【检测分类】
【1】 Boosting rare benthic macroinvertebrates taxa identification with one-class classification
用一类分类促进稀有底栖大型无脊椎动物分类鉴定
作者: Fahad Sohrab, Jenni Raitoharju
链接:https://arxiv.org/abs/2002.10420
【2】 Learning Attentive Pairwise Interaction for Fine-Grained Classification
细粒度分类的注意成对交互学习
作者: Peiqin Zhuang, Yu Qiao
备注:Accepted at AAAI-2020
链接:https://arxiv.org/abs/2002.10191
【3】 SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
Smoke:基于关键点估计的单级单目3D目标检测
作者: Zechen Liu, Roland Tóth
链接:https://arxiv.org/abs/2002.10111
【4】 VisionGuard: Runtime Detection of Adversarial Inputs to Perception Systems
VisionGuard:感知系统的对抗性输入的运行时检测
作者: Yiannis Kantaros, James Weimer
链接:https://arxiv.org/abs/2002.09792
【5】 Active Lighting Recurrence by Parallel Lighting Analogy for Fine-Grained Change Detection
用于细粒度变化检测的并行照明类比主动照明递归
作者: Qian Zhang, Ping Tan
链接:https://arxiv.org/abs/2002.09663
【6】 UnMask: Adversarial Detection and Defense Through Robust Feature Alignment
揭开掩码:通过健壮的特征对齐进行对抗性检测和防御
作者: Scott Freitas, Duen Horng Chau
链接:https://arxiv.org/abs/2002.09576
【7】 Deep Nearest Neighbor Anomaly Detection
深最近邻异常检测
作者: Liron Bergman, Yedid Hoshen
链接:https://arxiv.org/abs/2002.10445
[语义分割]:
【1】 Comparing View-Based and Map-Based Semantic Labelling in Real-Time SLAM
实时SLAM中基于视图和基于地图的语义标注比较
作者: Zoe Landgraf, Andrew Davison
备注:ICRA 2020
链接:https://arxiv.org/abs/2002.10342
【2】 Semantic Flow for Fast and Accurate Scene Parsing
用于快速准确场景解析的语义流
作者: Xiangtai Li, Yunhai Tong
链接:https://arxiv.org/abs/2002.10120
【3】 Assembling Semantically-Disentangled Representations for Predictive-Generative Models via Adaptation from Synthetic Domain
通过自适应从合成域组装预测-生成模型的语义解缠表示
作者: Burkay Donderici, Chenliang Xu
链接:https://arxiv.org/abs/2002.09818
【4】 Random Bundle: Brain Metastases Segmentation Ensembling through Annotation Randomization
随机束:通过注释随机化的脑转移瘤分割集合
作者: Darvin Yi, Daniel Rubin
链接:https://arxiv.org/abs/2002.09809
【5】 Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion
基于特征解缠和门控融合的鲁棒多模态脑肿瘤分割
作者: Cheng Chen, Pheng-Ann Heng
备注:MICCAI 2019
链接:https://arxiv.org/abs/2002.09708
【6】 Kullback-Leibler Divergence-Based Fuzzy C C C-Means Clustering Incorporating Morphological Reconstruction and Wavelet Frames for Image Segmentation
基于Kullback-Leibler散度的模糊C$均值聚类结合形态重建和小波帧的图像分割
作者: Cong Wang, MengChu Zhou
链接:https://arxiv.org/abs/2002.09479
【7】 Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation
通过深度强化学习的自动数据增强用于有效的肾脏肿瘤分割
作者: Tiexin Qin, Dinggang Shen
链接:https://arxiv.org/abs/2002.09703
【8】 Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning
基于深度学习的光学相干断层扫描图像的无标签三维分割
作者: Sripad Krishna Devalla, Michael J. A. Girard
链接:https://arxiv.org/abs/2002.09635
【9】 Convex Shape Representation with Binary Labels for Image Segmentation: Models and Fast Algorithms
用于图像分割的二值标签凸形表示:模型和快速算法
作者: Shousheng Luo, Yang Wang
链接:https://arxiv.org/abs/2002.09600
[人脸]:
【1】 Suppressing Uncertainties for Large-Scale Facial Expression Recognition
大规模人脸表情识别中的不确定性抑制
作者: Kai Wang, Yu Qiao
备注:This manuscript has been accepted by CVPR2020
链接:https://arxiv.org/abs/2002.10392
【2】 Audio-driven Talking Face Video Generation with Natural Head Pose
基于自然头部姿势的音频驱动说话人脸视频生成
作者: Ran Yi, Yong-Jin Liu
链接:https://arxiv.org/abs/2002.10137
【3】 DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition
DotFAN:一种面向姿态和光照不变人脸识别的域转移人脸增强网络
作者: Hao-Chiang Shao, Jiwen Lu
链接:https://arxiv.org/abs/2002.09859
[半/弱/无监督学习进展]:
【1】 Self-Supervised Poisson-Gaussian Denoising
自监督泊松-高斯去噪
作者: Wesley Khademi, Jonathan Ventura
链接:https://arxiv.org/abs/2002.09558
[跟踪]:
【1】 Guessing State Tracking for Visual Dialogue
视觉对话的猜测状态跟踪
作者: Wei Pang, Xiaojie Wang
备注:9 pages, 5 figures, Nov. 2019, this https URL
链接:https://arxiv.org/abs/2002.10340
【2】 Particle Filter Based Monocular Human Tracking with a 3D Cardbox Model and a Novel Deterministic Resampling Strategy
基于粒子滤波的三维纸盒模型和一种新的确定性重采样策略的单目人体跟踪
作者: Ziyuan Liu, Wolfgang Sepp
链接:https://arxiv.org/abs/2002.09554
[迁移学习/domain/主动学习/自适应]:
【1】 ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
ABCNet:基于自适应Bezier-Curve网络的实时场景文本定位
作者: Yuliang Liu, Liangwei Wang
备注:Accepted to Proc. IEEE Conf. Comp. Vis. Pattern Recogn. (CVPR) 2020
链接:https://arxiv.org/abs/2002.10200
【2】 Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference
三赢:通过启用输入自适应推理,一起提高准确性、健壮性和效率
作者: Ting-Kuei Hu, Zhangyang Wang
链接:https://arxiv.org/abs/2002.10025
【3】 Self-Adaptive Training: beyond Empirical Risk Minimization
自适应培训:超越经验风险最小化
作者: Lang Huang, Hongyang Zhang
链接:https://arxiv.org/abs/2002.10319
【4】 Towards Robust and Reproducible Active Learning Using Neural Networks
使用神经网络实现健壮和可重复性的主动学习
作者: Prateek Munjal, Shadab Khan
链接:https://arxiv.org/abs/2002.09564
[裁剪/量化/加速]:
【1】 HRank: Filter Pruning using High-Rank Feature Map
HRank:使用高等级特征映射的过滤器修剪
作者: Mingbao Lin, Ling Shao
链接:https://arxiv.org/abs/2002.10179
【2】 Generalized Octave Convolutions for Learned Multi-Frequency Image Compression
用于学习多频图像压缩的广义倍频程卷积
作者: Mohammad Akbari, Chengjie Tu
链接:https://arxiv.org/abs/2002.10032
【3】 Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks
使用卷积神经网络的特征相关性分数进行训练时的渐进式信道剪枝
作者: Sai Aparna Aketi, Kaushik Roy
链接:https://arxiv.org/abs/2002.09958
【4】 Neural Architecture Search for Compressed Sensing Magnetic Resonance Image Reconstruction
神经结构搜索在压缩传感磁共振图像重建中的应用
作者: Jiangpeng Yan, Yongbing Zhang
链接:https://arxiv.org/abs/2002.09625
[视频理解VQA/caption等]:
【1】 Image to Language Understanding: Captioning approach
图像到语言理解:字幕方法
作者: Madhavan Seshadri, Mikhail Belov
链接:https://arxiv.org/abs/2002.09536
[点云]:
【1】 PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling
PUGeo-net:一种以几何为中心的三维点云上采样网络
作者: Yue Qian, Ying He
链接:https://arxiv.org/abs/2002.10277
[3D/3D重建等]:
【1】 3DSSD: Point-based 3D Single Stage Object Detector
3DSSD:基于点的3D单级目标检测器
作者: Zetong Yang, Jiaya Jia
链接:https://arxiv.org/abs/2002.10187
【2】 Monocular Direct Sparse Localization in a Prior 3D Surfel Map
先前3D Surfel地图中的单目直接稀疏定位
作者: Haoyang Ye, Ming Liu
备注:7 pages, 6 figures, to appear in ICRA 2020
链接:https://arxiv.org/abs/2002.09923
[人群计数]:
【1】 Multi-Stream Networks and Ground-Truth Generation for Crowd Counting
用于人群计数的多流网络和地面真相生成
作者: Rodolfo Quispe, Helio Pedrini
链接:https://arxiv.org/abs/2002.09951
[视频相关]:
【1】 Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction
探索用于高保真和时间一致性视频预测的时空多频分析
作者: Beibei Jin, Xiaowei Li
链接:https://arxiv.org/abs/2002.09905