端监督产品量化
End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image来自单个室外图像的端到端延时视频合成
Engaging Image Captioning via Personality通过个性进行图像说明
Enhanced Bayesian Compression via Deep Reinforcement Learning通过深度强化学习增强贝叶斯压缩
Enhanced Pix2pix Dehazing Network增强的 Pix2pix 去雾网络
Enhancing Diversity of Defocus Blur Detectors via Cross-Ensemble Network通过交叉集成网络增强散焦模糊检测器的多样性
Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification增强 TripleGAN 用于半监督条件实例合成和分类
Ensemble Deep Manifold Similarity Learning Using Hard Proxies使用硬代理进行集成深度流形相似性学习
ESIR_ End-To-End Scene Text Recognition via Iterative Image RectificationESIR_通过迭代图像校正的端到端场景文本识别
ESPNetv2_ A Light-Weight, Power Efficient, and General Purpose Convolutional Neural NetworkESPNetv2_ 一种轻量级、高能效且通用的卷积神经网络
Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video从单目视频估计人-物交互的 3D 运动和力
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks通过平移不变攻击规避对可转移对抗样本的防御
Event Cameras, Contrast Maximization and Reward Functions_ An Analysis事件相机、对比度最大化和奖励函数_分析
Event-Based High Dynamic Range Image and Very High Frame Rate Video Generation Using Conditional Generative Adversarial Networks使用条件生成对抗网络生成基于事件的高动态范围图像和超高帧率视频
EventNet_ Asynchronous Recursive Event ProcessingEventNet_异步递归事件处理
Events-To-Video_ Bringing Modern Computer Vision to Event Cameras事件到视频_将现代计算机视觉带入事件摄像机
EV-Gait_ Event-Based Robust Gait Recognition Using Dynamic Vision SensorsEV-Gait_使用动态视觉传感器的基于事件的稳健步态识别
Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables通过具有潜在变量的结构化输出学习对图像字幕进行精确对抗攻击
Example-Guided Style-Consistent Image Synthesis From Semantic Labeling基于语义标签的示例引导风格一致的图像合成
Explainability Methods for Graph Convolutional Neural Networks图卷积神经网络的可解释性方法
Explainable and Explicit Visual Reasoning Over Scene Graphs基于场景图的可解释和显式视觉推理
Explicit Bias Discovery in Visual Question Answering Models视觉问答模型中的显式偏差发现
Explicit Spatial Encoding for Deep Local Descriptors深度局部描述符的显式空间编码
Exploiting Edge Features for Graph Neural Networks利用图神经网络的边缘特征
Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression利用内核稀疏性和熵进行可解释的 CNN 压缩
Exploiting Temporal Context for 3D Human Pose Estimation in the Wild在野外利用时间上下文进行 3D 人体姿势估计
Explore-Exploit Graph Traversal for Image Retrieval探索-利用图遍历进行图像检索
Exploring Context and Visual Pattern of Relationship for Scene Graph Generation探索场景图生成的上下文和视觉模式
Exploring Object Relation in Mean Teacher for Cross-Domain Detection探索 Mean Teacher 中的对象关系进行跨域检测
Exploring the Bounds of the Utility of Context for Object Detection探索用于对象检测的上下文效用的界限
Expressive Body Capture_ 3D Hands, Face, and Body From a Single Image富有表现力的身体捕捉_来自单个图像的 3D 手、脸和身体
Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion通过场景完成进行 RGB-D 扫描的极端相对姿态估计
Face Anti-Spoofing_ Model Matters, so Does Data人脸反欺骗_模型很重要，数据也很重要
Face Parsing With RoI Tanh-Warping使用 RoI Tanh-Warping 进行人脸解析
Face-Focused Cross-Stream Network for Deception Detection in Videos用于视频欺骗检测的人脸交叉流网络
Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally通过局部利用低等级标签相关性进行面部情绪分布学习
Factor Graph Attention因子图注意
FA-RPN_ Floating Region Proposals for Face DetectionFA-RPN_人脸检测的浮动区域建议
Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models通过深度卷积生成模型进行快速灵活的室内场景合成
Fast and Robust Multi-Person 3D Pose Estimation From Multiple Views来自多个视图的快速且稳健的多人 3D 姿势估计
Fast Human Pose Estimation快速人体姿势估计
Fast Interactive Object Annotation With Curve-GCN使用 Curve-GCN 进行快速交互式对象注释
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells通过辅助单元对紧凑语义分割模型的快速神经架构搜索
Fast Object Class Labelling via Speech通过语音快速标记对象类别
Fast Online Object Tracking and Segmentation_ A Unifying Approach快速在线对象跟踪和分割_一种统一的方法
Fast Single Image Reflection Suppression via Convex Optimization基于凸优化的快速单图像反射抑制
Fast Spatially-Varying Indoor Lighting Estimation快速空间变化的室内照明估计
Fast Spatio-Temporal Residual Network for Video Super-Resolution用于视频超分辨率的快速时空残差网络
Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks基于交互和传播网络的快速用户引导视频对象分割
Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech由词性引导的快速、多样化和准确的图像字幕
FastDraw_ Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction NetworkFastDraw_通过自适应顺序预测网络解决车道检测的长尾问题
FBNet_ Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchFBNet_ 基于可微神经架构搜索的硬件感知高效卷积网络设计
Feature Denoising for Improving Adversarial Robustness用于提高对抗鲁棒性的特征去噪
Feature Distillation_ DNN-Oriented JPEG Compression Against Adversarial Examples特征蒸馏_针对对抗样本的面向 DNN 的 JPEG 压缩
Feature Selective Anchor-Free Module for Single-Shot Object Detection用于单次目标检测的特征选择性无锚模块
Feature Space Perturbations Yield More Transferable Adversarial Examples特征空间扰动产生更多可转移的对抗样本
Feature Transfer Learning for Face Recognition With Under-Represented Data具有代表性数据不足的人脸识别的特征迁移学习
Feature-Level Frankenstein_ Eliminating Variations for Discriminative Recognition特征级科学怪人_消除差异识别
Feedback Adversarial Learning_ Spatial Feedback for Improving Generative Adversarial Networks反馈对抗学习_改进生成对抗网络的空间反馈
Feedback Network for Image Super-Resolution图像超分辨率反馈网络
FEELVOS_ Fast End-To-End Embedding Learning for Video Object SegmentationFEELVOS_ 视频对象分割的快速端到端嵌入学习
Few-Shot Adaptive Faster R-CNNFew-Shot Adaptive Faster R-CNN
Few-Shot Learning via Saliency-Guided Hallucination of Samples通过显着性引导的样本幻觉进行少量学习
Few-Shot Learning With Localization in Realistic Settings在现实环境中进行本地化的小样本学习
FickleNet_ Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic InferenceFickleNet_ 使用随机推理的弱和半监督语义图像分割
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration通过几何中值进行滤波器修剪以实现深度卷积神经网络加速
FilterReg_ Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist ParameterizationFilterReg_ 使用高斯滤波器和扭曲参数化的稳健且高效的概率点集配准
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal通过类别遍历为 Few-Shot 学习找到与任务相关的特征
FineGAN_ Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and DiscoveryFineGAN_ 用于细粒度对象生成和发现的无监督分层解缠结
Fitting Multiple Heterogeneous Models by Multi-Class Cascaded T-Linkage通过多类级联 T 链接拟合多个异构模型
FlowNet3D_ Learning Scene Flow in 3D Point CloudsFlowNet3D_ 在 3D 点云中学习场景流
FML_ Face Model Learning From VideosFML_ 从视频中学习人脸模型
FOCNet_ A Fractional Optimal Control Network for Image DenoisingFOCNet_一种用于图像去噪的分数最优控制网络
Focus Is All You Need_ Loss Functions for Event-Based Vision焦点就是你所需要的_基于事件的视觉的损失函数
Foreground-Aware Image Inpainting前景感知图像修复
Frame-Consistent Recurrent Video Deraining With Dual-Level Flow具有双级流的帧一致循环视频去雨
From Coarse to Fine_ Robust Hierarchical Localization at Large Scale从粗到细_大规模的鲁棒分层定位
From Recognition to Cognition_ Visual Commonsense Reasoning从识别到认知_视觉常识推理
FSA-Net_ Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single ImageFSA-Net_ Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a single image
Fully Automatic Video Colorization With Self-Regularization and Diversity具有自调节和多样性的全自动视频着色
Fully Learnable Group Convolution for Acceleration of Deep Neural Networks用于加速深度神经网络的完全可学习组卷积
Fully Quantized Network for Object Detection用于目标检测的全量化网络
F-VAEGAN-D2_ A Feature Generating Framework for Any-Shot LearningF-VAEGAN-D2_Any-Shot 学习的特征生成框架
Gait Recognition via Disentangled Representation Learning通过分离表示学习的步态识别
GA-Net_ Guided Aggregation Net for End-To-End Stereo MatchingGA-Net_端到端立体匹配的引导聚合网络
GANFIT_ Generative Adversarial Network Fitting for High Fidelity 3D Face ReconstructionGANFIT_ 用于高保真 3D 人脸重建的生成对抗网络拟合
Gaussian Temporal Awareness Networks for Action Localization用于动作定位的高斯时间感知网络
GCAN_ Graph Convolutional Adversarial Network for Unsupervised Domain AdaptationGCAN_ 用于无监督域自适应的图卷积对抗网络
Generalising Fine-Grained Sketch-Based Image Retrieval推广基于细粒度草图的图像检索
Generalizable Person Re-Identification by Domain-Invariant Mapping Network域不变映射网络的可泛化人员重新识别
Generalized Intersection Over Union_ A Metric and a Loss for Bounding Box Regression并集上的广义交集_边界框回归的度量和损失
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders通过对齐变分自动编码器进行广义零样本和少样本学习
Generalized Zero-Shot Recognition Based on Visually Semantic Embedding基于视觉语义嵌入的广义零样本识别
Generalizing Eye Tracking With Bayesian Adversarial Learning用贝叶斯对抗学习概括眼动追踪
Generating 3D Adversarial Point Clouds生成 3D 对抗点云
Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning使用 GNN 去噪自动编码器为 Few-Shot 学习生成分类权重
Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network使用混合密度网络为 3D 人体姿态估计生成多个假设
Generative Dual Adversarial Network for Generalized Zero-Shot Learning用于广义零样本学习的生成对偶对抗网络
Geometry-Aware Distillation for Indoor Semantic Segmentation用于室内语义分割的几何感知蒸馏
Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation单目深度估计的几何感知对称域自适应
Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping用于单面无监督域映射的几何一致生成对抗网络
GeoNet_ Deep Geodesic Networks for Point Cloud AnalysisGeoNet_ 用于点云分析的深度测地线网络
GFrames_ Gradient-Based Local Reference Frame for 3D Shape MatchingGFrames_ 用于 3D 形状匹配的基于梯度的局部参考框架
GIF2Video_ Color Dequantization and Temporal Interpolation of GIF ImagesGIF2Video_ GIF 图像的颜色去量化和时间插值
Global Second-Order Pooling Convolutional Networks全局二阶池化卷积网络
Good News, Everyone! Context Driven Entity-Aware Captioning for News Images好消息，大家！新闻图像的上下文驱动的实体感知字幕
Gotta Adapt 'Em All_ Joint Pixel and Feature-Level Domain Adaptation for Recognition in the WildGotta Adapt 'Em All_Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
GPSfM_ Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental MatricesGPSfM_在多视图基本矩阵上使用代数约束的全局投影 SFM
GQA_ A New Dataset for Real-World Visual Reasoning and Compositional Question AnsweringGQA_真实世界视觉推理和组合问答的新数据集
Gradient Matching Generative Networks for Zero-Shot Learning用于零样本学习的梯度匹配生成网络
Graph Attention Convolution for Point Cloud Semantic Segmentation点云语义分割的图注意力卷积
Graph Convolutional Label Noise Cleaner_ Train a Plug-And-Play Action Classifier for Anomaly DetectionGraph Convolutional Label Noise Cleaner_训练一个即插即用的动作分类器进行异常检测
Graph Convolutional Tracking图卷积跟踪
Graph-Based Global Reasoning Networks基于图的全局推理网络
Graphical Contrastive Losses for Scene Graph Parsing场景图解析的图形对比损失
Graphonomy_ Universal Human Parsing via Graph Transfer LearningGraphonomy_通过图迁移学习进行通用人类解析
Greedy Structure Learning of Hierarchical Compositional Models层次组合模型的贪心结构学习
Grid R-CNN网格 R-CNN
Grounded Video Description接地视频说明
Grounding Human-To-Vehicle Advice for Self-Driving Vehicles为自动驾驶车辆提供人对车辆建议
Group Sampling for Scale Invariant Face Detection用于尺度不变人脸检测的组采样
Group-Wise Correlation Stereo Network分组相关立体网络
GS3D_ An Efficient 3D Object Detection Framework for Autonomous DrivingGS3D_自动驾驶的高效 3D 目标检测框架
GSPN_ Generative Shape Proposal Network for 3D Instance Segmentation in Point CloudGSPN_ 用于点云中 3D 实例分割的生成形状建议网络
Guaranteed Matrix Completion Under Multiple Linear Transformations多重线性变换下的保证矩阵完成
Guided Stereo Matching引导式立体匹配
H+O_ Unified Egocentric Recognition of 3D Hand-Object Poses and InteractionsH+O_ 3D 手物体姿势和交互的统一以自我为中心的识别
Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning使用对抗学习的低资源脚本中的手写识别
HAQ_ Hardware-Aware Automated Quantization With Mixed PrecisionHAQ_ 混合精度的硬件感知自动量化
Hardness-Aware Deep Metric Learning硬度感知深度度量学习
Heavy Rain Image Restoration_ Integrating Physics Model and Conditional Adversarial Learning暴雨图像恢复_集成物理模型和条件对抗学习
HetConv_ Heterogeneous Kernel-Based Convolutions for Deep CNNsHetConv_ 用于深度 CNN 的基于异构内核的卷积
Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering用于视频问答的异构记忆增强多模态注意模型
Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss具有动态像素损失的分层跨模态说话人脸生成
Hierarchical Deep Stereo Matching on High-Resolution Images高分辨率图像的分层深度立体匹配
Hierarchical Discrete Distribution Decomposition for Match Density Estimation匹配密度估计的分层离散分布分解
Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning用于零样本学习的判别性潜在特征的分层解耦
Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction用于 3D 场景布局预测的层次去噪递归自动编码器
High Flux Passive Imaging With Single-Photon Sensors使用单光子传感器的高通量无源成像
High-Level Semantic Feature Detection_ A New Perspective for Pedestrian Detection高级语义特征检测_行人检测的新视角
High-Quality Face Capture Using Anatomical Muscles使用解剖肌肉进行高质量面部捕捉
Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images_ Learning From Radiology Reports and Label Ontology对不同 CT 图像的临床显着发现进行整体和综合注释_从放射学报告和标签本体中学习
HoloPose_ Holistic 3D Human Reconstruction In-The-WildHoloPose_野外整体3D人体重建
Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation用于不成对图像到图像转换的同态潜在空间插值
HorizonNet_ Learning Room Layout With 1D Representation and Pano Stretch Data AugmentationHorizonNet_ 具有一维表示和全景拉伸数据增强的学习室布局
How to Make a Pizza_ Learning a Compositional Layer-Based GAN Model如何制作披萨_学习基于组合层的 GAN 模型
HPLFlowNet_ Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point CloudsHPLFlowNet_ Hierarchical Permutohedral Lattice FlowNet 用于大规模点云上的场景流估计
Hybrid Scene Compression for Visual Localization用于视觉定位的混合场景压缩
Hybrid Task Cascade for Instance Segmentation用于实例分割的混合任务级联
Hybrid-Attention Based Decoupled Metric Learning for Zero-Shot Image Retrieval用于零样本图像检索的基于混合注意力的解耦度量学习
Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior使用深度空间光谱先验的高光谱图像重建
Hyperspectral Image Super-Resolution With Optimized RGB Guidance具有优化 RGB 引导的高光谱图像超分辨率
Hyperspectral Imaging With Random Printed Mask随机印刷掩模的高光谱成像
IGE-Net_ Inverse Graphics Energy Networks for Human Pose Estimation and Single-View ReconstructionIGE-Net_用于人体姿态估计和单视图重建的逆图形能量网络
Im2Pencil_ Controllable Pencil Illustration From PhotographsIm2Pencil_照片中的可控铅笔插图
Image Deformation Meta-Networks for One-Shot Learning用于一次性学习的图像变形元网络
Image Generation From Layout从布局生成图像
Image Super-Resolution by Neural Texture Transfer神经纹理转移的图像超分辨率
Image-Question-Answer Synergistic Network for Visual Dialog视觉对话的图像问答协同网络
Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation通过 Group-Wise Deep Whitening-and-Coloring 转换的图像到图像转换
IM-Net for High Resolution Video Frame Interpolation用于高分辨率视频帧插值的 IM-Net
Importance Estimation for Neural Network Pruning神经网络剪枝的重要性估计
Improved Road Connectivity by Joint Learning of Orientation and Segmentation通过方向和分段的联合学习改善道路连通性
Improving Action Localization by Progressive Cross-Stream Cooperation通过渐进的跨流合作提高行动本地化
Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis通过注视重定向合成改进 Few-Shot 用户特定注视适应
Improving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing通过跨模态注意力引导擦除改进引用表达式基础
Improving Semantic Segmentation via Video Propagation and Label Relaxation通过视频传播和标签松弛改进语义分割
Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition With Multimodal Training通过多模态训练提高单模态动态手势识别的性能
Improving Transferability of Adversarial Examples With Input Diversity通过输入多样性提高对抗性示例的可迁移性
In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images为道路驾驶图像的实时语义分割保护预训练的 ImageNet 架构
In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations在野外使用显式 2D 特征和中间 3D 表示进行人体姿势估计
Incremental Object Learning From Contiguous Views从连续视图中增量对象学习
Information Maximizing Visual Question Generation最大化视觉问题生成的信息
Informative Object Annotations_ Tell Me Something I Don’t Know信息丰富的对象注释_告诉我一些我不知道的事情
Inserting Videos Into Videos将视频插入视频
Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth通过联合优化空间嵌入和聚类带宽进行实例分割
Instance-Level Meta Normalization实例级元规范化
Intention Oriented Image Captions With Guiding Objects带有引导对象的面向意图的图像说明
Interaction-And-Aggregation Network for Person Re-Identification用于人员重新识别的交互聚合网络
Interactive Full Image Segmentation by Considering All Regions Jointly联合考虑所有区域的交互式全图像分割
Interactive Image Segmentation via Backpropagating Refinement Scheme通过反向传播细化方案进行交互式图像分割
Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks卷积神经网络的可解释和细粒度的视觉解释
Interpreting CNNs via Decision Trees通过决策树解释 CNN
Invariance Matters_ Exemplar Memory for Domain Adaptive Person Re-Identification不变性很重要_域自适应人员重新识别的示例记忆
Inverse Cooking_ Recipe Generation From Food Images逆向烹饪_从食物图像生成食谱
Inverse Discriminative Networks for Handwritten Signature Verification用于手写签名验证的逆判别网络
Inverse Path Tracing for Joint Material and Lighting Estimation关节材料和照明估计的反向路径跟踪
Inverse Procedural Modeling of Knitwear针织品的逆过程建模
InverseRenderNet_ Learning Single Image Inverse RenderingInverseRenderNet_学习单幅图像逆向渲染
IP102_ A Large-Scale Benchmark Dataset for Insect Pest RecognitionIP102_虫害识别的大规模基准数据集
IRLAS_ Inverse Reinforcement Learning for Architecture SearchIRLAS_架构搜索的逆强化学习
Isospectralization, or How to Hear Shape, Style, and Correspondence等光谱化，或如何听到形状、风格和对应
Iterative Alignment Network for Continuous Sign Language Recognition用于连续手语识别的迭代对齐网络
Iterative Normalization_ Beyond Standardization Towards Efficient Whitening迭代归一化_超越标准化走向高效美白
Iterative Projection and Matching_ Finding Structure-Preserving Representatives and Its Application to Computer Vision迭代投影与匹配_寻找结构保持代表及其在计算机视觉中的应用
Iterative Reorganization With Weak Spatial Constraints_ Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning具有弱空间约束的迭代重组_解决无监督表示学习的任意拼图游戏
Iterative Residual CNNs for Burst Photography Applications用于突发摄影应用的迭代残差 CNN
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation联合光流和遮挡估计的迭代残差改进
It’s Not About the Journey; It’s About the Destination_ Following Soft Paths Under Question-Guidance for Visual Reasoning这与旅程无关；它是关于目的地_在视觉推理问题指导下遵循软路径
Joint Discriminative and Generative Learning for Person Re-Identification人重新识别的联合判别和生成学习
Joint Face Detection and Facial Motion Retargeting for Multiple Faces多人脸的联合人脸检测和面部运动重定向
Joint Manifold Diffusion for Combining Predictions on Decoupled Observations用于组合解耦观测预测的联合流形扩散
Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation面部动作单元强度估计的联合表示和估计学习
Joint Representative Selection and Feature Learning_ A Semi-Supervised Approach联合代表选择和特征学习_一种半监督方法
JSIS3D_ Joint Semantic-Instance Segmentation of 3D Point Clouds With Multi-Task Pointwise Networks and Multi-Value Conditional Random FieldsJSIS3D_ 具有多任务点状网络和多值条件随机场的 3D 点云的联合语义实例分割
Jumping Manifolds_ Geometry Aware Dense Non-Rigid Structure From Motion跳跃歧管_运动中的几何感知密集非刚性结构
KE-GAN_ Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene ParsingKE-GAN_用于半监督场景解析的知识嵌入式生成对抗网络
Kernel Transformer Networks for Compact Spherical Convolution用于紧凑球形卷积的核变换器网络
Kervolutional Neural Networks卷积神经网络
K-Nearest Neighbors HashingK-最近邻哈希
Knockoff Nets_ Stealing Functionality of Black-Box ModelsKnockoff Nets_黑盒模型的窃取功能
Knowing When to Stop_ Evaluation and Verification of Conformity to Output-Size Specifications知道何时停止_输出尺寸规格符合性的评估和验证
Knowledge Adaptation for Efficient Semantic Segmentation高效语义分割的知识适应
Knowledge Distillation via Instance Relationship Graph通过实例关系图进行知识蒸馏
Knowledge-Embedded Routing Network for Scene Graph Generation用于场景图生成的知识嵌入式路由网络
L3-Net_ Towards Learning Based LiDAR Localization for Autonomous DrivingL3-Net_ 面向自动驾驶的基于学习的 LiDAR 定位
Label Efficient Semi-Supervised Learning via Graph Filtering通过图过滤标记高效的半监督学习
Label Propagation for Deep Semi-Supervised Learning深度半监督学习的标签传播
Label-Noise Robust Generative Adversarial Networks标签噪声鲁棒生成对抗网络
LAEO-Net_ Revisiting People Looking at Each Other in VideosLAEO-Net_重温视频中互相注视的人
LAF-Net_ Locally Adaptive Fusion Networks for Stereo Confidence EstimationLAF-Net_ 用于立体置信度估计的局部自适应融合网络
Language-Driven Temporal Activity Localization_ A Semantic Matching Reinforcement Learning Model语言驱动的时间活动本地化_一种语义匹配强化学习模型
Large Scale High-Resolution Land Cover Mapping With Multi-Resolution Data具有多分辨率数据的大规模高分辨率土地覆盖制图
Large Scale Incremental Learning大规模增量学习
Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks使用 Kronecker 因子近似曲率对深度卷积神经网络进行大规模分布式二阶优化
Large-Scale Few-Shot Learning_ Knowledge Transfer With Class Hierarchy大规模小样本学习_基于类层次结构的知识迁移
Large-Scale Interactive Object Segmentation With Human Annotators使用人工注释器进行大规模交互式对象分割
Large-Scale Long-Tailed Recognition in an Open World开放世界中的大规模长尾识别
Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition用于视频动作识别的大规模弱监督预训练
Large-Scale, Metric Structure From Motion for Unordered Light Fields无序光场运动的大规模度量结构
LaserNet_ An Efficient Probabilistic 3D Object Detector for Autonomous DrivingLaserNet_一种用于自动驾驶的高效概率 3D 物体检测器
LaSO_ Label-Set Operations Networks for Multi-Label Few-Shot LearningLaSO_ 用于多标签少样本学习的标签集操作网络
LaSOT_ A High-Quality Benchmark for Large-Scale Single Object TrackingLaSOT_大规模单目标跟踪的高质量基准
Latent Filter Scaling for Multimodal Unsupervised Image-To-Image Translation用于多模态无监督图像到图像转换的潜在滤波器缩放
Latent Space Autoregression for Novelty Detection用于新奇检测的潜在空间自回归
Layout-Graph Reasoning for Fashion Landmark Detection时尚地标检测的布局图推理
LBS Autoencoder_ Self-Supervised Fitting of Articulated Meshes to Point CloudsLBS Autoencoder_ 关节网格到点云的自监督拟合
Learning 3D Human Dynamics From Video从视频中学习 3D 人体动力学
Learning a Deep ConvNet for Multi-Label Classification With Partial Labels使用部分标签学习用于多标签分类的深度卷积网络
Learning a Unified Classifier Incrementally via Rebalancing通过再平衡逐步学习统一分类器
Learning Active Contour Models for Medical Image Segmentation学习用于医学图像分割的主动轮廓模型
Learning Actor Relation Graphs for Group Activity Recognition学习用于群体活动识别的演员关系图
Learning Attraction Field Representation for Robust Line Segment Detection学习用于鲁棒线段检测的吸引力场表示
Learning Binary Code for Personalized Fashion Recommendation学习个性化时尚推荐的二进制代码
Learning Channel-Wise Interactions for Binary Convolutional Neural Networks学习二元卷积神经网络的通道交互
Learning Context Graph for Person Search学习人物搜索的上下文图
Learning Correspondence From the Cycle-Consistency of Time从时间的循环一致性中学习对应
Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food Images使用对抗网络学习用于烹饪食谱和食物图像的跨模态嵌入
Learning for Single-Shot Confidence Calibration in Deep Neural Networks Through Stochastic Inferences通过随机推断学习深度神经网络中的单次置信度校准
Learning From Noisy Labels by Regularized Estimation of Annotator Confusion通过注释器混淆的正则化估计从噪声标签中学习
Learning From Synthetic Data for Crowd Counting in the Wild从合成数据中学习野外人群计数
Learning Image and Video Compression Through Spatial-Temporal Energy Compaction通过时空能量压缩学习图像和视频压缩
Learning Implicit Fields for Generative Shape Modeling学习用于生成形状建模的隐式字段
Learning Independent Object Motion From Unlabelled Stereoscopic Videos从未标记的立体视频中学习独立的物体运动
Learning Individual Styles of Conversational Gesture学习会话手势的个人风格
Learning Instance Activation Maps for Weakly Supervised Instance Segmentation学习用于弱监督实例分割的实例激活图
Learning Joint Gait Representation via Quintuplet Loss Minimization通过五元组损失最小化学习联合步态表示
Learning Joint Reconstruction of Hands and Manipulated Objects学习手和操作物体的联合重建
Learning Linear Transformations for Fast Image and Video Style Transfer学习用于快速图像和视频风格迁移的线性变换
Learning Loss for Active Learning主动学习的学习损失
Learning Metrics From Teachers_ Compact Networks for Image Embedding从教师那里学习指标_用于图像嵌入的紧凑网络
Learning Monocular Depth Estimation Infusing Traditional Stereo Knowledge学习注入传统立体知识的单目深度估计
Learning Multi-Class Segmentations From Single-Class Datasets从单类数据集中学习多类分割
Learning Non-Volumetric Depth Fusion Using Successive Reprojections使用连续重投影学习非体积深度融合
Learning Not to Learn_ Training Deep Neural Networks With Biased Data学习不学习_用有偏差的数据训练深度神经网络
Learning Parallax Attention for Stereo Image Super-Resolution学习立体图像超分辨率的视差注意
Learning Personalized Modular Network Guided by Structured Knowledge学习结构化知识引导下的个性化模块化网络
Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting用于高质量图像修复的金字塔上下文编码器网络
Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos视频异常检测的骨架轨迹学习规律
Learning RoI Transformer for Oriented Object Detection in Aerial Images学习用于航空图像中定向目标检测的 RoI Transformer
Learning Semantic Segmentation From Synthetic Data_ A Geometrically Guided Input-Output Adaptation Approach从合成数据中学习语义分割_一种几何引导的输入输出自适应方法
Learning Shape-Aware Embedding for Scene Text Detection学习用于场景文本检测的形状感知嵌入
Learning Single-Image Depth From Videos Using Quality Assessment Networks使用质量评估网络从视频中学习单图像深度
Learning Spatial Common Sense With Geometry-Aware Recurrent Networks使用几何感知循环网络学习空间常识
Learning Spatio-Temporal Representation With Local and Global Diffusion通过局部和全局扩散学习时空表示
Learning Structure-And-Motion-Aware Rolling Shutter Correction学习结构和运动感知滚动快门校正
Learning the Depths of Moving People by Watching Frozen People通过观看冰冻的人来学习感动人的深度
Learning to Adapt for Stereo学习适应立体声
Learning to Calibrate Straight Lines for Fisheye Image Rectification学习校准鱼眼图像校正的直线
Learning to Cluster Faces on an Affinity Graph学习在亲和图上聚类人脸
Learning to Compose Dynamic Tree Structures for Visual Contexts学习为视觉上下文构建动态树结构
Learning to Detect Human-Object Interactions With Knowledge学习用知识检测人与物体的交互
Learning to Explain With Complemental Examples学习用互补的例子来解释
Learning to Explore Intrinsic Saliency for Stereoscopic Video学习探索立体视频的内在显着性
Learning to Extract Flawless Slow Motion From Blurry Videos学习从模糊视频中提取完美的慢动作
Learning to Film From Professional Human Motion Videos从专业的人体运动视频中学习拍摄
Learning to Generate Synthetic Data via Compositing学习通过合成生成合成数据
Learning to Learn From Noisy Labeled Data学习从嘈杂的标记数据中学习
Learning to Learn How to Learn_ Self-Adaptive Visual Navigation Using Meta-Learning学习学习如何学习_使用元学习的自适应视觉导航
Learning to Learn Image Classifiers With Visual Analogy学习用视觉类比学习图像分类器
Learning to Learn Relation for Important People Detection in Still Images学习学习静止图像中重要人物检测的关系
Learning to Localize Through Compressed Binary Maps通过压缩二进制地图学习本地化
Learning to Minify Photometric Stereo学习缩小光度立体
Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss通过使用任务损失优化量化间隔来学习量化深度网络
Learning to Reconstruct People in Clothing From a Single RGB Camera学习从单个 RGB 相机重建服装中的人物
Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification学习减少红外可见人员重新识别的双重差异
Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision在没有 3D 监督的情况下学习从图像中回归 3D 面部形状和表情
Learning to Remember_ A Synaptic Plasticity Driven Framework for Continual Learning学习记忆_持续学习的突触可塑性驱动框架
Learning to Sample学习采样
Learning to Separate Multiple Illuminants in a Single Image学习在单个图像中分离多个光源
Learning to Synthesize Motion Blur学习合成运动模糊
Learning to Transfer Examples for Partial Domain Adaptation学习迁移示例以进行部分域适应
Learning Transformation Synchronization学习转换同步
Learning Unsupervised Video Object Segmentation Through Visual Attention通过视觉注意学习无监督视频对象分割
Learning Video Representations From Correspondence Proposals从信函提案中学习视频表示
Learning View Priors for Single-View 3D Reconstruction学习单视图 3D 重建的视图先验
Learning With Batch-Wise Optimal Transport Loss for 3D Shape Recognition3D 形状识别的批量优化传输损失学习
Learning Without Memorizing学习不死记硬背
Learning Words by Drawing Images通过绘图学习单词
Learning-Based Sampling for Natural Image Matting基于学习的自然图像抠图采样
Led3D_ A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D FacesLed3D_一种识别低质量3D人脸的轻量级高效深度方法
Lending Orientation to Neural Networks for Cross-View Geo-Localization借用神经网络的方向来进行跨视图地理定位
Less Is More_ Learning Highlight Detection From Video Duration少即是多_从视频时长学习高光检测
Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery利用众包 GPS 数据从航空影像中提取道路
Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting利用异构辅助任务来辅助人群计数
Leveraging Shape Completion for 3D Siamese Tracking利用形状完成进行 3D 连体跟踪
Leveraging the Invariant Side of Generative Zero-Shot Learning利用生成式零样本学习的不变性
Libra R-CNN_ Towards Balanced Learning for Object DetectionLibra R-CNN_ 面向对象检测的平衡学习
LiFF_ Light Field Features in Scale and DepthLiFF_ 规模和深度的光场特征
Lifting Vectorial Variational Problems_ A Natural Formulation Based on Geometric Measure Theory and Discrete Exterior Calculus提升向量变分问题_基于几何测度理论和离散外微积分的自然公式
Light Field Messaging With Deep Photographic Steganography具有深度摄影隐写术的光场消息传递
Linkage Based Face Clustering via Graph Convolution Network基于图卷积网络的基于链接的人脸聚类
Listen to the Image听图像
LiveSketch_ Query Perturbations for Guided Sketch-Based Visual SearchLiveSketch_ 基于引导草图的视觉搜索的查询扰动
Local Detection of Stereo Occlusion Boundaries立体遮挡边界的局部检测
Local Features and Visual Words Emerge in Activations局部特征和视觉词出现在激活中
Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection用于面部动作单元检测的人特定形状正则化的局部关系学习
Local Temporal Bilinear Pooling for Fine-Grained Action Parsing用于细粒度动作解析的局部时间双线性池
Local to Global Learning_ Gradually Adding Classes for Training Deep Neural Networks从局部到全局学习_逐渐增加训练深度神经网络的类
Locating Objects Without Bounding Boxes在没有边界框的情况下定位对象
LO-Net_ Deep Real-Time Lidar OdometryLO-Net_深度实时激光雷达里程计
Long-Term Feature Banks for Detailed Video Understanding用于详细视频理解的长期特征库
Look Back and Predict Forward in Image Captioning在图像字幕中回顾和预测
Look More Than Once_ An Accurate Detector for Text of Arbitrary Shapes多看一次_任意形状文本的准确检测器
Looking for the Devil in the Details_ Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition在细节中寻找魔鬼_学习Trilinear Attention Sampling Network for Fine-Grained Image Recognition
Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition用于鲁棒人脸识别的低秩拉普拉斯均匀混合模型
Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms由可逆线性变换诱导的新张量核范数的低秩张量补全
LP-3DCNN_ Unveiling Local Phase in 3D Convolutional Neural NetworksLP-3DCNN_ 揭示 3D 卷积神经网络中的局部相位
LSTA_ Long Short-Term Attention for Egocentric Action RecognitionLSTA_以自我为中心的动作识别的长期短期注意力
LVIS_ A Dataset for Large Vocabulary Instance SegmentationLVIS_大词汇量实例分割的数据集
Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds机器视觉引导的 3D 医学图像压缩，用于云中的高效传输和准确分割
MAGSAC_ Marginalizing Sample ConsensusMAGSAC_边缘化样本共识
MAN_ Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph AdjustmentMAN_ Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment
ManTra-Net_ Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous FeaturesManTra-Net_ 用于检测和定位具有异常特征的图像伪造的操纵跟踪网络
MAP Inference via Block-Coordinate Frank-Wolfe Algorithm通过块坐标 Frank-Wolfe 算法进行 MAP 推理
Mapping, Localization and Path Planning for Image-Based Navigation Using Visual Features and Map使用视觉特征和地图的基于图像的导航的映射、定位和路径规划
Marginalized Latent Semantic Encoder for Zero-Shot Learning用于零样本学习的边缘化潜在语义编码器
MARS_ Motion-Augmented RGB Stream for Action RecognitionMARS_用于动作识别的运动增强 RGB 流
Mask Scoring R-CNN掩码评分 R-CNN
Mask-Guided Portrait Editing With Conditional GANs使用条件 GAN 进行蒙版引导的人像编辑
MaxpoolNMS_ Getting Rid of NMS Bottlenecks in Two-Stage Object DetectorsMaxpoolNMS_ 摆脱两阶段目标检测器中的 NMS 瓶颈
Max-Sliced Wasserstein Distance and Its Use for GANs最大切片 Wasserstein 距离及其在 GAN 中的用途
MBS_ Macroblock Scaling for CNN Model ReductionMBS_ 用于 CNN 模型缩减的宏块缩放
Memory in Memory_ A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics记忆中的记忆_从时空动力学中学习高阶非平稳性的预测神经网络
Memory-Attended Recurrent Network for Video Captioning用于视频字幕的内存参与循环网络
MeshAdv_ Adversarial Meshes for Visual RecognitionMeshAdv_ 用于视觉识别的对抗网格
MetaCleaner_ Learning to Hallucinate Clean Representations for Noisy-Labeled Visual RecognitionMetaCleaner_ 学习幻觉清洁表示以进行带噪声标记的视觉识别
Meta-Learning Convolutional Neural Architectures for Multi-Target Concrete Defect Classification With the COncrete DEfect BRidge IMage Dataset使用混凝土缺陷桥图像数据集进行多目标混凝土缺陷分类的元学习卷积神经架构
Meta-Learning With Differentiable Convex Optimization具有可微凸优化的元学习
Meta-SR_ A Magnification-Arbitrary Network for Super-ResolutionMeta-SR_超分辨率的任意放大网络
Meta-Transfer Learning for Few-Shot Learning少样本学习的元迁移学习
Metric Learning for Image Registration图像配准的度量学习
MFAS_ Multimodal Fusion Architecture SearchMFAS_多模式融合架构搜索
MHP-VOS_ Multiple Hypotheses Propagation for Video Object SegmentationMHP-VOS_视频对象分割的多假设传播
Mind Your Neighbours_ Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks注意你的邻居_使用元数据邻域图共同注意网络进行图像注释
Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment3D 多扫描对齐中的 Mini-Loop Closures 的最小求解器
Min-Max Statistical Alignment for Transfer Learning迁移学习的最小-最大统计对齐
MirrorGAN_ Learning Text-To-Image Generation by RedescriptionMirrorGAN_通过重新描述学习文本到图像的生成
Mitigating Information Leakage in Image Representations_ A Maximum Entropy Approach减轻图像表示中的信息泄漏_最大熵方法
Mixed Effects Neural Networks (MeNets) With Applications to Gaze Estimation用于注视估计的混合效应神经网络 (MeNet)
Mixture Density Generative Adversarial Networks混合密度生成对抗网络
MMFace_ A Multi-Metric Regression Network for Unconstrained Face ReconstructionMMFace_一种用于无约束人脸重建的多度量回归网络
MnasNet_ Platform-Aware Neural Architecture Search for MobileMnasNet_面向移动设备的平台感知神经架构搜索
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis用于多样化图像合成的模式寻求生成对抗网络
Model-Blind Video Denoising via Frame-To-Frame Training通过帧到帧训练的模型盲视频去噪
Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN使用 Geo-CNN 对 3D 点云的局部几何结构进行建模
Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling使用自注意力和 Gumbel 子集采样对点云进行建模
Modularized Textual Grounding for Counterfactual Resilience反事实弹性的模块化文本基础
Modulating Image Restoration With Continual Levels via Adaptive Feature Modification Layers通过自适应特征修改层调制具有连续级别的图像恢复
Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction利用准确的建议和形状重建的单目 3D 对象检测
Monocular Depth Estimation Using Relative Depth Maps使用相对深度图的单目深度估计
Monocular Total Capture_ Posing Face, Body, and Hands in the Wild单目全摄_野外摆脸、身、手
Motion Estimation of Non-Holonomic Ground Vehicles From a Single Feature Correspondence Measured Over N Views从 N 个视图上测量的单个特征对应关系对非完整地面车辆的运动估计
MOTS_ Multi-Object Tracking and SegmentationMOTS_多目标跟踪和分割
Moving Object Detection Under Discontinuous Change in Illumination Using Tensor Low-Rank and Invariant Sparse Decomposition使用张量低秩和不变稀疏分解的光照不连续变化下的运动目标检测
MSCap_ Multi-Style Image Captioning With Unpaired Stylized TextMSCap_ 带有未配对风格化文本的多样式图像字幕
MS-TCN_ Multi-Stage Temporal Convolutional Network for Action SegmentationMS-TCN_ 用于动作分割的多阶段时间卷积网络
Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection用于人脸呈现攻击检测的多对抗判别深度域泛化
Multi-Agent Tensor Fusion for Contextual Trajectory Prediction用于上下文轨迹预测的多智能体张量融合
Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image Translation具有级联语义指导的多通道注意力选择 GAN 用于跨视图图像翻译
Multi-Granularity Generator for Temporal Action Proposal时间行动建议的多粒度生成器
Multi-Label Image Recognition With Graph Convolutional Networks图卷积网络的多标签图像识别
Multi-Level Context Ultra-Aggregation for Stereo Matching用于立体匹配的多级上下文超聚合
Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding用于图像短语接地的多级多模态公共语义空间
Multimodal Explanations by Predicting Counterfactuality in Videos通过预测视频中的反事实进行多模态解释
Multi-Person Articulated Tracking With Spatial and Temporal Embeddings具有空间和时间嵌入的多人关节式跟踪
Multi-Person Pose Estimation With Enhanced Channel-Wise and Spatial Information具有增强的通道和空间信息的多人姿势估计
Multi-Scale Geometric Consistency Guided Multi-View Stereo多尺度几何一致性引导多视图立体
Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning用于深度度量学习的通用对加权的多重相似性损失
Multi-Source Weak Supervision for Saliency Detection显着性检测的多源弱监督
Multispectral and Hyperspectral Image Fusion by MS_HS Fusion NetMS_HS Fusion Net的多光谱和高光谱图像融合
Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgrounds多光谱成像对复杂背景上的粉末进行细粒度识别
Multi-Step Prediction of Occupancy Grid Maps With Recurrent Neural Networks使用循环神经网络的占用网格图的多步预测
Multi-Target Embodied Question Answering多目标体现问答
Multi-Task Learning of Hierarchical Vision-Language Representation分层视觉语言表示的多任务学习
Multi-Task Multi-Sensor Fusion for 3D Object Detection用于 3D 对象检测的多任务多传感器融合
Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations通过回收边界框注释的多任务自监督目标检测
Multiview 2D_3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation通过兴趣点网络进行多视图 2D_3D 刚性配准以进行跟踪和三角测量
MUREL_ Multimodal Relational Reasoning for Visual Question AnsweringMUREL_视觉问答的多模态关系推理
Mutual Learning of Complementary Networks via Residual Correction for Improving Semi-Supervised Classification通过残差校正的互补网络相互学习改进半监督分类
MVF-Net_ Multi-View 3D Face Morphable Model RegressionMVF-Net_Multi-View 3D Face Morphable Model Regression
MVTec AD – A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionMVTec AD——用于无监督异常检测的综合真实世界数据集
NAS-FPN_ Learning Scalable Feature Pyramid Architecture for Object DetectionNAS-FPN_ 用于对象检测的学习可扩展特征金字塔架构
Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold Discrimination具有显式自然流形判别的自然逼真的单图像超分辨率
NDDR-CNN_ Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality ReductionNDDR-CNN_ 通过神经判别降维在多任务 CNN 中进行分层特征融合
Neighbourhood Watch_ Referring Expression Comprehension via Language-Guided Graph Attention NetworksNeighborhood Watch_通过语言引导的图注意网络引用表达理解
Nesti-Net_ Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural NetworksNesti-Net_ 使用卷积神经网络的非结构化 3D 点云的法线估计
NetTailor_ Tuning the Architecture, Not Just the WeightsNetTailor_ 调整架构，而不仅仅是权重
Networks for Joint Affine and Non-Parametric Image Registration联合仿射和非参数图像配准网络
Neural Illumination_ Lighting Prediction for Indoor Environments神经照明_室内环境的照明预测
Neural Rejuvenation_ Improving Deep Network Training by Enhancing Computational Resource Utilization神经再生_通过提高计算资源利用率来改进深度网络训练
Neural Rerendering in the Wild野外的神经重新渲染
Neural RGB®D Sensing_ Depth and Uncertainty From a Video Camera神经 RGB®D 传感_来自摄像机的深度和不确定性
Neural Scene Decomposition for Multi-Person Motion Capture用于多人动作捕捉的神经场景分解
Neural Sequential Phrase Grounding (SeqGROUND)神经顺序短语接地 (SeqGROUND)
Neural Task Graphs_ Generalizing to Unseen Tasks From a Single Video Demonstration神经任务图_从单个视频演示中推广到看不见的任务
Neuro-Inspired Eye Tracking With Eye Movement Dynamics具有眼动动力学的神经启发式眼动追踪
NM-Net_ Mining Reliable Neighbors for Robust Feature CorrespondencesNM-Net_ 挖掘可靠的邻居以获得鲁棒的特征对应
Noise2Void - Learning Denoising From Single Noisy ImagesNoise2Void - 从单个嘈杂图像中学习去噪
Noise-Aware Unsupervised Deep Lidar-Stereo Fusion噪声感知无监督深度激光雷达立体融合
Noise-Tolerant Paradigm for Training Face Recognition CNNs用于训练人脸识别 CNN 的噪声容忍范式
Non-Adversarial Image Synthesis With Generative Latent Nearest Neighbors具有生成潜在最近邻的非对抗性图像合成
Non-Local Meets Global_ An Integrated Paradigm for Hyperspectral Denoising非本地遇到全球_高光谱去噪的集成范式
Normalized Diversification标准化多元化
Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation用于类别级 6D 对象姿势和大小估计的归一化对象坐标空间
Not All Areas Are Equal_ Transfer Learning for Semantic Segmentation via Hierarchical Region Selection并非所有区域都是平等的_通过分层区域选择进行语义分割的迁移学习
Not All Frames Are Equal_ Weakly-Supervised Video Grounding With Contextual Similarity and Visual Clustering Losses并非所有帧都是平等的_具有上下文相似性和视觉聚类损失的弱监督视频接地
Not Using the Car to See the Sidewalk – Quantifying and Controlling the Effects of Context in Classification and Segmentation不使用汽车看人行道——量化和控制上下文在分类和分割中的影响
Object Counting and Instance Segmentation With Image-Level Supervision图像级监督的对象计数和实例分割
Object Detection With Location-Aware Deformable Convolution and Backward Attention Filtering使用位置感知可变形卷积和后向注意过滤的目标检测
Object Discovery in Videos as Foreground Motion Clustering视频中的对象发现作为前景运动聚类
Object Instance Annotation With Deep Extreme Level Set Evolution具有深度极限水平集演化的对象实例注释
Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters使用特定于视图的判别相关过滤器通过重建进行对象跟踪
Object-Aware Aggregation With Bidirectional Temporal Graph for Video Captioning用于视频字幕的具有双向时间图的对象感知聚合
Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video以对象为中心的自动编码器和虚拟异常用于视频中的异常事件检测
Object-Driven Text-To-Image Synthesis via Adversarial Training通过对抗训练进行对象驱动的文本到图像合成
Occlusion-Net_ 2D_3D Occluded Keypoint Localization Using Graph NetworksOcclusion-Net_2D_3D Occlusion Keypoint Localization Using Graph Networks
Occupancy Networks_ Learning 3D Reconstruction in Function SpaceOccupancy Networks_学习函数空间中的3D重构
OCGAN_ One-Class Novelty Detection Using GANs With Constrained Latent RepresentationsOCGAN_ 使用具有约束潜在表示的 GAN 的一类新奇检测
Octree Guided CNN With Spherical Kernels for 3D Point Clouds用于 3D 点云的带有球形内核的八叉树引导 CNN
ODE-Inspired Network Design for Single Image Super-Resolution单图像超分辨率的 ODE 启发网络设计
OICSR_ Out-In-Channel Sparsity Regularization for Compact Deep Neural NetworksOICSR_ 紧凑型深度神经网络的通道外稀疏正则化
OK-VQA_ A Visual Question Answering Benchmark Requiring External KnowledgeOK-VQA_ 需要外部知识的视觉问答基准
On Exploring Undetermined Relationships for Visual Relationship Detection关于探索用于视觉关系检测的未确定关系
On Finding Gray Pixels关于寻找灰色像素
On Implicit Filter Level Sparsity in Convolutional Neural Networks卷积神经网络中的隐式滤波器级稀疏性
On Learning Density Aware Embeddings关于学习密度感知嵌入
On Stabilizing Generative Adversarial Training With Noise用噪声稳定生成对抗训练
On the Continuity of Rotation Representations in Neural Networks关于神经网络中旋转表示的连续性
On the Intrinsic Dimensionality of Image Representations关于图像表示的内在维度
On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions关于深度卷积网络对傅里叶基函数方向的结构敏感性
On Zero-Shot Recognition of Generic Objects关于通用对象的零样本识别
Online High Rank Matrix Completion在线高阶矩阵完成
Orthogonal Decomposition Network for Pixel-Wise Binary Classification用于像素级二进制分类的正交分解网络
Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognition广义零样本动作识别的分布外检测
Overcoming Limitations of Mixture Density Networks_ A Sampling and Fitting Framework for Multimodal Future Prediction克服混合密度网络的局限性_多模态未来预测的采样和拟合框架
P2SGrad_ Refined Gradients for Optimizing Deep Face ModelsP2SGrad_ 优化深度人脸模型的细化梯度
P3SGD_ Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image ClassificationP3SGD_ Patient Privacy Preserving SGD 用于在病理图像分类中对深度 CNN 进行正则化
PA3D_ Pose-Action 3D Machine for Video RecognitionPA3D_ 用于视频识别的 Pose-Action 3D 机器
Panoptic Feature Pyramid Networks全景特征金字塔网络
Panoptic Segmentation全景分割
Parallel Optimal Transport GAN并行最优传输 GAN
Parametric Noise Injection_ Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack参数噪声注入_可训练随机性以提高深度神经网络对抗对抗性攻击的鲁棒性
Parsing R-CNN for Instance-Level Human Analysis解析 R-CNN 以进行实例级人体分析
Partial Order Pruning_ For Best Speed_Accuracy Trade-Off in Neural Architecture Search偏阶修剪_在神经架构搜索中实现最佳速度_准确度权衡
PartNet_ A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object UnderstandingPartNet_ 用于细粒度和分层零件级 3D 对象理解的大规模基准
PartNet_ A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape SegmentationPartNet_ 用于细粒度和分层形状分割的递归零件分解网络
Part-Regularized Near-Duplicate Vehicle Re-Identification部分正则化近重复车辆重新识别
Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification用于无监督人员重新识别的基于补丁的判别特征学习
Patch-Based Progressive 3D Point Set Upsampling基于补丁的渐进式 3D 点集上采样
Path-Invariant Map Networks路径不变映射网络
Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation跨深度、表面法线和语义分割的模式亲和传播
Pay Attention! - Robustifying a Deep Visuomotor Policy Through Task-Focused Visual Attention注意！ - 通过以任务为中心的视觉注意强化深度视觉运动策略
PCAN_ 3D Attention Map Learning Using Contextual Information for Point Cloud Based RetrievalPCAN_ 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval
PDE Acceleration for Active Contours活动轮廓的 PDE 加速
Pedestrian Detection With Autoregressive Network Phases使用自回归网络阶段的行人检测
Peeking Into the Future_ Predicting Future Person Activities and Locations in Videos窥视未来_在视频中预测未来人的活动和位置
PEPSI _ Fast Image Inpainting With Parallel Decoding NetworkPEPSI _ 使用并行解码网络的快速图像修复
Perceive Where to Focus_ Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification感知关注点_学习可见性感知的部分级特征以进行部分人员重新识别
Perturbation Analysis of the 8-Point Algorithm_ A Case Study for Wide FoV Cameras8点算法的扰动分析_宽视场相机案例研究
Phase-Only Image Based Kernel Estimation for Single Image Blind Deblurring单图像盲去模糊的基于相位图像的核估计
Photo Wake-Up_ 3D Character Animation From a Single Photo照片唤醒_单张照片的 3D 角色动画
Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction视频对齐 3D 对象重建的光度网格优化
Photon-Flooded Single-Photon 3D Cameras光子泛洪单光子 3D 相机
PIEs_ Pose Invariant EmbeddingsPIEs_Pose Invariant Embeddings
PifPaf_ Composite Fields for Human Pose EstimationPifPaf_ 用于人体姿势估计的复合场
Pixel-Adaptive Convolutional Neural Networks像素自适应卷积神经网络
PlaneRCNN_ 3D Plane Detection and Reconstruction From a Single ImagePlaneRCNN_ 3D 平面检测和单张图像重建
Pluralistic Image Completion多元图像完成
PMS-Net_ Robust Haze Removal Based on Patch Map for Single ImagesPMS-Net_ 基于 Patch Map 的单幅图像鲁棒去雾
Point Cloud Oversegmentation With Graph-Structured Deep Metric Learning图结构深度度量学习的点云过分割
Point in, Box Out_ Beyond Counting Persons in CrowdsPoint in, Box Out_超越人群中的人数
PointConv_ Deep Convolutional Networks on 3D Point CloudsPointConv_ 3D 点云上的深度卷积网络
PointFlowNet_ Learning Representations for Rigid Motion Estimation From Point CloudsPointFlowNet_ 从点云中学习刚体运动估计的表示
Pointing Novel Objects in Image Captioning在图像说明中指向新对象
PointNetLK_ Robust & Efficient Point Cloud Registration Using PointNetPointNetLK_ 使用 PointNet 进行稳健高效的点云注册
PointPillars_ Fast Encoders for Object Detection From Point CloudsPointPillars_ 用于从点云进行对象检测的快速编码器
PointRCNN_ 3D Object Proposal Generation and Detection From Point CloudPointRCNN_ 3D Object Proposal Generation and Detection From Point Cloud
Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant Layer使用残差置换等变层的基于点对姿势投票的手势估计
PointWeb_ Enhancing Local Neighborhood Features for Point Cloud ProcessingPointWeb_增强点云处理的局部邻域特征
Polarimetric Camera Calibration Using an LCD Monitor使用 LCD 监视器进行偏振相机校准
Polynomial Representation for Persistence Diagram持久性图的多项式表示
Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval用于跨模态检索的多义视觉语义嵌入
Pose2Seg_ Detection Free Human Instance SegmentationPose2Seg_检测免费人体实例分割
PoseFix_ Model-Agnostic General Human Pose Refinement NetworkPoseFix_ 与模型无关的通用人体姿势细化网络
PPGNet_ Learning Point-Pair Graph for Line Segment DetectionPPGNet_Learning Point-Pair Graph for Line Segment Detection
Practical Coding Function Design for Time-Of-Flight Imaging飞行时间成像的实用编码函数设计
Practical Full Resolution Learned Lossless Image Compression实用的全分辨率学习无损图像压缩
Precise Detection in Densely Packed Scenes密集场景中的精确检测
Predicting Future Frames Using Retrospective Cycle GAN使用追溯循环 GAN 预测未来帧
Predicting Visible Image Differences Under Varying Display Brightness and Viewing Distance预测不同显示亮度和视距下的可见图像差异
Privacy Preserving Image-Based Localization隐私保护基于图像的本地化
Privacy Protection in Street-View Panoramas Using Depth and Multi-View Imagery使用深度和多视图图像的街景全景图中的隐私保护
Probabilistic End-To-End Noise Correction for Learning With Noisy Labels带有噪声标签的概率端到端噪声校正
Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope使用 Birkhoff 多面体的黎曼结构的概率置换同步
Progressive Attention Memory Network for Movie Story Question Answering用于电影故事问答的渐进注意记忆网络
Progressive Ensemble Networks for Zero-Shot Recognition用于零样本识别的渐进集成网络
Progressive Feature Alignment for Unsupervised Domain Adaptation无监督域自适应的渐进特征对齐
Progressive Image Deraining Networks_ A Better and Simpler Baseline渐进式图像去雨网络_更好更简单的基线
Progressive Pose Attention Transfer for Person Image Generation用于人物图像生成的渐进式姿势注意力转移
Progressive Teacher-Student Learning for Early Action Prediction用于早期行动预测的渐进式师生学习
Propagation Mechanism for Deep and Wide Neural Networks深度和广度神经网络的传播机制
Pseudo-LiDAR From Visual Depth Estimation_ Bridging the Gap in 3D Object Detection for Autonomous Driving视觉深度估计中的伪激光雷达_弥合自动驾驶 3D 对象检测的差距
Pushing the Boundaries of View Extrapolation With Multiplane Images用多平面图像推动视图外推的边界
Pushing the Envelope for RGB-Based Dense 3D Hand Pose Estimation via Neural Rendering通过神经渲染推动基于 RGB 的密集 3D 手部姿势估计的信封
Putting Humans in a Scene_ Learning Affordance in 3D Indoor Environments将人类置于场景中_在 3D 室内环境中学习可负担性
PVNet_ Pixel-Wise Voting Network for 6DoF Pose EstimationPVNet_ 用于 6DoF 姿态估计的 Pixel-Wise Voting Network
Pyramid Feature Attention Network for Saliency Detection用于显着性检测的金字塔特征注意网络
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training通过多损失动态训练的金字塔人重新识别
QATM_ Quality-Aware Template Matching for Deep LearningQATM_深度学习的质量感知模板匹配
Quantization Networks量化网络
Quasi-Unsupervised Color Constancy准无监督颜色恒常性
Query-Guided End-To-End Person Search查询引导的端到端人员搜索
R2GAN_ Cross-Modal Recipe Retrieval With Generative Adversarial NetworkR2GAN_ 使用生成对抗网络的跨模态配方检索
R3 Adversarial Network for Cross Model Face Recognition用于跨模型人脸识别的 R3 对抗网络
Radial Distortion Triangulation径向畸变三角剖分
Ranked List Loss for Deep Metric Learning深度度量学习的排名表损失
Rare Event Detection Using Disentangled Representation Learning使用分离表示学习的罕见事件检测
RAVEN_ A Dataset for Relational and Analogical Visual REasoNingRAVEN_ 用于关系和类比视觉推理的数据集
Ray-Space Projection Model for Light Field Camera光场相机的射线空间投影模型
Real-Time Self-Adaptive Deep Stereo实时自适应深度立体声
Reasoning Visual Dialogs With Structural and Partial Observations用结构和部分观察推理视觉对话
Reasoning-RCNN_ Unifying Adaptive Global Reasoning Into Large-Scale Object DetectionReasoning-RCNN_将自适应全局推理统一到大规模目标检测中
Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization用于联合人群计数和精确定位的循环注意缩放
Recurrent Back-Projection Network for Video Super-Resolution用于视频超分辨率的循环反投影网络
Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference用于高分辨率多视图立体深度推理的循环 MVSNet
Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth用于单目视频视觉里程计和深度的（非）监督学习的递归神经网络
Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring用于视频去模糊的具有帧内迭代的递归神经网络
Recursive Visual Attention in Visual Dialog视觉对话框中的递归视觉注意
Reducing Uncertainty in Undersampled MRI Reconstruction With Active Acquisition通过主动采集减少欠采样 MRI 重建的不确定性
Refine and Distill_ Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth EstimationRefine and Distill_ Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monoocular Depth Estimation
Reflection Removal Using a Dual-Pixel Sensor使用双像素传感器去除反射
Reflective and Fluorescent Separation Under Narrow-Band Illumination窄带照明下的反射和荧光分离
Region Proposal by Guided Anchoring引导锚定的区域提案
RegularFace_ Deep Face Recognition via Exclusive RegularizationRegularFace_通过独家正则化的深度人脸识别
Regularizing Activation Distribution for Training Binarized Deep Networks训练二值化深度网络的正则化激活分布
Re-Identification Supervised Texture Generation重新识别监督纹理生成
Re-Identification With Consistent Attentive Siamese Networks使用一致的细心连体网络重新识别
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation用于视觉语言导航的增强型跨模态匹配和自监督模仿学习
Relational Action Forecasting关系行动预测
Relational Knowledge Distillation关系知识蒸馏
Relation-Shape Convolutional Neural Network for Point Cloud Analysis用于点云分析的关系型卷积神经网络
Reliable and Efficient Image Cropping_ A Grid Anchor Based Approach可靠高效的图像裁剪_基于网格锚的方法
RENAS_ Reinforced Evolutionary Neural Architecture SearchRENAS_强化进化神经架构搜索
REPAIR_ Removing Representation Bias by Dataset ResamplingREPAIR_通过数据集重采样消除表示偏差
RepMet_ Representative-Based Metric Learning for Classification and Few-Shot Object DetectionRepMet_基于代表性的度量学习分类和小样本目标检测
RepNet_ Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationRepNet_ 用于 3D 人体姿态估计的对抗性重投影网络的弱监督训练
RePr_ Improved Training of Convolutional FiltersRePr_改进了卷积滤波器的训练
Representation Flow for Action Recognition动作识别的表示流
Representation Similarity Analysis for Efficient Task Taxonomy & Transfer Learning高效任务分类和迁移学习的表示相似性分析
Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification通过度量融合重新排名以进行对象检索和人员重新识别
Residual Networks for Light Field Image Super-Resolution用于光场图像超分辨率的残差网络
Residual Regression With Semantic Prior for Crowd Counting用于人群计数的带有语义先验的残差回归
RES-PCA_ A Scalable Approach to Recovering Low-Rank MatricesRES-PCA_一种恢复低秩矩阵的可扩展方法
Rethinking Knowledge Graph Propagation for Zero-Shot Learning重新思考零样本学习的知识图传播
Rethinking the Evaluation of Video Summaries重新思考视频摘要的评估
Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples针对对抗样本的检索增强卷积神经网络
Revealing Scenes by Inverting Structure From Motion Reconstructions通过从运动重建中反转结构来揭示场景
Reversible GANs for Memory-Efficient Image-To-Image Translation用于内存高效图像到图像转换的可逆 GAN
Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot Learning重新审视基于局部描述符的 Image-To-Class 度量以进行 Few-Shot 学习
Revisiting Perspective Information for Efficient Crowd Counting重新审视有效人群计数的透视信息
Revisiting Self-Supervised Visual Representation Learning重新审视自我监督的视觉表征学习
RF-Net_ An End-To-End Image Matching Network Based on Receptive FieldRF-Net_一种基于感受野的端到端图像匹配网络
RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion用于 3D 语义场景完成的基于 RGBD 的维度分解残差网络
RL-GAN-Net_ A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape CompletionRL-GAN-Net_ 用于实时点云形状完成的强化学习代理控制 GAN 网络
Rob-GAN_ Generator, Discriminator, and Adversarial AttackerRob-GAN_ 生成器、鉴别器和对抗性攻击者
Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks基于遮挡自适应深度网络的鲁棒面部地标检测
Robust Histopathology Image Analysis_ To Label or to Synthesize_强大的组织病理学图像分析_标记或合成_
Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes基于鲁棒点云的大规模户外场景重建
Robust Subspace Clustering With Independent and Piecewise Identically Distributed Noise Modeling具有独立和分段同分布噪声建模的鲁棒子空间聚类
Robust Video Stabilization by Optimization in CNN Weight Space通过 CNN 权重空间中的优化实现稳健的视频稳定
Robustness of 3D Deep Learning in an Adversarial Setting对抗环境中 3D 深度学习的鲁棒性
Robustness Verification of Classification Deep Neural Networks via Linear Programming通过线性规划验证分类深度神经网络的鲁棒性
Robustness via Curvature Regularization, and Vice Versa通过曲率正则化实现鲁棒性，反之亦然
ROI Pooled Correlation Filters for Visual Tracking用于视觉跟踪的 ROI 合并相关过滤器
ROI-10D_ Monocular Lifting of 2D Detection to 6D Pose and Metric ShapeROI-10D_ 2D 检测到 6D 姿态和度量形状的单目提升
Rules of the Road_ Predicting Driving Behavior With a Convolutional Model of Semantic Interactions道路规则_用语义交互的卷积模型预测驾驶行为
RVOS_ End-To-End Recurrent Network for Video Object SegmentationRVOS_视频对象分割的端到端循环网络
S4Net_ Single Stage Salient-Instance SegmentationS4Net_单阶段显着实例分割
SAIL-VOS_ Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and BaselinesSAIL-VOS_ Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines
Salient Object Detection With Pyramid Attention and Salient Edges具有金字塔注意力和显着边缘的显着目标检测
Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects从稀疏注释对象中进行大规模对象检测的采样技术
Scalable Convolutional Neural Network for Image Compressed Sensing用于图像压缩感知的可扩展卷积神经网络
Scale-Adaptive Neural Dense Features_ Learning via Hierarchical Context Aggregation尺度自适应神经密集特征_通过分层上下文聚合学习
Scan2CAD_ Learning CAD Model Alignment in RGB-D ScansScan2CAD_ 在 RGB-D 扫描中学习 CAD 模型对齐
Scan2Mesh_ From Unstructured Range Scans to 3D MeshesScan2Mesh_ 从非结构化范围扫描到 3D 网格
Scene Categorization From Contours_ Medial Axis Based Salience Measures基于轮廓的场景分类_基于中轴的显着性度量
Scene Graph Generation With External Knowledge and Image Reconstruction使用外部知识和图像重建的场景图生成
Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks长视野任务中具体代理的场景记忆转换器
Scene Parsing via Integrated Classification Model and Variance-Based Regularization通过集成分类模型和基于方差的正则化进行场景解析
SceneCode_ Monocular Dense Semantic Reconstruction Using Learned Encoded Scene RepresentationsSceneCode_ 使用学习到的编码场景表示进行单目密集语义重建
SCOPS_ Self-Supervised Co-Part SegmentationSCOPS_自我监督的共同部分分割
ScratchDet_ Training Single-Shot Object Detectors From ScratchScratchDet_ 从零开始训练单次目标检测器
SDC - Stacked Dilated Convolution_ A Unified Descriptor Network for Dense Matching TasksSDC - Stacked Dilated Convolution_ 用于密集匹配任务的统一描述符网络
SDRSAC_ Semidefinite-Based Randomized Approach for Robust Point Cloud Registration Without CorrespondencesSDRSAC_ 无对应关系的鲁棒点云配准的基于半定的随机方法
Seamless Scene Segmentation无缝场景分割
Searching for a Robust Neural Architecture in Four GPU Hours在四个 GPU 小时内寻找稳健的神经架构
Sea-Thru_ A Method for Removing Water From Underwater ImagesSea-Thru_一种从水下图像中去除水分的方法
Second-Order Attention Network for Single Image Super-Resolution单图像超分辨率的二阶注意力网络
See More, Know More_ Unsupervised Video Object Segmentation With Co-Attention Siamese NetworksSee More, Know More_ 使用 Co-Attention Siamese 网络进行无监督视频对象分割
SeerNet_ Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit QuantizationSeerNet_通过低位量化预测卷积神经网络特征图稀疏性
Segmentation-Driven 6D Object Pose Estimation分割驱动的 6D 对象姿态估计
Selective Kernel Networks选择性内核网络
Selective Sensor Fusion for Neural Visual-Inertial Odometry用于神经视觉惯性里程计的选择性传感器融合
Self-Calibrating Deep Photometric Stereo Networks自校准深度光度立体网络
Self-Critical N-Step Training for Image Captioning图像描述的自我批判 N 步训练
SelFlow_ Self-Supervised Learning of Optical FlowSelFlow_光流的自监督学习
Self-Supervised 3D Hand Pose Estimation Through Training by Fitting通过拟合训练进行自我监督的 3D 手部姿势估计
Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking用于单目性能跟踪的高保真人脸模型的自监督适应
Self-Supervised Convolutional Subspace Clustering Network自监督卷积子空间聚类网络
Self-Supervised GANs via Auxiliary Rotation Loss通过辅助旋转损失的自我监督 GAN
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry使用多视图几何的 3D 人体姿势的自监督学习
Self-Supervised Learning via Conditional Motion Propagation通过条件运动传播的自我监督学习
Self-Supervised Representation Learning by Rotation Feature Decoupling通过旋转特征解耦的自监督表示学习
Self-Supervised Representation Learning From Videos for Facial Action Unit Detection从视频中学习用于面部动作单元检测的自监督表示
Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction通过视频剪辑顺序预测的自监督时空学习
Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics通过预测运动和外观统计的视频自监督时空表示学习
Semantic Alignment_ Finding Semantically Consistent Ground-Truth for Facial Landmark Detection语义对齐_为面部地标检测寻找语义一致的地面实况
Semantic Attribute Matching Networks语义属性匹配网络
Semantic Component Decomposition for Face Attribute Manipulation人脸属性操作的语义成分分解
Semantic Correlation Promoted Shape-Variant Context for Segmentation语义相关促进了用于分割的形状变体上下文
Semantic Graph Convolutional Networks for 3D Human Pose Regression用于 3D 人体姿态回归的语义图卷积网络
Semantic Image Synthesis With Spatially-Adaptive Normalization具有空间自适应归一化的语义图像合成
Semantic Projection Network for Zero- and Few-Label Semantic Segmentation零标签和少标签语义分割的语义投影网络
Semantically Aligned Bias Reducing Zero Shot Learning减少零镜头学习的语义对齐偏差
Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval基于零镜头草图的图像检索的语义关联配对循环一致性
Semantics Disentangling for Text-To-Image Generation文本到图像生成的语义分离
Semi-Supervised Learning With Graph Learning-Convolutional Networks使用图学习-卷积网络的半监督学习
Semi-Supervised Transfer Learning for Image Rain Removal图像雨水去除的半监督迁移学习
Sensitive-Sample Fingerprinting of Deep Neural Networks深度神经网络的敏感样本指纹
Separate to Adapt_ Open Set Domain Adaptation via Progressive SeparationSeparation to Adapt_Open Set Domain Adaptation via Progressive Separation
Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition用于鲁棒文本图像识别的序列到序列域自适应网络
SFNet_ Learning Object-Aware Semantic CorrespondenceSFNet_Learning Object-Aware Semantic Correspondence
Shape Robust Text Detection With Progressive Scale Expansion Network具有渐进式扩展网络的形状鲁棒文本检测
Shape Unicode_ A Unified Shape RepresentationShape Unicode_一种统一的形状表示
Shape2Motion_ Joint Analysis of Motion Parts and Attributes From 3D ShapesShape2Motion_ 3D 形状的运动部件和属性的联合分析
Shapes and Context_ In-The-Wild Image Synthesis & ManipulationShapes and Context_In-The-Wild 图像合成和处理
ShieldNets_ Defending Against Adversarial Attacks Using Probabilistic Adversarial RobustnessShieldNets_ 使用概率对抗鲁棒性防御对抗性攻击
Shifting More Attention to Video Salient Object Detection将更多注意力转移到视频显着目标检测上
Show, Control and Tell_ A Framework for Generating Controllable and Grounded CaptionsShow, Control and Tell_一个生成可控和接地字幕的框架
Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking用于实时视觉跟踪的连体级联区域建议网络
SiamRPN++_ Evolution of Siamese Visual Tracking With Very Deep NetworksSiamRPN++连体视觉跟踪的演进与非常深的网络
SiCloPe Silhouette-Based Clothed PeopleSiCloPe_剪影型衣着人
Side Window Filtering侧窗过滤
Signal-To-Noise Ratio_ A Robust Distance Metric for Deep Metric Learning信噪比_深度度量学习的鲁棒距离度量
SIGNet_ Semantic Instance Aided Unsupervised 3D Geometry PerceptionSIGNet_ 语义实例辅助无监督 3D 几何感知
Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation用于 3D 室内导航的 Sim-Real 联合强化转移
Sim-To-Real via Sim-To-Sim_ Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation NetworksSim-To-Real via Sim-To-Sim_ Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks
SimulCap _ Single-View Human Performance Capture With Cloth SimulationSimulCap _ 使用布料模拟的单视图人体性能捕获
Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation利用截断高斯逼近同时优化三元神经网络的权值和量化器
Single Image Depth Estimation Trained via Depth From Defocus Cues通过 Defocus Cues 的深度训练的单图像深度估计
Single Image Deraining_ A Comprehensive Benchmark Analysis单幅图像去雨_综合基准分析
Single Image Reflection Removal Beyond Linearity超越线性的单图像反射去除
Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements利用未对齐的训练数据和网络增强来去除单图像反射
Single-Frame Regularization for Temporally Stable CNNs时间稳定 CNN 的单帧正则化
Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding通过关联嵌入进行单图像分段平面 3D 重建
SIXray_ A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping ImagesSIXray_ 用于在重叠图像中发现违禁物品的大规模安全检查 X 射线基准
Skeleton-Based Action Recognition With Directed Graph Neural Networks有向图神经网络的基于骨架的动作识别
SketchGAN_ Joint Sketch Completion and Recognition With Generative Adversarial NetworkSketchGAN_与生成对抗网络的联合草图完成和识别
Skin-Based Identification From Multispectral Image Data Using CNNs使用 CNN 从多光谱图像数据中进行基于皮肤的识别
Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation无监督域适应的切片 Wasserstein 差异
Sliced Wasserstein Generative Models切片 Wasserstein 生成模型
Slim DensePose_ Thrifty Learning From Sparse Annotations and Motion CuesSlim DensePose_从稀疏注释和运动线索中节俭学习
Snapshot Distillation_ Teacher-Student Optimization in One Generation快照蒸馏_一代师生优化
Social Relation Recognition From Videos via Multi-Scale Spatial-Temporal Reasoning通过多尺度时空推理从视频中识别社会关系
Social-IQ_ A Question Answering Benchmark for Artificial Social IntelligenceSocial-IQ_人工智能的问答基准
SoDeep_ A Sorting Deep Net to Learn Ranking Loss SurrogatesSoDeep_一种用于学习排名损失代理的排序深度网络
Soft Labels for Ordinal Regression序数回归的软标签
SoPhie_ An Attentive GAN for Predicting Paths Compliant to Social and Physical ConstraintsSoPhie_ 用于预测符合社会和物理约束的路径的细心 GAN
SOSNet_ Second Order Similarity Regularization for Local Descriptor LearningSOSNet_局部描述符学习的二阶相似性正则化
SparseFool_ A Few Pixels Make a Big DifferenceSparseFool_ 几个像素有很大的不同
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset具有高质量真实降雨数据集的空间注意力单图像去雨
Spatial Fusion GAN for Image Synthesis用于图像合成的空间融合 GAN
Spatial-Aware Graph Relation Network for Large-Scale Object Detection用于大规模目标检测的空间感知图关系网络
Spatially Variant Linear Representation Models for Joint Filtering联合滤波的空间变体线性表示模型
Spatiotemporal CNN for Video Object Segmentation用于视频对象分割的时空 CNN
Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning用于视频字幕的时空动态和语义属性丰富的视觉编码
Spatio-Temporal Video Re-Localization by Warp LSTMWarp LSTM 的时空视频重新定位
Spectral Metric for Dataset Complexity Assessment数据集复杂性评估的频谱度量
Spectral Reconstruction From Dispersive Blur_ A Novel Light Efficient Spectral Imager色散模糊的光谱重建_一种新型的光效光谱成像仪
Speech2Face_ Learning the Face Behind a VoiceSpeech2Face_学习声音背后的面孔
Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras使用基于事件的相机学习检测角点的速度不变时间曲面
Sphere Generative Adversarial Network Based on Geometric Moment Matching基于几何矩匹配的球面生成对抗网络
SpherePHD_ Applying CNNs on a Spherical PolyHeDron Representation of 360deg ImagesSpherePHD_ 将 CNN 应用于 360 度图像的球形多面体表示
Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition用于点云识别的球面分形卷积神经网络
Spherical Regression_ Learning Viewpoints, Surface Normals and 3D Rotations on N-Spheres球面回归_在 N 球上学习视点、表面法线和 3D 旋转
SPM-Tracker_ Series-Parallel Matching for Real-Time Visual Object TrackingSPM-Tracker_实时视觉对象跟踪的串并匹配
Spot and Learn_ A Maximum-Entropy Patch Sampler for Few-Shot Image ClassificationSpot and Learn_Few-Shot 图像分类的最大熵补丁采样器
SpotTune_ Transfer Learning Through Adaptive Fine-TuningSpotTune_通过自适应微调进行迁移学习
SR-LSTM_ State Refinement for LSTM Towards Pedestrian Trajectory PredictionSR-LSTM_ LSTM 的状态细化对行人轨迹预测
SSN_ Learning Sparse Switchable Normalization via SparsestMaxSSN_ 通过 SparsestMax 学习稀疏可切换归一化
Steady-State Non-Line-Of-Sight Imaging稳态非视距成像
STEP_ Spatio-Temporal Progressive Learning for Video Action DetectionSTEP_视频动作检测的时空渐进学习
Stereo R-CNN Based 3D Object Detection for Autonomous Driving基于 Stereo R-CNN 的自动驾驶 3D 目标检测
StereoDRNet_ Dilated Residual StereoNetStereoDRNet_扩张残差立体网络
STGAN_ A Unified Selective Transfer Network for Arbitrary Image Attribute EditingSTGAN_用于任意图像属性编辑的统一选择性传输网络
Stochastic Class-Based Hard Example Mining for Deep Metric Learning用于深度度量学习的基于随机类的硬样本挖掘
StoryGAN_ A Sequential Conditional GAN for Story VisualizationStoryGAN_ 用于故事可视化的顺序条件 GAN
Strand-Accurate Multi-View Hair CaptureStrand-Accurate 多视图头发捕捉
Streamlined Dense Video Captioning流线型密集视频字幕
Strike (With) a Pose_ Neural Networks Are Easily Fooled by Strange Poses of Familiar ObjectsStrike (With) a Pose_神经网络很容易被熟悉物体的奇怪姿势所欺骗
Striking the Right Balance With Uncertainty在不确定性中取得正确的平衡
Strong-Weak Distribution Alignment for Adaptive Object Detection自适应目标检测的强弱分布对齐
Structural Relational Reasoning of Point Clouds点云的结构关系推理
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation用于准确图像分类和语义分割的结构化二元神经网络
Structured Knowledge Distillation for Semantic Segmentation语义分割的结构化知识蒸馏
Structured Pruning of Neural Networks With Budget-Aware Regularization具有预算意识正则化的神经网络的结构化剪枝
Structure-Preserving Stereoscopic View Synthesis With Multi-Scale Adversarial Correlation Matching具有多尺度对抗相关匹配的结构保持立体视图合成
Student Becoming the Master_ Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More学生成为大师_联合场景解析、深度估计等的知识融合
Style Transfer by Relaxed Optimal Transport and Self-Similarity通过轻松的最优传输和自相似性进行风格迁移
Superquadrics Revisited_ Learning 3D Shape Parsing Beyond CuboidsSuperquadrics Revisited_超越长方体学习 3D 形状解析
Supervised Fitting of Geometric Primitives to 3D Point Clouds几何基元到 3D 点云的监督拟合
Surface Reconstruction From Normals_ A Robust DGP-Based Discontinuity Preservation Approach从法线重建表面_一种基于 DGP 的稳健不连续性保留方法
Synthesizing 3D Shapes From Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks使用多投影生成对抗网络从剪影图像集合中合成 3D 形状
Synthesizing Environment-Aware Activities via Activity Sketches通过活动草图综合环境感知活动
TACNet_ Transition-Aware Context Network for Spatio-Temporal Action DetectionTACNet_用于时空动作检测的Transition-Aware Context Network
Tactical Rewind_ Self-Correction via Backtracking in Vision-And-Language Navigation战术倒带_通过视觉和语言导航中的回溯进行自我校正
TAFE-Net_ Task-Aware Feature Embeddings for Low Shot LearningTAFE-Net_ Task-Aware Feature Embeddings for Low Shot 学习
Taking a Closer Look at Domain Shift_ Category-Level Adversaries for Semantics Consistent Domain Adaptation仔细研究域转移_语义一致域适应的类别级对手
Taking a Deeper Look at the Inverse Compositional Algorithm深入了解逆组合算法
Tangent-Normal Adversarial Regularization for Semi-Supervised Learning用于半监督学习的正态正则化正则化
Target-Aware Deep Tracking目标感知深度跟踪
Task Agnostic Meta-Learning for Few-Shot Learning用于少量学习的任务不可知元学习
Task-Free Continual Learning无任务持续学习
Tell Me Where I Am_ Object-Level Scene Context Prediction告诉我我在哪里_对象级场景上下文预测
Temporal Cycle-Consistency Learning时间周期一致性学习
Temporal Transformer Networks_ Joint Learning of Invariant and Discriminative Time WarpingTemporal Transformer Networks_不变和判别时间扭曲的联合学习
Text Guided Person Image Synthesis文本引导人图像合成
Text2Scene_ Generating Compositional Scenes From Textual DescriptionsText2Scene_从文本描述生成组合场景
Texture Mixer_ A Network for Controllable Synthesis and Interpolation of TextureTexture Mixer_一种用于纹理可控合成和插值的网络
Textured Neural Avatars纹理神经化身
TextureNet_ Consistent Local Parametrizations for Learning From High-Resolution Signals on MeshesTextureNet_从网格上的高分辨率信号中学习的一致局部参数化
The Alignment of the Spheres_ Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation球体的对齐_相机位姿估计的全局最优球面混合对齐
The Domain Transform Solver域变换求解器
The Perfect Match_ 3D Point Cloud Matching With Smoothed Densities完美匹配_具有平滑密度的 3D 点云匹配
The Pros and Cons_ Rank-Aware Temporal Attention for Skill Determination in Long Videos长视频中用于技能确定的 Rank-Aware Temporal Attention 的优点和缺点
The Regretful Agent_ Heuristic-Aided Navigation Through Progress Estimation遗憾的代理_通过进度估计的启发式辅助导航
The Visual Centrifuge_ Model-Free Layered Video Representations视觉离心机_无模型分层视频表示
Thinking Outside the Pool_ Active Training Image Creation for Relative Attributes池外思考_相关属性的主动训练图像创建
Tightness-Aware Evaluation Protocol for Scene Text Detection用于场景文本检测的紧密度感知评估协议
Timeception for Complex Action Recognition复杂动作识别的时间感知
Time-Conditioned Action Anticipation in One Shot一枪中的时间条件动作预期
T-Net_ Parametrizing Fully Convolutional Nets With a Single High-Order TensorT-Net_ 使用单个高阶张量参数化全卷积网络
ToothNet_ Automatic Tooth Instance Segmentation and Identification From Cone Beam CT ImagesToothNet_ 锥束 CT 图像的自动牙齿实例分割和识别
TopNet_ Structural Point Cloud DecoderTopNet_结构点云解码器
Topology Reconstruction of Tree-Like Structure in Images via Structural Similarity Measure and Dominant Set Clustering基于结构相似性度量和显性集聚类的图像树状结构拓扑重建
TOUCHDOWN_ Natural Language Navigation and Spatial Reasoning in Visual Street EnvironmentsTOUCHDOWN_视觉街道环境中的自然语言导航和空间推理
Toward Convolutional Blind Denoising of Real Photographs走向真实照片的卷积盲去噪
Toward Realistic Image Compositing With Adversarial Learning用对抗性学习实现逼真的图像合成
Towards Accurate One-Stage Object Detection With AP-Loss使用 AP-Loss 实现准确的单阶段目标检测
Towards High-Fidelity Nonlinear 3D Face Morphable Model迈向高保真非线性 3D 人脸可变形模型
Towards Instance-Level Image-To-Image Translation迈向实例级图像到图像转换
Towards Natural and Accurate Future Motion Prediction of Humans and Animals走向自然和准确的人类和动物未来运动预测
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning通过生成对抗学习实现最优结构化 CNN 修剪
Towards Real Scene Super-Resolution With Raw Images使用原始图像实现真实场景超分辨率
Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification通过类激活图增强实现丰富的特征发现以进行人员重新识别
Towards Robust Curve Text Detection With Conditional Spatial Expansion具有条件空间扩展的稳健曲线文本检测
Towards Scene Understanding_ Unsupervised Monocular Depth Estimation With Semantic-Aware Representation走向场景理解_使用语义感知表示的无监督单目深度估计
Towards Social Artificial Intelligence_ Nonverbal Social Signal Prediction in a Triadic Interaction迈向社交人工智能_三元交互中的非语言社交信号预测
Towards Universal Object Detection by Domain Attention通过域注意实现通用对象检测
Towards Visual Feature Translation迈向视觉特征翻译
Towards VQA Models That Can Read迈向可以阅读的 VQA 模型
Tracking by Animation_ Unsupervised Learning of Multi-Object Attentive TrackersTracking by Animation_多目标注意力跟踪器的无监督学习
Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior从没有基本事实和没有图像先验的欠采样测量中训练基于深度学习的图像降噪器
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering通过无监督任务发现进行迁移学习以进行视觉问答
Transferable AutoML by Model Sharing Over Grouped Datasets通过分组数据集上的模型共享可转移 AutoML
Transferable Interactiveness Knowledge for Human-Object Interaction Detection用于人-物交互检测的可迁移交互知识
Transferrable Prototypical Networks for Unsupervised Domain Adaptation用于无监督域适应的可转移原型网络
TransGaGa_ Geometry-Aware Unsupervised Image-To-Image TranslationTransGaGa_几何感知无监督图像到图像转换
Translate-to-Recognize Networks for RGB-D Scene Recognition用于 RGB-D 场景识别的翻译识别网络
TraPHic_ Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted InteractionsTraPHic_ 使用加权交互的密集和异构交通中的轨迹预测
TraVeLGAN_ Image-To-Image Translation by Transformation Vector LearningTraVeLGAN_ Image-To-Image Translation by Transformation Vector Learning
Triangulation Learning Network_ From Monocular to Stereo 3D Object Detection三角学习网络_从单目到立体3D物体检测
Triply Supervised Decoder Networks for Joint Detection and Segmentation用于联合检测和分割的三重监督解码器网络
Trust Region Based Adversarial Attack on Neural Networks基于信任区域的神经网络对抗性攻击
Turn a Silicon Camera Into an InGaAs Camera将硅相机变成 InGaAs 相机
Two Body Problem_ Collaborative Visual Task Completion两体问题_协同视觉任务完成
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition用于基于骨架的动作识别的两流自适应图卷积网络
Typography With Decor_ Intelligent Text Style Transfer带装饰的排版_智能文本样式转换
Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining不确定性引导的多尺度残差学习——使用循环旋转 CNN 进行单幅图像去雨
Underexposed Photo Enhancement Using Deep Illumination Estimation使用深度照明估计的曝光不足照片增强
Understanding and Visualizing Deep Visual Saliency Models理解和可视化深度视觉显着性模型
Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift通过方差偏移理解 Dropout 和 Batch Normalization 之间的不协调
Understanding the Limitations of CNN-Based Absolute Camera Pose Regression了解基于 CNN 的绝对相机姿态回归的局限性
Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data使用长尾噪声数据进行深度人脸识别的不平等训练
Unified Visual-Semantic Embeddings_ Bridging Vision and Language With Structured Meaning Representations统一的视觉-语义嵌入_用结构化的意义表示桥接视觉和语言
UniformFace_ Learning Deep Equidistributed Representation for Face RecognitionUniformFace_人脸识别学习深度等分布表示
Unifying Heterogeneous Classifiers With Distillation用蒸馏统一异构分类器
Universal Domain Adaptation通用域适配
UnOS_ Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching VideosUnOS_统一无监督光流和立体深度估计通过观看视频
Unprocessing Images for Learned Raw Denoising为学习的原始去噪处理图像
Unsupervised 3D Pose Estimation With Geometric Self-Supervision具有几何自监督的无监督 3D 姿态估计
Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes用于静止或动态场景的无监督深度核极流
Unsupervised Deep Tracking无监督深度跟踪
Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network可变形生成器网络对外观和几何形状的无监督解开
Unsupervised Domain Adaptation for ToF Data Denoising With Adversarial LearningToF 数据去噪与对抗性学习的无监督域自适应
Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss使用特征白化和共识损失的无监督域自适应
Unsupervised Domain-Specific Deblurring via Disentangled Representations通过分离表示进行无监督领域特定去模糊
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature通过不变和扩展实例特征进行无监督嵌入学习
Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion光流、深度和自我运动的基于事件的无监督学习
Unsupervised Face Normalization With Extreme Pose and Expression in the Wild野外极端姿势和表情的无监督人脸归一化
Unsupervised Image Captioning无监督图像字幕
Unsupervised Image Matching and Object Discovery as Optimization无监督图像匹配和目标发现作为优化
Unsupervised Learning of Action Classes With Continuous Temporal Embedding具有连续时间嵌入的动作类的无监督学习
Unsupervised Learning of Consensus Maximization for 3D Vision Problems3D 视觉问题共识最大化的无监督学习
Unsupervised Learning of Dense Shape Correspondence密集形状对应的无监督学习
Unsupervised Moving Object Detection via Contextual Information Separation通过上下文信息分离进行无监督运动目标检测
Unsupervised Multi-Modal Neural Machine Translation无监督多模态神经机器翻译
Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization基于语义差异最小化的无监督开放域识别
Unsupervised Part-Based Disentangling of Object Shape and Appearance对象形状和外观的无监督的基于部分的解开
Unsupervised Person Image Generation With Semantic Parsing Transformation使用语义解析转换的无监督人物图像生成
Unsupervised Person Re-Identification by Soft Multilabel Learning通过软多标签学习进行无监督人员重新识别
Unsupervised Primitive Discovery for Improved 3D Generative Modeling用于改进 3D 生成建模的无监督原始发现
Unsupervised Visual Domain Adaptation_ A Deep Max-Margin Gaussian Process Approach无监督视觉域自适应_一种深度最大边距高斯过程方法
UPSNet_ A Unified Panoptic Segmentation NetworkUPSNet_一个统一的全景分割网络
Using Unknown Occluders to Recover Hidden Scenes使用未知遮挡物恢复隐藏场景
Variational Autoencoders Pursue PCA Directions (by Accident)变分自动编码器遵循 PCA 方向（意外）
Variational Bayesian Dropout With a Hierarchical Prior具有分层先验的变分贝叶斯辍学
Variational Convolutional Neural Network Pruning变分卷积神经网络剪枝
Variational Information Distillation for Knowledge Transfer知识转移的变分信息蒸馏
Variational Prototyping-Encoder_ One-Shot Learning With Prototypical ImagesVariational Prototyping-Encoder_One-Shot Learning with Prototypical Images
Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding ApproachVeritatem Dies Aperit - 由多任务几何和语义场景理解方法实现的时间一致深度预测
VERI-Wild_ A Large Dataset and a New Method for Vehicle Re-Identification in the WildVERI-Wild_一个大型数据集和一种在野外重新识别车辆的新方法
Versatile Multiple Choice Learning and Its Application to Vision Computing多功能多项选择学习及其在视觉计算中的应用
Video Action Transformer Network视频动作变压器网络
Video Generation From Single Semantic Label Map从单个语义标签映射生成视频
Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution在时间分布中使用分数各向异性进行野外视频放大
Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph使用门控时空能量图的视频关系推理
Video Summarization by Learning From Unpaired Data从非配对数据中学习视频摘要
Viewport Proposal CNN for 360deg Video Quality Assessment用于 360 度视频质量评估的 Viewport Proposal CNN
Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention基于视觉的导航和基于语言的辅助通过间接干预的模仿学习
Visual Attention Consistency Under Image Transforms for Multi-Label Image Classification用于多标签图像分类的图像变换下的视觉注意一致性
Visual Localization by Learning Objects-Of-Interest Dense Match Regression通过学习感兴趣的对象密集匹配回归进行视觉定位
Visual Query Answering by Entity-Attribute Graph Matching and Reasoning实体-属性图匹配推理的可视化查询回答
Visual Question Answering as Reading Comprehension视觉问答作为阅读理解
Visual Tracking via Adaptive Spatially-Regularized Correlation Filters通过自适应空间正则化相关滤波器进行视觉跟踪
VITAMIN-E_ VIsual Tracking and MappINg With Extremely Dense Feature PointsVITAMIN-E_ 具有极其密集特征点的视觉跟踪和映射
VizWiz-Priv_ A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind PeopleVizWiz-Priv_ 用于识别盲人拍摄图像中私人视觉信息的存在和目的的数据集
Volumetric Capture of Humans With a Single RGBD Camera via Semi-Parametric Learning通过半参数学习使用单个 RGBD 相机对人体进行体积捕捉
VRSTC_ Occlusion-Free Video Person Re-IdentificationVRSTC_无遮挡视频人物再识别
WarpGAN_ Automatic Caricature GenerationWarpGAN_自动漫画生成
Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up自下而上的细粒度图像分类的弱监督互补部分模型
Weakly Supervised Deep Image Hashing Through Tag Embeddings通过标签嵌入的弱监督深度图像散列
Weakly Supervised Image Classification Through Noise Regularization通过噪声正则化的弱监督图像分类
Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations具有像素间关系的实例分割的弱监督学习
Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration基于双域协作的弱监督开放集域自适应
Weakly Supervised Person Re-Identification弱监督人员重新识别
Weakly Supervised Video Moment Retrieval From Text Queries来自文本查询的弱监督视频时刻检索
Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation用于 3D 人体姿势估计的几何感知表示的弱监督发现
What and How Well You Performed_ A Multitask Learning Approach to Action Quality Assessment你的表现和表现如何_行动质量评估的多任务学习方法
What Correspondences Reveal About Unknown Camera and Motion Models_哪些通信揭示了未知的相机和运动模型_
What Do Single-View 3D Reconstruction Networks Learn_单视图 3D 重建网络学到了什么_
What Does It Mean to Learn in Deep Networks_ And, How Does One Detect Adversarial Attacks_在深度网络中学习意味着什么_以及如何检测对抗性攻击_
What Object Should I Use_ - Task Driven Object Detection我应该使用什么对象_ - 任务驱动的对象检测
What’s to Know_ Uncertainty as a Guide to Asking Goal-Oriented Questions要知道什么_不确定性作为提出目标导向问题的指南
When Color Constancy Goes Wrong_ Correcting Improperly White-Balanced Images当颜色恒定性出错时_纠正不正确的白平衡图像
Where’s Wally Now_ Deep Generative and Discriminative Embeddings for Novelty DetectionWally 现在在哪里_ 用于新奇检测的深度生成和判别嵌入
Which Way Are You Going_ Imitative Decision Learning for Path Forecasting in Dynamic Scenes你走哪条路_动态场景中路径预测的模仿决策学习
Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem为什么 ReLU 网络会产生远离训练数据的高置信度预测以及如何缓解该问题
Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs通过地平面密度图和多视图融合 CNN 进行广域人群计数
Wide-Context Semantic Image Extrapolation宽上下文语义图像外推
World From Blur模糊世界
X2CT-GAN_ Reconstructing CT From Biplanar X-Rays With Generative Adversarial NetworksX2CT-GAN_使用生成对抗网络从双平面 X 射线重建 CT
You Look Twice_ GaterNet for Dynamic Filter Selection in CNNsYou Look Twice_GaterNet 用于 CNN 中的动态过滤器选择
You Reap What You Sow_ Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection播种即收_使用视频生成用于弱监督对象检测的高精度对象建议
Zero-Shot Task Transfer零样本任务转移
ZigZagNet_ Fusing Top-Down and Bottom-Up Context for Object SegmentationZigZagNet_融合自顶向下和自底向上的上下文进行对象分割
Zoom to Learn, Learn to Zoom放大学习，学习放大
Zoom-In-To-Check_ Boosting Video Interpolation via Instance-Level DiscriminationZoom-In-To-Check_通过实例级判别提升视频插值