同步wx订阅号(arXiv每日论文速递),支持后台回复'search 关键词'查询相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)
cs.CV 方向,今日共计36篇
[检测分类相关]:
【1】 Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes
检测11K类:没有细粒度包围盒的大规模对象检测
作者: Hao Yang, Hao Chen
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.05217
【2】 Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy
基于最大分类器差异的无监督分布失配检测
作者: Qing Yu, Kiyoharu Aizawa
链接:https://arxiv.org/abs/1908.04951
【3】 Generalised Zero-Shot Learning with Domain Classification in a Joint Semantic and Visual Space
语义和视觉空间结合领域分类的广义零射击学习
作者: Rafael Felix, Gustavo Carneiro
链接:https://arxiv.org/abs/1908.04930
[分割/语义相关]:
【1】 DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation
DAPAS:对自动编码器进行去噪以防止语义分割中的对抗攻击
作者: Seung Ju Cho, Daeyoung Kim
链接:https://arxiv.org/abs/1908.05195
【2】 Shape-Aware Complementary-Task Learning for Multi-Organ Segmentation
面向多器官分割的形状感知互补任务学习
作者: Fernando Navarro, Bjoern Menze
备注:Accepted in MLMI Workshop 2019 MICCAI
链接:https://arxiv.org/abs/1908.05099
【3】 Benchmarking the Robustness of Semantic Segmentation Models
对语义分割模型的健壮性进行基准测试
作者: Christoph Kamann, Carsten Rother
链接:https://arxiv.org/abs/1908.05005
【4】 Faster Unsupervised Semantic Inpainting: A GAN Based Approach
快速无监督语义修复:一种基于GAN的方法
作者: Avisek Lahiri, Prabir Kumar Biswas
备注:Accepted as full paper at IEEE ICIP, 2019
链接:https://arxiv.org/abs/1908.04968
【5】 3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
3-D场景图:智能Agent物理环境的稀疏语义表示
作者: Ue-Hwan Kim, Jong-Hwan Kim
链接:https://arxiv.org/abs/1908.04929
【6】 D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation
D-UNET:一种用于慢性卒中病变分割的维度融合U形网络
作者: Yongjin Zhou, Shanshan Wang
链接:https://arxiv.org/abs/1908.05104
【7】 Segmentation of Multimodal Myocardial Images Using Shape-Transfer GAN
基于形状转移GAN的多模态心肌图像分割
作者: Xumin Tao, Dong Ni
备注:accepted by STACOM 21019
链接:https://arxiv.org/abs/1908.05094
【8】 Boosting Liver and Lesion Segmentation from CT Scans By Mask Mining
利用掩模挖掘增强CT扫描中的肝脏和病变分割
作者: Karsten Roth, Tomasz Konopczyński
链接:https://arxiv.org/abs/1908.05062
[GAN/对抗式/生成式相关]:
【1】 Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once
一次一人:通过学习多目标对抗网络一次走向多目标攻击
作者: Jiangfan Han, Xiaogang Wang
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.05185
【2】 AdvFaces: Adversarial Face Synthesis
AdvFaces:对抗性脸部合成
作者: Debayan Deb, Anil K. Jain
链接:https://arxiv.org/abs/1908.05008
[半/弱/无监督相关]:
【1】 Semi-supervised Learning with Adaptive Neighborhood Graph Propagation Network
基于自适应邻域图传播网络的半监督学习
作者: Bo Jiang, Bin Luo
链接:https://arxiv.org/abs/1908.05153
[裁剪/量化/加速相关]:
【1】 Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks
可微软量化:桥接全精度和低位神经网络
作者: Ruihao Gong, Junjie Yan
备注:IEEE ICCV 2019
链接:https://arxiv.org/abs/1908.05033
[Re-id相关]:
【1】 GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification
GreyReID:一种基于RGB-灰色信息的人再识别的双流深度框架
作者: Lei Qi, Yang Gao
链接:https://arxiv.org/abs/1908.05142
【2】 Person Re-identification in Aerial Imagery
航空影像中人的再识别
作者: Shizhou Zhang, Yanning Zhang
链接:https://arxiv.org/abs/1908.05024
【3】 HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning
Hornet:一种通过图像字幕提高人Re-ID的分层分支循环网络
作者: Shiyang Yan, Lin Xu
备注:10 pages, 5 figures, published in IJCAI19
链接:https://arxiv.org/abs/1908.04915
[视频理解VQA/caption等]:
【1】 VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
VideoNavQA:弥合可视和具体化问答之间的差距
作者: Cătălina Cangea, Aaron Courville
备注:To appear at BMVC 2019. 15 pages, 5 figures
链接:https://arxiv.org/abs/1908.04950
【2】 Towards Diverse and Accurate Image Captions via Reinforcing Determinantal Point Process
通过强化判定点过程实现图像字幕的多样化和精确化
作者: Qingzhong Wang, Antoni B. Chan
链接:https://arxiv.org/abs/1908.04919
[数据集dataset]:
【1】 FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age
FairFace:平衡种族、性别和年龄的面部属性数据集
作者: Kimmo Kärkkäinen, Jungseock Joo
链接:https://arxiv.org/abs/1908.04913
[人脸相关]:
【1】 Directional TSDF: Modeling Surface Orientation for Coherent Meshes
方向TSDF:为相干网格的曲面方向建模
作者: Malte Splietker, Sven Behnke
链接:https://arxiv.org/abs/1908.05146
[其他]:
【1】 AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations
自动更正:噪声几何标注的深度归纳对齐
作者: Honglie Chen, Andrew Zisserman
备注:BMVC 2019 (Spotlight)
链接:https://arxiv.org/abs/1908.05263
【2】 Few-Shot Learning with Global Class Representations
使用全局班级表示的少数镜头学习
作者: Tiange Luo, Liwei Wang
备注:Accepted by ICCV2019
链接:https://arxiv.org/abs/1908.05257
【3】 A Tour of Convolutional Networks Guided by Linear Interpreters
线性解释器引导下的卷积网络之旅
作者: Pablo Navarrete Michelini, Xingqun Jiang
备注:To appear in ICCV 2019
链接:https://arxiv.org/abs/1908.05168
【4】 Deep Generalized Max Pooling
深度广义极大池
作者: Vincent Christlein, Andreas Maier
备注:ICDAR'19
链接:https://arxiv.org/abs/1908.05040
【5】 Memory-Based Neighbourhood Embedding for Visual Recognition
基于记忆的邻域嵌入用于视觉识别
作者: Suichan Li, Rui Zhao
备注:Accepted by ICCV2019 for oral presentation
链接:https://arxiv.org/abs/1908.04992
【6】 Learning Two-View Correspondences and Geometry Using Order-Aware Network
利用顺序感知网络学习两视图对应和几何
作者: Jiahui Zhang, Hongen Liao
备注:Accepted to ICCV 2019, and Winner solution to both tracks of CVPR IMW 2019 Challenge. Code will be available soon at this https URL
链接:https://arxiv.org/abs/1908.04964
【7】 A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading
汉语普通话唇读的级联序列到序列模型
作者: Ya Zhao, Mingli Song
链接:https://arxiv.org/abs/1908.04917
【8】 SP-NET: One Shot Fingerprint Singular-Point Detector
SP-NET:一次性指纹奇异点检测器
作者: Geetika Arora, Aditya Nigam
链接:https://arxiv.org/abs/1908.04842
【9】 Reactive Multi-Stage Feature Fusion for Multimodal Dialogue Modeling
用于多模态对话建模的反应式多阶段特征融合
作者: Yi-Ting Yeh, Yun-Nung Chen
备注:Accepted for a poster session at the DSTC7 workshop at AAAI 2019
链接:https://arxiv.org/abs/1908.05067
【10】 Fusion of Detected Objects in Text for Visual Question Answering
用于视觉问答的文本中检测对象的融合
作者: Chris Alberti, David Reitter
链接:https://arxiv.org/abs/1908.05054
【11】 Histographs: Graphs in Histopathology
组织图:组织病理学中的图形
作者: Shrey Gadiya, Amit Sethi
链接:https://arxiv.org/abs/1908.05020
【12】 Visualizing Image Content to Explain Novel Image Discovery
将图像内容可视化以解释新的图像发现
作者: Jake H. Lee, Kiri L. Wagstaff
链接:https://arxiv.org/abs/1908.05006
【13】 Harmonized Multimodal Learning with Gaussian Process Latent Variable Models
基于高斯过程潜变量模型的协调多模态学习
作者: Guoli Song, Qi Tian
链接:https://arxiv.org/abs/1908.04979
【14】 Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks
人机交互任务的概率多模态建模
作者: Joseph Campbell, Heni Ben Amor
链接:https://arxiv.org/abs/1908.04955
翻译:腾讯翻译君