首页 > 编程学习 > CVPR 2019 论文汇总(按方向划分,0409 更新中)[转载]

转载链接:http://bbs.cvmart.net/topics/302/cvpr2019paper

作为计算机视觉领域三大顶会之一,CVPR2019(2019.6.16-6.19在美国洛杉矶举办)被CVers 重点关注。目前CVPR 2019 接收结果已经出来啦,相关报道:1300篇!CVPR2019接收结果公布,你中了吗?
开设此帖希望可以实时跟进CVPR2019的即时信息及相关优秀论文,欢迎点击文末关注按钮file,即可获取本帖最新更新消息。

 

  • cvpr2019 accepted papers list

  • Github论文汇总链接(欢迎star)

  • 论文PDF下载(更新中,提取码:osvy)

  • 论文解读汇总



目录:(也欢迎大家推荐自己的CVPR2019文章,以下篇幅较大,分类如有错误欢迎留言指出和补充谢谢~)

检测 16
分割 19
分类、识别 7
跟踪 13
人脸 4
人体姿态估计 14
行为识别、手势识别 5
时序动作检测及视频相关 11
Related to Networks 28
GAN、图像文本生成 14
图像处理 8
点云、三维重建 12
VQA、视觉语言导航 7
多任务学习、迁移学习 2
自动驾驶、SLAM 8
人群计数 2
数据集 5
行人重识别 2
其他 122

 

 

检测

1、Stereo R-CNN based 3D Object Detection for Autonomous Driving
作者:Peiliang Li, Xiaozhi Chen, Shaojie Shen
论文链接:https://arxiv.org/abs/1902.09738


2、Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
作者:Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, Silvio Savarese
论文链接:https://arxiv.org/abs/1902.09630
论文解读:https://mp.weixin.qq.com/s/6QsyYtEVjavoLfU_lQF1pw


3、ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape 作者:Fabian Manhardt, Wadim Kehl, Adrien Gaidon
论文链接:https://arxiv.org/abs/1812.02781


4、Bi-Directional Cascade Network for Perceptual Edge Detection
作者:Jianzhong He, Shiliang Zhang, Ming Yang, Yanhu Shan, Tiejun Huang
论文链接:https://arxiv.org/abs/1902.10903
Github源码:https://github.com/pkuCactus/BDCN


5、RepMet: Representative-based metric learning for classification and one-shot object detection
作者:Leonid Karlinsky, Joseph Shtok, Sivan Harary, Eli Schwartz, Amit Aides, Rogerio Feris, Raja Giryes, Alex M. Bronstein
论文链接:https://arxiv.org/abs/1806.04728


6、Region Proposal by Guided Anchoring
作者:Jiaqi Wang, Kai Chen, Shuo Yang, Chen Change Loy, Dahua Lin
论文链接:https://arxiv.org/abs/1901.03278
论文解读:https://mp.weixin.qq.com/s/Sl958JkcJjy-HW9_c-SH4g
Github链接:https://github.com/open-mmlab/mmdetection


7、Less is More: Learning Highlight Detection from Video Duration
作者:Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman
论文链接:https://arxiv.org/abs/1903.00859


8、AIRD: Adversarial Learning Framework for Image Repurposing Detection
作者:Ayush Jaiswal, Yue Wu, Wael AbdAlmageed, Iacopo Masi, Premkumar Natarajan
论文链接:https://arxiv.org/abs/1903.00788


9、Feature Selective Anchor-Free Module for Single-Shot Object Detection
作者:Chenchen Zhu, Yihui He, Marios Savvides
论文链接:https://arxiv.org/abs/1903.00621


10、Learning Attraction Field Representation for Robust Line Segment Detection
作者:Nan Xue, Song Bai, Fudong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang
论文链接:https://arxiv.org/abs/1812.02122
代码链接:https://github.com/cherubicXN/afm_cvpr2019



11、Latent Space Autoregression for Novelty Detection
作者:Davide Abati, Angelo Porrello, Simone Calderara, Rita Cucchiara
论文链接:https://arxiv.org/abs/1807.01653
代码链接: https://github.com/aimagelab/novelty-detection


12、SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection(行人检测)
作者:Chengju Zhou,Meiqing Wu,Siew-Kei Lam
论文链接:https://arxiv.org/abs/1902.09080v1
论文摘要:本文将语义分割结果作为自我关注线索进行探索,以显着提高行人检测性能。


13、Strong-Weak Distribution Alignment for Adaptive Object Detection
作者:Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada, Kate Saenko
论文链接:https://arxiv.org/abs/1812.04798


14、Few-shot Adaptive Faster R-CNN
作者:Tao Wang, Xiaopeng Zhang, Li Yuan, Jiashi Feng
论文链接:https://arxiv.org/abs/1903.09372


15、Attention Based Glaucoma Detection: A Large-scale Database and CNN Model
作者:Liu Li, Mai Xu, Xiaofei Wang, Lai Jiang, Hanruo Liu
论文链接:https://arxiv.org/abs/1903.10831


16、Bounding Box Regression with Uncertainty for Accurate Object Detection(目标检测边界框回归损失算法)
作者:Yihui He, Chenchen Zhu, Jianren Wang, Marios Savvides, Xiangyu Zhang
论文链接:https://arxiv.org/abs/1809.08545
代码链接:https://github.com/yihui-he/KL-Loss


 

分割

1、Attention-guided Unified Network for Panoptic Segmentation
作者:Yanwei Li, Xinze Chen, Zheng Zhu, Lingxi Xie, Guan Huang, Dalong Du, Xingang Wang
论文链接:https://arxiv.org/abs/1812.03904
论文解读:https://mp.weixin.qq.com/s/1tohID6SM3weS476XU5okw


2、FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
作者:Paul Voigtlaender, Yuning Chai, Florian Schroff, Hartwig Adam, Bastian Leibe, Liang-Chieh Chen
论文链接:https://arxiv.org/abs/1902.09513


3、Associatively Segmenting Instances and Semantics in Point Clouds
作者:Xinlong Wang, Shu Liu, Xiaoyong Shen, Chunhua Shen, Jiaya Jia
论文链接:https://arxiv.org/abs/1902.09852
代码链接:https://github.com/WXinlong/ASIS


4、3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
作者:Ji Hou Angela Dai Matthias Nießner
论文链接:https://niessnerlab.org/projects/hou20183dsis.html
YouTube视频:https://youtu.be/IH9rNLD1-JE


5、Data augmentation using learned transforms for one-shot medical image segmentation
作者:Amy Zhao, Guha Balakrishnan, Frédo Durand, John V. Guttag, Adrian V. Dalca
论文链接:https://arxiv.org/abs/1902.09383


6、FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference
作者:Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon
论文链接:https://arxiv.org/abs/1902.10421



7、Dual Attention Network for Scene Segmentation
作者:Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, Hanqing Lu
论文链接:https://arxiv.org/abs/1809.02983
Github源码:https://github.com/junfu1115/DANet


8、Mask Scoring R-CNN
作者:Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, Xinggang Wang
论文链接:https://arxiv.org/abs/1903.00241
Github链接:https://github.com/zjhuang22/maskscoring_rcnn
论文解读:https://mp.weixin.qq.com/s/aP7O7AF6WoynWK_FFHkOTw


9、Hybrid Task Cascade for Instance Segmentation(实例分割)
作者:Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin
论文链接:https://arxiv.org/abs/1901.07518
论文解读:https://mp.weixin.qq.com/s/xug0xKfc9RgJEUci1a_xog
Github链接:https://github.com/open-mmlab/mmdetection


10、Object Counting and Instance Segmentation with Image-level Supervision
作者:Hisham Cholakkal, Guolei Sun (equal contribution), Fahad Shahbaz Khan, Ling Shao
论文链接:https://arxiv.org/abs/1903.02494


11、MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation
作者:Yazan Abu Farha, Juergen Gall
论文链接:https://arxiv.org/abs/1903.01945


12、Structured Knowledge Distillation for Semantic Segmentation(语义分割)
作者:Yifan Liu, Ke Chen, Chris Liu, Zengchang Qin, Zhenbo Luo, Jingdong Wang
论文链接:https://arxiv.org/abs/1903.04197


13、RVOS: End-to-End Recurrent Network for Video Object Segmentation
作者:Carles Ventura, Miriam Bellver, Andreu Girbau, Amaia Salvador, Ferran Marques, Xavier Giro-i-Nieto
论文链接:https://arxiv.org/abs/1903.05612
项目链接:https://imatge-upc.github.io/rvos/


14、Structured Knowledge Distillation for Semantic Segmentation(语义分割)
作者:Yifan Liu, Ke Chen, Chris Liu, Zengchang Qin, Zhenbo Luo, Jingdong Wang
论文链接:https://arxiv.org/abs/1903.04197


15、Knowledge Adaptation for Efficient Semantic Segmentation(语义分割)
作者:Tong He, Chunhua Shen, Zhi Tian, Dong Gong, Changming Sun, Youliang Yan
论文链接:https://arxiv.org/abs/1903.04688


16、Improving Semantic Segmentation via Video Propagation and Label Relaxation(oral)
作者:Yi Zhu, Karan Sapra, Fitsum A. Reda, Kevin J. Shih, Shawn Newsam, Andrew Tao, Bryan Catanzaro
论文链接:https://arxiv.org/abs/1812.01593


17、In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
作者:Marin Oršić, Ivan Krešo, Petra Bevandić, Siniša Šegvić
论文链接:https://arxiv.org/abs/1903.08469
代码链接:https://github.com/orsic/swiftnet


18、Large-scale interactive object segmentation with human annotators
作者:Rodrigo Benenson, Stefan Popov, Vittorio Ferrari
论文链接:https://arxiv.org/abs/1903.10830


19、Pose2Seg: Detection Free Human Instance Segmentation
作者:Song-Hai Zhang, Ruilong Li, Xin Dong, Paul L. Rosin, Zixi Cai, Han Xi, Dingcheng Yang, Hao-Zhi Huang, Shi-Min Hu
论文链接:https://arxiv.org/abs/1803.10683
项目链接:http://www.liruilong.cn/Pose2Seg/index.html
代码链接:https://github.com/liruilong940607/OCHumanApi



 

分类、识别

1、Learning a Deep ConvNet for Multi-label Classification with Partial Labels(分类)
作者:Thibaut Durand, Nazanin Mehrasa, Greg Mori
论文链接:https://arxiv.org/abs/1902.09720


2、Efficient Video Classification Using Fewer Frames
作者:Shweta Bhardwaj, Mukundhan Srinivasan, Mitesh M. Khapra
论文链接:https://arxiv.org/abs/1902.10640


3、Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up
作者:Weifeng Ge, Xiangru Lin, Yizhou Yu
论文链接:https://arxiv.org/abs/1903.02827


4、All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification(分类)
作者:Weijie Chen, Di Xie, Yuan Zhang, Shiliang Pu
论文链接:https://arxiv.org/abs/1903.05285


5、Bag of Tricks for Image Classification with Convolutional Neural Networks
作者:Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li
论文链接:https://arxiv.org/abs/1812.01187
源码链接:https://github.com/dmlc/gluon-cv
论文解读:图像分类技巧:Bag of Tricks for Image Classification with Convolutional Neural Networks


6、Direct Object Recognition Without Line-of-Sight Using Optical Coherence(目标识别)
作者:Xin Lei, Liangyu He, Yixuan Tan, Ken Xingze Wang, Xinggang Wang, Yihan Du, Shanhui Fan, Zongfu Yu
论文链接:https://arxiv.org/abs/1903.07705


7、Direct Object Recognition Without Line-of-Sight Using Optical Coherence(非视距物体识别技术)
作者:Xin Lei, Liangyu He, Yixuan Tan, Ken Xingze Wang, Xinggang Wang, Yihan Du, Shanhui Fan, Zongfu Yu
论文链接:https://arxiv.org/abs/1903.07705



 

跟踪

1、Fast Online Object Tracking and Segmentation: A Unifying Approach(SiamMask,目标跟踪)
作者:Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, Philip H.S. Torr
论文链接:https://arxiv.org/abs/1812.05050
Github链接:https://github.com/foolwood/SiamMask
project链接:http://www.robots.ox.ac.uk/~qwang/SiamMask/
论文解读:CVPR2019 | SiamMask:视频跟踪最高精度


2、Deeper and Wider Siamese Networks for Real-Time Visual Tracking(CIR,目标跟踪)
作者:Zhipeng Zhang, Houwen Peng
论文链接:https://arxiv.org/pdf/1901.01660.pdf
Code链接:https://gitlab.com/MSRA_NLPR/deeper_wider_siamese_trackers


3、SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks(目标跟踪)
作者:Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan
论文链接:https://arxiv.org/pdf/1812.11703.pdf
Project链接:http://bo-li.info/SiamRPN++/
论文解读:https://mp.weixin.qq.com/s/dB5u2No8eakLnrjto0kvyQ


4、Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking(CRPN,目标跟踪)
作者:Heng Fan, Haibin Ling
论文链接:https://arxiv.org/pdf/1812.06148.pdf


5、LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking(目标跟踪)
作者:Heng Fan, Liting Lin, Fan Yang, Peng Chu, Ge Deng, Sijia Yu, Hexin Bai, Yong Xu, Chunyuan Liao, Haibin Ling
论文链接:https://arxiv.org/pdf/1809.07845.pdf
project链接:https://cis.temple.edu/lasot/


6、Leveraging Shape Completion for 3D Siamese Tracking
作者:Silvio Giancola, Jesus Zarzar, Bernard Ghanem
论文链接:https://arxiv.org/abs/1903.01784


7、Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics(多目标跟踪)
作者:Yaron Meirovitch, Lu Mi, Hayk Saribekyan, Alexander Matveev, David Rolnick, Casimir Wierzynski, Nir Shavit
论文链接:https://arxiv.org/abs/1812.01157


8、Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation (POINT^2)
作者:Haofu Liao, Wei-An Lin, Jiarui Zhang, Jingdan Zhang, Jiebo Luo, S. Kevin Zhou
论文链接:https://arxiv.org/abs/1903.03896


9、Inverse Path Tracing for Joint Material and Lighting Estimation(Oral)
作者:Jiaxin Cheng, Yue Wu, Wael Abd-Almageed, Premkumar Natarajan
论文链接:https://arxiv.org/abs/1903.07145


10、Inverse Path Tracing for Joint Material and Lighting Estimation(Oral)
作者:Jiaxin Cheng, Yue Wu, Wael Abd-Almageed, Premkumar Natarajan
论文链接:https://arxiv.org/abs/1903.07145
 

11、Multi-person Articulated Tracking with Spatial and Temporal Embeddings
作者:Sheng Jin, Wentao Liu, Wanli Ouyang, Chen Qian
论文链接:https://arxiv.org/abs/1903.09214


12、CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
作者:Zheng Tang, Milind Naphade, Ming-Yu Liu, Xiaodong Yang, Stan Birchfield, Shuo Wang, Ratnesh Kumar, David Anastasiu, Jenq-Neng Hwang
论文链接:https://arxiv.org/abs/1903.09254


13、MOTS: Multi-Object Tracking and Segmentation
作者:Paul Voigtlaender, Michael Krause, Aljosa Osep, Jonathon Luiten, Berin Balachandar Gnana Sekar, Andreas Geiger, Bastian Leibe
论文链接:https://arxiv.org/abs/1902.03604


 

人脸

1、Disentangled Representation Learning for 3D Face Shape
作者:Baris Gecer, Stylianos Ploumpis, Irene Kotsia, Stefanos Zafeiriou
论文链接:https://arxiv.org/abs/1902.05978


2、Joint Face Detection and Facial Motion Retargeting for Multiple Faces
作者:Bindita Chaudhuri, Noranart Vesdapunt, Baoyuan Wang
论文链接:https://arxiv.org/abs/1902.10744


3、ArcFace: Additive Angular Margin Loss for Deep Face Recognition(人脸识别)
作者:Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou
论文链接:https://arxiv.org/abs/1801.07698
Demo链接:https://github.com/vita-epfl/openpifpafwebdemo


4、Linkage Based Face Clustering via Graph Convolution Network
作者:Zhongdao Wang, Liang Zheng, Yali Li, Shengjin Wang
论文链接:https://arxiv.org/abs/1903.11306


 

人体姿态估计

1、Deep High-Resolution Representation Learning for Human Pose Estimation(目前SOTA,已经开源)
作者:Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang
论文链接:https://128.84.21.199/abs/1902.09212
代码链接:https://github.com/leoxiaobin/deep-high-resolution-net.pytorch
论文解读:https://mp.weixin.qq.com/s/ZRCzBTBmlEzQCVo1HLWtbQ


2、DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
作者:Chen Wang, Danfei Xu, Yuke Zhu, Roberto Martín-Martín, Cewu Lu, Li Fei-Fei, Silvio Savarese
论文链接:https://arxiv.org/abs/1901.04780
论文解读:https://mp.weixin.qq.com/s/wrND2cocWlPPVXPqpq-Glg


3、RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
作者:Bastian Wandt, Bodo Rosenhahn
论文链接:https://arxiv.org/abs/1902.09868


4、3D Hand Shape and Pose Estimation from a Single RGB Image
作者:Liuhao Ge, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang, Jianfei Cai, Junsong Yuan
论文链接:https://arxiv.org/abs/1903.00812


5、Self-Supervised Learning of 3D Human Pose using Multi-view Geometry
作者:Muhammed Kocabas, Salih Karagoz, Emre Akbas
论文链接:https://arxiv.org/abs/1903.02330
Github链接:https://github.com/mkocabas/EpipolarPose


6、Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
作者:Junting Dong, Wen Jiang, Qixing Huang, Hujun Bao, Xiaowei Zhou
论文链接:https://arxiv.org/abs/1901.04111
项目链接:https://zju-3dv.github.io/mvpose/
代码链接:https://github.com/zju-3dv/mvpose


7、Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion (Oral)
作者:Zhenpei Yang, Jeffrey Z.Pan, Linjie Luo, Xiaowei Zhou, Kristen Grauman and Qixing Huang
论文链接:https://arxiv.org/pdf/1901.00063.pdf
代码链接: https://github.com/zhenpeiyang/RelativePose


8、PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
作者:Sida Peng, Yuan Liu, Qixing Huang, Hujun Bao, and Xiaowei Zhou
论文链接:https://arxiv.org/pdf/1812.11788.pdf


9、PoseFix: Model-agnostic General Human Pose Refinement Network
作者:Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee
论文链接:https://arxiv.org/abs/1812.03595
源码链接:https://github.com/mks0601/PoseFix_RELEASE


10、Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation(oral)
作者:He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas
论文链接:https://arxiv.org/abs/1901.02970


11、PifPaf: Composite Fields for Human Pose Estimation(姿态估计)
作者:Sven Kreiss, Lorenzo Bertoni, Alexandre Alahi
论文链接:https://arxiv.org/abs/1903.06593
Demo链接:https://github.com/vita-epfl/openpifpafwebdemo


12、Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation(Oral,3D姿态估计)
作者:Xipeng Chen, Kwan-Yee Lin, Wentao Liu, Chen Qian, Liang Lin
论文链接:https://arxiv.org/abs/1903.08839


13、CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
作者:Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, Cewu Lu
论文链接:https://arxiv.org/abs/1812.00324
代码链接:https://github.com/Jeff-sjtu/CrowdPose


14、Dense Intrinsic Appearance Flow for Human Pose Transfer
作者:Yining Li, Chen Huang, Chen Change Loy
论文链接:https://arxiv.org/abs/1903.11326


 

行为识别、手势识别

1、An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
作者:Chenyang Si, Wentao Chen, Wei Wang, Liang Wang, Tieniu Tan
论文链接:https://arxiv.org/abs/1902.09130


2、Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training
作者:Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel
链接:https://arxiv.org/abs/1812.06145


3、Collaborative Spatio-temporal Feature Learning for Video Action Recognition
作者:Chao Li, Qiaoyong Zhong, Di Xie, Shiliang Pu
论文链接:https://arxiv.org/abs/1903.01197


4、Peeking into the Future: Predicting Future Person Activities and Locations in Videos(行为预测)
作者:Junwei Liang, Lu Jiang, Juan Carlos Niebles, Alexander Hauptmann, Li Fei-Fei
论文链接:https://arxiv.org/abs/1902.03748


5、Neural Scene Decomposition for Multi-Person Motion Capture
作者:Helge Rhodin, Victor Constantin, Isinsu Katircioglu, Mathieu Salzmann, Pascal Fua
论文链接:https://arxiv.org/abs/1903.05684



 

时序动作检测及视频相关

1、Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
作者:Nayyer Aafaq, Naveed Akhtar, Wei Liu, Syed Zulqarnain Gilani, Ajmal Mian
论文链接:https://arxiv.org/abs/1902.10322
来源:https://mp.weixin.qq.com/s/61C-k3Ijy_7ry5B5lRML6Q


2、Single-frame Regularization for Temporally Stable CNNs(视频处理)
作者:Gabriel Eilertsen, Rafał K. Mantiuk, Jonas Unger
论文链接:https://arxiv.org/abs/1902.10424
来源:https://mp.weixin.qq.com/s/61C-k3Ijy_7ry5B5lRML6Q


3、Neural RGB-D Sensing: Depth estimation from a video
作者:Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa Narasimhan, Jan Kautz
论文链接:https://arxiv.org/pdf/1901.02571.pdf
project链接:https://research.nvidia.com/publication/2019-06_Neural-RGBD



4、Competitive Collaboration: Joint Unsupervised Learning of Depth, CameraMotion, Optical Flow and Motion Segmentation
作者:Anurag Ranjan, Varun Jampani, Kihwan Kim, Deqing Sun, Jonas Wulff, Michael J. Black
论文链接:https://arxiv.org/pdf/1805.09806.pdf



5、Representation Flow for Action Recognition
作者:AJ Piergiovanni, Michael S. Ryoo
论文链接:https://arxiv.org/abs/1810.01455
项目链接:https://piergiaj.github.io/rep-flow-site/
代码链接:https://github.com/piergiaj/representation-flow-cvpr19


6、Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
作者:Romero Morais, Vuong Le, Truyen Tran, Budhaditya Saha, Moussa Mansour, Svetha Venkatesh
论文链接:https://arxiv.org/abs/1903.03295


7、Video Generation from Single Semantic Label Map
作者:Junting Pan, Chengyu Wang, Xu Jia, Jing Shao, Lu Sheng, Junjie Yan, Xiaogang Wang
论文链接:https://arxiv.org/abs/1903.04480
源码链接:https://github.com/junting/seg2vid/tree/master


8、Inserting Videos into Videos
作者:Donghoon Lee, Tomas Pfister, Ming-Hsuan Yang
论文链接:https://arxiv.org/abs/1903.06571


9、Recurrent Back-Projection Network for Video Super-Resolution
作者:Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
论文链接:https://alterzero.github.io/projects/rbpn_cvpr2019.pdf
代码链接:https://github.com/alterzero/RBPN-PyTorch
项目链接:https://alterzero.github.io/projects/RBPN.html


10、Depth-Aware Video Frame Interpolation
作者:Wenbo Bao Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang
论文链接:https://sites.google.com/view/wenbobao/dain
代码链接:https://github.com/baowenbo/DAIN



11、Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph
作者:Yao-Hung Hubert Tsai, Santosh Divvala, Louis-Philippe Morency, Ruslan Salakhutdinov, Ali Farhadi
论文链接:https://arxiv.org/abs/1903.10547


12、Dual Encoding for Zero-Example Video Retrieval
作者:Jianfeng Dong, Xirong Li, Chaoxi Xu, Shouling Ji, Yuan He, Gang Yang and Xun Wang
论文链接:https://arxiv.org/abs/1809.06181
代码链接:https://github.com/danieljf24/dual_encoding


13、Rethinking the Evaluation of Video Summaries
作者:Jacques Manderscheid, Amos Sironi, Nicolas Bourdis, Davide Migliore, Vincent Lepetit
论文链接:https://arxiv.org/abs/1903.11328



 

Related to Networks

1、RePr: Improved Training of Convolutional Filters
作者:Aaditya Prakash, James Storer, Dinei Florencio, Cha Zhang
论文链接:https://arxiv.org/abs/1811.07275


2、Iterative Residual CNNs for Burst Photography Applications
作者:Filippos Kokkinos   Stamatis Lefkimmiatis
论文链接:https://arxiv.org/abs/1811.12197


3、SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Images
作者:Yeon Kun Lee, Jaeseok Jeong, Jong Seob Yun, Cho Won June, Kuk-Jin Yoon
论文链接:https://arxiv.org/abs/1811.08196


4、On the Continuity of Rotation Representations in Neural Networks
作者:Yi Zhou, Connelly Barnes, Jingwan Lu, Jimei Yang, Hao Li
论文链接:https://arxiv.org/pdf/1812.07035.pdf


5、Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?
作者:Shilin Zhu, Xin Dong, Hao Su
论文链接:https://arxiv.org/abs/1806.07550
简要:Ensemble of binary neural networks has better stability and robustness, and may perform as well as floating-point networks.


6、A Neurobiological Evaluation Metric for Neural Network Model Search
作者:Nathaniel Blanchard, Jeffery Kinnison, Brandon RichardWebster, Pouya Bashivan, Walter J. Scheirer
论文链接:https://arxiv.org/pdf/1805.10726.pdf


7、MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment
作者:Da Zhang, Xiyang Dai, Xin Wang, Yuan-Fang Wang, Larry S. Davis
论文链接:https://arxiv.org/pdf/1812.00087.pdf


8、Multi-Step Prediction of Occupancy Grid Maps with Recurrent Neural Networks
作者:Nima Mohajerin, Mohsen Rohani
论文链接:https://arxiv.org/pdf/1812.09395.pdf


9、Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem(oral)
作者:Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf
论文链接:https://arxiv.org/abs/1812.05720
Reading Note:In the paper, we give a theoretical argument of why ReLU activation can lead to models with overconfident predictions. Moreover, we propose a robust optimization training scheme that mitigates this problem.


10、RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion
作者:Jie Li, Yu Liu, Dong Gong, Qinfeng Shi, Xia Yuan, Chunxia Zhao, Ian Reid
论文链接:https://arxiv.org/abs/1903.00620


11、PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation
作者:Fenggen Yu, Kun Liu, Yan Zhang, Chenyang Zhu, Kai Xu
论文链接:https://arxiv.org/abs/1903.00709


12、3D Point-Capsule Networks
作者:Yongheng Zhao, Tolga Birdal, Haowen Deng, Federico Tombari
论文链接:https://arxiv.org/abs/1812.10775


13、CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
作者:Chi Zhang, Guosheng Lin, Fayao Liu, Rui Yao, Chunhua Shen
论文链接:https://arxiv.org/abs/1903.02351


14、Path-Invariant Map Networks (Oral)
作者:Zaiwei Zhang, Zhenxiao Liang, Lemeng Wu, Xiaowei Zhou and Qixing Huang
论文链接:https://arxiv.org/pdf/1812.11647.pdf
代码链接: https://github.com/zaiweizhang/path_invariance_map_network
 

15、A Main/Subsidiary Network Framework for Simplifying Binary Neural Network
作者:Yinghao Xu, Xin Dong, Yudian Li, Hao Su
论文链接:https://arxiv.org/abs/1812.04210
简要:A simple learning-based binary neural network pruning scheme.


16、Knowledge-Embedded Routing Network for Scene Graph Generation
作者:Tianshui Chen, Weihao Yu, Riquan Chen, Liang Lin
论文链接:https://arxiv.org/abs/1903.03326


17、Knowledge-Embedded Routing Network for Scene Graph Generation
作者:Tianshui Chen, Weihao Yu, Riquan Chen, Liang Lin
论文链接:https://arxiv.org/abs/1903.03326


18、HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
作者:Pravendra Singh, Vinay Kumar Verma, Piyush Rai, Vinay P. Namboodiri
论文链接:https://arxiv.org/abs/1903.04120

 

19、Large-scale Distributed Second-order Optimization Using Kronecker-factored Approximate Curvature for Deep Convolutional Neural Networks
作者:Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka
论文链接:https://arxiv.org/abs/1811.12019


20、ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding
作者:Ning Liu, Yongchao Long, Changqing Zou, Qun Niu, Li Pan, Hefeng Wu
论文链接:https://arxiv.org/abs/1811.11968


21、LaSO: Label-Set Operations networks for multi-label few-shot learning(oral)
作者:Amit Alfassy, Leonid Karlinsky, Amit Aides, Joseph Shtok, Sivan Harary, Rogerio Feris, Raja Giryes, Alex M. Bronstein
论文链接:https://arxiv.org/abs/1902.09811


22、Selective Kernel Networks
作者:Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang
论文链接:https://arxiv.org/abs/1903.06586
源码链接:https://github.com/implus/SKNet


23、Self-calibrating Deep Photometric Stereo Networks(Oral)
作者:Guanying Chen, Kai Han, Boxin Shi, Yasuyuki Matsushita, Kwan-Yee K. Wong
论文链接:https://arxiv.org/abs/1903.07366
项目链接:http://gychen.org/SDPS-Net/
代码链接:https://github.com/guanyingc/SDPS-Net


24、Self-calibrating Deep Photometric Stereo Networks(Oral)
作者:Guanying Chen, Kai Han, Boxin Shi, Yasuyuki Matsushita, Kwan-Yee K. Wong
论文链接:https://arxiv.org/abs/1903.07366
项目链接:http://gychen.org/SDPS-Net/
代码链接:https://github.com/guanyingc/SDPS-Net


25、Networks for Joint Affine and Non-parametric Image Registration
作者:Zhengyang Shen, Xu Han, Zhenlin Xu, Marc Niethammer
论文链接:https://arxiv.org/abs/1903.08811


26、Learning for Single-Shot Confidence Calibration in Deep Neural Networks through Stochastic Inferences
作者:Seonguk Seo, Paul Hongsuck Seo, Bohyung Han
论文链接:https://arxiv.org/abs/1810.02358


27、Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
作者:Shaohui Lin, Rongrong Ji, Chenqian Yan, Baochang Zhang, Liujuan Cao, Qixiang Ye, Feiyue Huang, David Doermann
论文链接:https://arxiv.org/abs/1903.09291


28、TIN: Transferable Interactiveness Network
作者:Yong-Lu Li, Siyuan Zhou, Xijie Huang, Liang Xu, Ze Ma, Hao-Shu Fang, Yan-Feng Wang, Cewu Lu
论文链接:https://arxiv.org/abs/1811.08264
代码链接:

https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network


 

GAN、图像文本生成

1、Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks
作者:S. Mohammad Mostafavi I., Lin Wang, Yo-Sung Ho, Kuk-Jin Yoon
论文链接:https://arxiv.org/abs/1811.08230


2、Mixture Density Generative Adversarial Networks
作者:Hamid Eghbal-zadeh, Werner Zellinger, Gerhard Widmer
论文链接:https://arxiv.org/abs/1811.00152


3、GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
作者:Baris Gecer, Stylianos Ploumpis, Irene Kotsia, Stefanos Zafeiriou
论文链接:https://arxiv.org/abs/1902.05978
github链接:https://github.com/barisgecer/ganfit


4、Self-Supervised Generative Adversarial Networks
作者:Ting Chen, Xiaohua Zhai, Marvin Ritter, Mario Lucic, Neil Houlsby
论文链接:https://arxiv.org/abs/1811.11212
Github链接:https://github.com/google/compare_gan


5、CollaGAN : Collaborative GAN for Missing Image Data Imputation
作者:Dongwook Lee, Junyoung Kim, Won-Jin Moon, Jong Chul Ye
论文链接:https://arxiv.org/abs/1901.09764


6、Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
作者:Qi Mao, Hsin-Ying Lee, Hung-Yu Tseng, Siwei Ma, Ming-Hsuan Yang
论文链接:https://arxiv.org/abs/1903.05628
代码链接:https://github.com/HelenMao/MSGAN (待更新)


7、MirrorGAN: Learning Text-to-image Generation by Redescription(图像文本生成)
作者:Tingting Qiao, Jing Zhang, Duanqing Xu, Dacheng Tao
论文链接:https://arxiv.org/abs/1903.05854


8、From Adversarial Training to Generative Adversarial Networks
作者:Xuanqing Liu, Cho-Jui Hsieh
论文链接:https://arxiv.org/pdf/1807.10454.pdf


9、OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
作者:Pramuditha Perera, Ramesh Nallapati, Bing Xiang
论文链接:https://arxiv.org/abs/1903.08550


10、SalGAN: Visual Saliency Prediction with Generative Adversarial Networks(商汤/华为/港中文)
作者:Junting Pan, Cristian Canton Ferrer, Kevin McGuinness, Noel E. O'Connor, Jordi Torres, Elisa Sayrol, Xavier Giro-i-Nieto
论文链接:https://arxiv.org/abs/1701.01081
代码链接:https://github.com/junting/seg2vid


11、StoryGAN: A Sequential Conditional GAN for Story Visualization(图像文本生成)
作者:Yitong Li, Zhe Gan, Yelong Shen, Jingjing Liu, Yu Cheng, Yuexin Wu, Lawrence Carin, David Carlson, Jianfeng Gao
论文链接:https://arxiv.org/abs/1812.02784
代码链接:https://github.com/yitong91/StoryGAN


12、Object-driven Text-to-Image Synthesis via Adversarial Training(图像文本生成)
作者:Wenbo Li, Pengchuan Zhang, Lei Zhang, Qiuyuan Huang, Xiaodong He, Siwei Lyu, Jianfeng Gao
论文链接:https://arxiv.org/abs/1902.10740


13、Text2Scene: Generating Compositional Scenes from Textual Descriptions
作者:Yitong Li, Zhe Gan, Yelong Shen, Jingjing Liu, Yu Cheng, Yuexin Wu, Lawrence Carin, David Carlson, Jianfeng Gao
论文链接:https://arxiv.org/abs/1809.01110
代码链接:https://github.com/uvavision/Text2Image


14、Image Generation from Layout
作者:Bo Zhao, Lili Meng, Weidong Yin, Leonid Sigal
论文链接:https://arxiv.org/abs/1811.11389



 

图像处理

1、Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
作者:Yao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan
论文链接:https://arxiv.org/abs/1902.10556
代码链接:https://github.com/YoYo000/MVSNet


2、Unprocessing Images for Learned Raw Denoising (Oral Presentation)
作者:Tim Brooks, Ben Mildenhall, Tianfan Xue, Jiawen Chen, Dillon Sharlet, Jonathan T. Barron
论文链接:https://arxiv.org/abs/1811.11127
project链接:http://timothybrooks.com/tech/unprocessing/
Reading note:We can learn a better denoising model by processing and unprocessing images the same way a camera does.


3、Image Super-Resolution by Neural Texture Transfer
作者:Zhifei Zhang, Zhaowen Wang, Zhe Lin, Hairong Qi
论文链接:https://arxiv.org/pdf/1903.00834.pdf
项目链接:http://web.eecs.utk.edu/~zzhang61/project_page/SRNTT/SRNTT.html
代码链接:https://github.com/ZZUTK/SRNTT


4、Toward Convolutional Blind Denoising of Real Photographs
作者:Shi Guo, Zifei Yan, Kai Zhang, Wangmeng Zuo, Lei Zhang
论文链接:https://arxiv.org/abs/1807.04686
代码链接:https://github.com/GuoShi28/CBDNet


5、Learning Parallax Attention for Stereo Image Super-Resolution(图像超分辨)
作者:Longguang Wang, Yingqian Wang, Zhengfa Liang, Zaiping Lin, Jungang Yang, Wei An, Yulan Guo
论文链接:https://arxiv.org/abs/1903.05784


6、Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
作者:Xing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani
论文链接:https://arxiv.org/abs/1903.08817


7、PASSRnet: Parallax Attention Stereo Super-Resolution Network
作者:Longguang Wang, Yingqian Wang, Zhengfa Liang, Zaiping Lin, Jungang Yang, Wei An, Yulan Guo
论文链接:https://arxiv.org/abs/1903.05784
代码链接:https://github.com/LongguangWang/PASSRnet


8、Feedback Network for Image Super-Resolution
作者:Zhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, Wei Wu
论文链接:https://arxiv.org/abs/1903.09814


 

3D点云、三维重建

1、The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
作者:Zan Gojcic, Caifa Zhou, Jan D. Wegner, Andreas Wieser
论文链接:https://arxiv.org/abs/1811.06879


2、Octree guided CNN with Spherical Kernels for 3D Point Clouds
作者:Huan Lei, Naveed Akhtar, Ajmal Mian
论文链接:https://arxiv.org/abs/1903.00343


3、DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds
作者:Li Ding, Chen Feng
论文链接:https://arxiv.org/abs/1811.11397


4、Generating 3D Adversarial Point Clouds
作者:Chong Xiang (1), Charles R. Qi (2), Bo Li (3) ((1) Shanghai Jiao Tong Univerisity, (2) Stanford University, (3) University of Illinois at Urbana-Champaign)
论文链接:https://arxiv.org/abs/1809.07016
简要:Proposed several novel algorithms to craft adversarial point clouds against 3D deep learning models with adversarial points perturbation and adversarial points generation.


5、FlowNet3D: Learning Scene Flow in 3D Point Clouds
作者:Xingyu Liu, Charles R. Qi, Leonidas J. Guibas
论文链接:https://arxiv.org/abs/1806.01411
简要:Proposed a novel deep neural network that learns scene flow from point clouds in an end-to-end fashion.


6、33.Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding(开源)
作者:Zehao Yu, Jia Zheng, Dongze Lian, Zihan Zhou, Shenghua Gao
论文链接:https://arxiv.org/abs/1902.09777
代码链接:https://github.com/svip-lab/PlanarReconstruction


7、FML: Face Model Learning from Videos(Oral)
作者:A. Tewari F. Bernard P. Garrido G. Bharaj M. Elgharib H-P. Seidel P. Perez M. Zollhöfer C.Theobalt
项目链接:http://gvv.mpi-inf.mpg.de/projects/FML19/
论文链接:http://gvv.mpi-inf.mpg.de/projects/FML19/paper.pdf


8、SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representation
作者:Shuaifeng Zhi, Michael Bloesch, Stefan Leutenegger, Andrew J. Davison
论文链接:https://arxiv.org/abs/1903.06482


9、Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
作者:Pelin Dogan, Leonid Sigal, Markus Gross
论文链接:
https://chenhsuanlin.bitbucket.io/photometric-mesh-optim/paper.pdf
代码链接:
https://github.com/chenhsuanlin/photometric-mesh-optim
项目链接:
https://chenhsuanlin.bitbucket.io/photometric-mesh-optim/


10、Learning View Priors for Single-view 3D Reconstruction
作者:Hiroharu Kato, Tatsuya Harada
论文链接:https://arxiv.org/abs/1811.10719
项目链接:http://hiroharu-kato.com/projects_en/view_prior_learning.html


11、Patch-based Progressive 3D Point Set Upsampling
作者:Wang Yifan, Shihao Wu, Hui Huang, Daniel Cohen-Or, Olga Sorkine-Hornung
论文链接:https://arxiv.org/abs/1811.11286
代码链接:https://github.com/yifita/3PU


12、GeoNet: Deep Geodesic Networks for Point Cloud Analysis(Oral,旷视,根据测地间隔的点云剖析深度网络)
作者:Tong He, Haibin Huang, Li Yi, Yuqian Zhou, Chihao Wu, Jue Wang, Stefano Soatto
论文链接:https://arxiv.org/abs/1901.00680
论文解读:CVPR 2019 | 旷视等Oral论文提出GeoNet:基于测地距离的点云分析深度网络


 

VQA、视觉语言导航

1、MUREL: Multimodal Relational Reasoning for Visual Question Answering
作者:Remi Cadene, Hedi Ben-younes, Matthieu Cord, Nicolas Thome
论文链接:https://arxiv.org/abs/1902.09487


2、Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
作者:Xin Wang, Qiuyuan Huang, Asli Celikyilmaz, Jianfeng Gao, Dinghan Shen, Yuan-Fang Wang, William Yang Wang, Lei Zhang
论文链接:https://arxiv.org/abs/1811.10092
论文解读:https://mp.weixin.qq.com/s/LsHWkdwqqrOPFgCNNcBdpg


3、Image-Question-Answer Synergistic Network for Visual Dialog
作者:Dalu Guo, Chang Xu, Dacheng Tao
论文链接:https://arxiv.org/abs/1902.09774


4、Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation(oral)
作者:Liyiming Ke, Xiujun Li, Yonatan Bisk, Ari Holtzman, Zhe Gan, Jingjing Liu, Jianfeng Gao, Yejin Choi, Siddhartha Srinivasa
论文链接:https://arxiv.org/abs/1903.02547
YouTube:https://youtu.be/ik9uz06Fcpk


5、Learning to Compose Dynamic Tree Structures for Visual Contexts(VQA,Oral)
作者:Kaihua Tang, Hanwang Zhang, Baoyuan Wu, Wenhan Luo, Wei Liu
论文链接:https://arxiv.org/abs/1812.01880
代码链接:
https://github.com/KaihuaTang/VCTree-Visual-Question-Answering


6、Transfer Learning via Unsupervised Task Discovery for Visual Question Answering(VQA)
作者:Hyeonwoo Noh, Taehoon Kim, Jonghwan Mun, Bohyung Han
论文链接:https://arxiv.org/abs/1810.02358


7、Information Maximizing Visual Question Generation(VQA)
作者:Zhongdao Wang, Liang Zheng, Yali Li, Shengjin Wang
论文链接:https://arxiv.org/abs/1903.11306



 

多任务学习、迁移学习

1、End-to-End Multi-Task Learning with Attention
作者:Shikun Liu, Edward Johns, Andrew J. Davison
论文链接:https://arxiv.org/abs/1803.10704


2、Deep Transfer Learning for Multiple Class Novelty Detection
作者:Pramuditha Perera, Vishal M. Patel
论文链接:https://arxiv.org/abs/1903.02196



 

自动驾驶

1、Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving(自动驾驶)
作者:Yan Wang, Wei-Lun Chao, Divyansh Garg, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger
论文链接:https://arxiv.org/abs/1812.07179
项目链接:https://mileyan.github.io/pseudo_lidar/
代码链接:https://github.com/mileyan/pseudo_lidar


2、ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
作者:Xibin Song, Peng Wang, Dingfu Zhou, Rui Zhu, Chenye Guan, Yuchao Dai, Hao Su, Hongdong Li, Ruigang Yang
论文链接:https://arxiv.org/abs/1811.12222
简要:The first large-scale database suitable for 3D car instance understanding, ApolloCar3D, collected by Baidu. The dataset contains 5,277 driving images and over 60K car instances, where each car is fitted with an industry-grade 3D CAD model with absolute model size and semantically labelled keypoints.


3、Group-wise Correlation Stereo Network
作者:Xiaoyang Guo, Kai Yang, Wukui Yang, Xiaogang Wang, Hongsheng Li
论文链接:https://arxiv.org/abs/1903.04025


4、Stereo R-CNN based 3D Object Detection for Autonomous Driving
作者:Peiliang Li, Xiaozhi Chen, Shaojie Shen
论文链接:https://arxiv.org/abs/1902.09738


5、Deep Rigid Instance Scene Flow
作者:Wei-Chiu Ma 、Shenlong Wang 、Rui Hu、Yuwen Xiong、 Raquel Urtasun
论文链接:
https://people.csail.mit.edu/weichium/papers/cvpr19-dsisf/paper.pdf
论文摘要:在本文中,我们解决了自动驾驶环境下的场景流量估计问题。 我们利用深度学习技术以及强大的先验,因为在我们的应用领域中,场景的运动可以由机器人的运动和场景中的演员的3D运动来组成。


6、An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM
作者:Patrick Geneva, James Maley, Guoquan Huang
论文链接:https://arxiv.org/abs/1903.08636


7、LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
作者:Gregory P. Meyer, Ankit Laddha, Eric Kee, Carlos Vallespi-Gonzalez, Carl K. Wellington
论文链接:https://arxiv.org/abs/1903.08701


8、.GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
作者:Buyu Li, Wanli Ouyang, Lu Sheng, Xingyu Zeng, Xiaogang Wang
论文链接:https://arxiv.org/abs/1903.10955


 

人群计数

1、Learning from Synthetic Data for Crowd Counting in the Wild
作者:Qi Wang, Junyu Gao, Wei Lin, Yuan Yuan
论文链接:https://arxiv.org/abs/1903.03303


2、Point in, Box out: Beyond Counting Persons in Crowds
作者:待更新
论文链接:https://github.com/xiaofanglegoc/xiaofanglegoc.github.io/blob/master/publications/cvpr2019.pdf



 

数据集

1、COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis
作者:Yansong Tang, Dajun Ding, Yongming Rao, Yu Zheng, Danyang Zhang, Lili Zhao, Jiwen Lu, Jie Zhou
论文链接:https://arxiv.org/abs/1903.02874
项目链接:https://coin-dataset.github.io/
代码链接:https://github.com/coin-dataset/code
 

2、RAVEN: A Dataset for Relational and Analogical Visual rEasoNing
作者:Yansong Tang, Dajun Ding, Yongming Rao, Yu Zheng, Danyang Zhang, Lili Zhao, Jiwen Lu, Jie Zhou
论文链接:https://arxiv.org/abs/1903.02741
项目链接:https://wellyzhang.github.io/project/raven.html


3、SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images(金山云大规模X光违禁品安检数据集)
作者:Caijing Miao, Lingxi Xie, Fang Wan, Chi Su, Hongye Liu, Jianbin Jiao, Qixiang Ye
论文链接:https://arxiv.org/abs/1901.00303
论文简要:本文针对X光安检数据集,提出了类别平衡的分层细化模型处置数据集存在的成绩。


4、A Cross-Season Correspondence Dataset for Robust Semantic Segmentation
作者:Måns Larsson, Erik Stenborg, Lars Hammarstrand, Torsten Sattler, Mark Pollefeys, Fredrik Kahl
论文链接:https://arxiv.org/abs/1903.06916


5、A Cross-Season Correspondence Dataset for Robust Semantic Segmentation
作者:Måns Larsson, Erik Stenborg, Lars Hammarstrand, Torsten Sattler, Mark Pollefeys, Fredrik Kahl
论文链接:https://arxiv.org/abs/1903.06916


 

行人重识别

1、Dissecting Person Re-identification from the Viewpoint of Viewpoint
作者:Xiaoxiao Sun, Liang Zheng
论文链接:https://arxiv.org/abs/1812.02162
源码链接:https://github.com/sxzrt/Dissecting-Person-Re-ID-from-the-Viewpoint-of-Viewpoint


2、Unsupervised Person Re-identification by Soft Multilabel Learning(行人再识别,Oral)
作者:Hong-Xing Yu, Wei-Shi Zheng, Ancong Wu, Xiaowei Guo, Shaogang Gong, Jian-Huang Lai
论文链接:https://arxiv.org/abs/1903.06325
源码链接:https://github.com/KovenYu/MAR


 

其他

2、Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
作者:De-An Huang, Suraj Nair, Danfei Xu, Yuke Zhu, Animesh Garg, Li Fei-Fei, Silvio Savarese, Juan Carlos Niebles
论文链接:https://arxiv.org/abs/1807.03480
 

3、Variational Bayesian Dropout
作者:Yuhang Liu, Wenyong Dong, Lei Zhang, Dong Gong, Qinfeng Shi
论文链接:https://arxiv.org/abs/1811.07533


4、LiFF: Light Field Features in Scale and Depth
作者:Donald G. Dansereau, Bernd Girod, Gordon Wetzstein
论文链接:https://arxiv.org/abs/1901.03916


5、Classification-Reconstruction Learning for Open-Set Recognition
作者:Ryota Yoshihashi, Wen Shao, Rei Kawakami, Shaodi You, Makoto Iida, Takeshi Naemura
论文链接:https://arxiv.org/abs/1812.04246


6、Weakly Supervised Deep Image Hashing through Tag Embeddings
作者:Vijetha Gattupalli, Yaoxin Zhuo, Baoxin Li
论文链接:https://arxiv.org/abs/1806.05804


7、InverseRenderNet: Learning single image inverse rendering
作者:Ye Yu, William A. P. Smith
论文链接:https://arxiv.org/abs/1811.12328


8、End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization
作者:Yeonwoo Jeong, Yoonsuing Kim, Hyun Oh Song
论文链接:https://arxiv.org/abs/1902.10990
代码链接:https://github.com/maestrojeong/Deep-Hash-Table-CVPR19


9、Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
作者:Yawei Luo, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang
论文链接:https://arxiv.org/abs/1809.09478


10、Efficient Parameter-free Clustering Using First Neighbor Relations
作者:M. Saquib Sarfraz, Vivek Sharma, Rainer Stiefelhagen
论文链接:https://arxiv.org/abs/1902.11266
Reading Notes:FINCH, a new clustering algorithm, absolutily no hyperparameters , no need to specify no. of clusters. Scalable(Memory O(N)), very fast (ON(logN)) clusters ~8 million samples in 18 minutes on standard CPU.



11、3D Hand Shape and Pose from Images in the Wild
作者:Adnane Boukhayma, Rodrigo de Bem, Philip H.S. Torr
论文链接:https://arxiv.org/pdf/1902.03451.pdf
Github链接:https://github.com/boukhayma/3dhand


12、Monocular Total Capture: Posing Face, Body, and Hands in the Wild
作者:Donglai Xiang, Hanbyul Joo, Yaser Sheikh
论文链接:https://arxiv.org/pdf/1812.01598.pdf
项目链接:http://domedb.perception.cs.cmu.edu/monototalcapture.html


13、Learning to Synthesize Motion Blur(Oral Presentation)
作者:Tim Brooks, Jonathan T. Barron
论文链接:https://arxiv.org/abs/1811.11745
project链接:http://timothybrooks.com/tech/motion-blur/
Reading note:Frame interpolation techniques can be used to train a network to directly synthesize linear motion blur.


14、A General and Adaptive Robust Loss Function(Oral Presentation)
作者:Jonathan T. Barron
论文链接:https://arxiv.org/abs/1701.03077
Reading Note:A single robust loss function is a superset of many other common robust loss functions, and allows training to automatically adapt the robustness of its own loss.


15、Context-Aware Visual Compatibility Prediction
作者:Guillem Cucurull, Perouz Taslakian, David Vazquez
论文链接:https://arxiv.org/abs/1902.03646
Reading Note:It proposes a graph convolutional neural network that predicts compatibility between two items based on their visual features, as well as their context
 

16、A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations
作者:Saeid Asgari Taghanaki Kumar Abhishek1 Shekoofeh Azizi and Ghassan Hamarneh
论文链接:http://cs.sfu.ca/~hamarneh/ecopy/cvpr2019.pdf
Arxiv链接:https://arxiv.org/abs/1903.01015


17、Self-supervised Learning of Dense Shape Correspondence(Oral Presentation)
作者:Oshri Halimi, Or Litany, Emanuele Rodolà, Alex Bronstein, Ron Kimmel
论文链接:https://arxiv.org/abs/1812.02415



18、Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation
作者:Matteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
论文链接:https://arxiv.org/abs/1811.10666


19、Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
作者:Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
论文链接:https://arxiv.org/abs/1811.10652
代码链接:https://github.com/aimagelab/show-control-and-tell
 

20、Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing
作者:Xihui Liu, Zihao Wang, Jing Shao, Xiaogang Wang, Hongsheng Li
论文链接:https://arxiv.org/abs/1903.00839
 

21、Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion
作者:Ryutaro Tanno, Ardavan Saeedi, Swami Sankaranarayanan, Daniel C. Alexander, Nathan Silberman
论文链接:https://arxiv.org/abs/1902.03680
 

22、Variational Autoencoders Pursue PCA Directions (by Accident)
作者:Michal Rolinek, Dominik Zietlow, Georg Martius
论文链接:https://arxiv.org/abs/1812.06775

 

23、The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation(oral)
作者:Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira
论文链接:https://arxiv.org/abs/1903.01602
Github:https://github.com/chihyaoma/regretful-agent


24、Understanding and Visualizing Deep Visual Saliency Models
作者:Sen He, Hamed R. Tavakoli, Ali Borji, Yang Mi, Nicolas Pugeault
论文链接:https://arxiv.org/abs/1903.02501
 



25、Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation(非最终版)
作者:Zhi Tian, Chunhua Shen, Tong He, Youliang Yanl
论文链接:https://arxiv.org/abs/1903.02120


26、Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search(oral)
作者:Abhimanyu Dubey, Laurens van der Maaten, Zeki Yalniz, Yixuan Li, Dhruv Mahajan
论文链接:https://arxiv.org/abs/1903.01612


27、Unsupervised Domain-Specific Deblurring via Disentangled Representations
作者:Boyu Lu, Jun-Cheng Chen, Rama Chellappa
论文链接:https://arxiv.org/abs/1903.01594


28、Selective Sensor Fusion for Neural Visual-Inertial Odometry
作者:Changhao Chen, Stefano Rosa, Yishu MiaoChris Xiaoxuan Lu, Wei Wu, Andrew Markham, Niki Trigoni
论文链接:https://arxiv.org/abs/1903.01534


29、.Learning Deep Compositional Grammatical Architectures for Visual Recognition
作者:Xilai Li, Tianfu Wu, Xi Song
论文链接:https://arxiv.org/abs/1711.05847
代码链接:https://github.com/xilaili/AOGNet


30、Taking a Deeper Look at the Inverse Compositional Algorithm(oral)
作者:Zhaoyang Lv, Frank Dellaert, James M. Rehg, Andreas Geiger
论文链接:https://arxiv.org/pdf/1812.06861.pdf
代码链接:https://github.com/lvzhaoyang/DeeperInverseCompositionalAlgorithm
 

31、Learning Transformation Synchronization
作者:Xiangru Huang, Zhenxiao Liang, Xiaowei Zhou, Yao Xie, Leonidas Guibas, and Qixing Huang
论文链接:https://arxiv.org/pdf/1901.09458.pdf
代码链接: https://github.com/xiangruhuang/Learning2Sync
 

32、SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction
作者:Pu Zhang, Wanli Ouyang, Pengfei Zhang, Jianru Xue, Nanning Zheng
论文链接:https://arxiv.org/abs/1903.02793

 

33、Handwriting Recognition in Low-resource Scripts using Adversarial Learning
作者:Ayan Kumar Bhunia, Abhirup Das, Ankan Kumar Bhunia, Perla Sai Raj Kishore, Partha Pratim Roy
论文链接:https://arxiv.org/pdf/1811.01396.pdf


34、ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation(Facebook mobile vision team)
作者:Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia, Peter Vajda, Matt Uyttendaele, Niraj K. Jha
论文链接:https://arxiv.org/abs/1812.08934


34、FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search(Facebook mobile vision team)
作者:Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, Kurt Keutzer
论文链接:https://arxiv.org/abs/1812.03443
 

35、PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding
作者:Kaichun Mo, Shilin Zhu, Angel X. Chang, Li Yi, Subarna Tripathi, Leonidas J. Guibas, Hao Su
项目链接:https://cs.stanford.edu/~kaichun/partnet/
论文链接:https://arxiv.org/abs/1812.02713
简要:A 3D object database with fine-grained and hierarchical part annotation. To assist segmentation and affordance research.


36、Adversarial Defense by Stratified Convolutional Sparse Coding
作者:Bo Sun, Nian-hsuan Tsai, Fangchen Liu, Ronald Yu, Hao Su
论文链接:https://arxiv.org/abs/1812.00037
简要:An attack-agnostic defense mechanism for neural networks.
 

37、Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval
作者:Anjan Dutta, Zeynep Akata
论文链接:https://arxiv.org/abs/1903.03372
 

39、Ranked List Loss for Deep Metric Learning
作者:Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Romain Garnier, Neil M. Robertson
论文链接:https://arxiv.org/abs/1903.03238


40、Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation
作者:Adrian V. Dalca, John Guttag, Mert R. Sabuncu
论文链接:https://arxiv.org/abs/1903.03148
 

41、Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation
作者:Andrea Pilzer, Stéphane Lathuilière, Nicu Sebe, Elisa Ricci
论文链接:https://arxiv.org/pdf/1903.04202.pdf


42、Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation(领域自适应)
作者:Chen-Yu Lee, Tanmay Batra, Mohammad Haris Baig, Daniel Ulbricht
论文链接:https://arxiv.org/abs/1903.04064


43、Deep Robust Subjective Visual Property Prediction in Crowdsourcing
作者:Qianqian Xu, Zhiyong Yang, Yangbangyan Jiang, Xiaochun Cao, Qingming Huang, Yuan Yao
论文链接:https://arxiv.org/abs/1903.03956


44、Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
作者:Xiaogang Wang, Bin Zhou, Yahao Shi, Xiaowu Chen, Qinping Zhao, Kai Xu
论文链接:https://arxiv.org/abs/1903.03911


45、Fast Single Image Reflection Suppression via Convex Optimization
作者:Yang Yang, Wenye Ma, Yin Zheng, Jian-Feng Cai, Weiyu Xu
论文链接:https://arxiv.org/abs/1903.03889


46、Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks
作者:Kuan Fang, Alexander Toshev, Li Fei-Fei, Silvio Savarese
论文链接:https://arxiv.org/abs/1903.03878


47、SSN: Learning Sparse Switchable Normalization via SparsestMax
作者:Wenqi Shao, Tianjian Meng, Jingyu Li, Ruimao Zhang, Yudian Li, Xiaogang Wang, Ping Luo
论文链接:https://arxiv.org/abs/1903.03793



48、Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
作者:Xin Li, Yiming Zhou, Zheng Pan, Jiashi Feng
论文链接:https://arxiv.org/abs/1903.03777


49、Dense Classification and Implanting for Few-Shot Learning
作者:Yann Lifchitz, Yannis Avrithis, Sylvaine Picard, Andrei Bursuc
论文链接:https://arxiv.org/abs/1903.05050


50、A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images(oral)
作者:Jiapeng Tang, Xiaoguang Han, Junyi Pan, Kui Jia, Xin Tong
论文链接:https://arxiv.org/abs/1903.04704


51、Real-time self-adaptive deep stereo(oral)
作者:Alessio Tonioni, Fabio Tosi, Matteo Poggi, Stefano Mattoccia, Luigi Di Stefano
论文链接:https://arxiv.org/abs/1903.04704
源码链接:https://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo


52、Scan2CAD: Learning CAD Model Alignment in RGB-D Scans(oral)
作者:Armen Avetisyan, Manuel Dahnert, Angela Dai, Manolis Savva, Angel X. Chang, Matthias Nießner
论文链接:https://arxiv.org/abs/1811.11187
源码链接:https://github.com/skanti/Scan2CAD
简要:Present Scan2CAD, a novel data-driven method that learns to align 3D CAD models from a shape database to 3D scans.


53、HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation
作者:Cheng Sun, Chi-Wei Hsiao, Min Sun, Hwann-Tzong Chen
论文链接:https://arxiv.org/abs/1901.03861
源码链接:https://github.com/sunset1995/HorizonNet


54、A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images(oral)
作者:Jiapeng Tang, Xiaoguang Han, Junyi Pan, Kui Jia, Xin Tong
论文链接:https://arxiv.org/abs/1903.04704


55、Handwriting Recognition in Low-resource Scripts using Adversarial Learning
作者:Ayan Kumar Bhunia, Abhirup Das, Ankan Kumar Bhunia, Perla Sai Raj Kishore, Partha Pratim Roy
论文链接:https://arxiv.org/abs/1811.01396


56、Tangent-Normal Adversarial Regularization for Semi-supervised Learning
作者:Bing Yu, Jingfeng Wu, Jinwen Ma, Zhanxing Zhu
论文链接:https://arxiv.org/abs/1808.06088


57、Bringing Alive Blurred Moments
作者:Kuldeep Purohit, Anshul Shah, A. N. Rajagopalan
论文链接:https://arxiv.org/abs/1804.02913


58、A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem
作者:Ganzhao Yuan, Li Shen, Wei-Shi Zheng
论文链接:https://arxiv.org/abs/1802.09303


59、Hardness-Aware Deep Metric Learning(oral)
作者:Wenzhao Zheng, Zhaodong Chen, Jiwen Lu, Jie Zhou
论文链接:https://arxiv.org/abs/1903.05503
代码链接:https://github.com/wzzheng/HDML(待更新)


60、Depth Coefficients for Depth Completion
作者:Saif Imran, Yunfei Long, Xiaoming Liu, Daniel Morris
论文链接:https://arxiv.org/abs/1903.05421


61、3D Guided Fine-Grained Face Manipulation
作者:Zhenglin Geng, Chen Cao, Sergey Tulyakov
论文链接:https://arxiv.org/abs/1902.08900
简要:Disentangle shape and texture and can continuously manipulate the facial expression.


62、Scene Categorization from Contours: Medial Axis Based Salience Measures
作者:Morteza Rezanejad, Gabriel Downs, John Wilder, Dirk B. Walther, Allan Jepson, Sven Dickinson, Kaleem Siddiqi
论文链接:https://arxiv.org/abs/1811.10524v1


63、ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch(Oral)
作者:Rui Zhu, Shifeng Zhang, Xiaobo Wang, Longyin Wen, Hailin Shi, Liefeng Bo, Tao Mei
论文链接:https://arxiv.org/abs/1810.08425v3
源码链接:https://github.com/KimSoybean/ScratchDet


64、Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
作者:Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon
论文链接:https://arxiv.org/abs/1903.05942


65、Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments
作者:Xueting Li, SIfei Liu, Kihwan Kim, Xiaolong Wang, Ming-Hsuan Yang, Jan Kautz
论文链接:https://arxiv.org/abs/1903.05690


66、Bringing Blurry Alive at High Frame-Rate with an Event Camera
作者:Liyuan Pan, Richard Hartley, Cedric Scheerlinck, Miaomiao Liu, Xin Yu, Yuchao Dai
论文链接:https://arxiv.org/abs/1903.06531


67、MFAS: Multimodal Fusion Architecture Search
作者:Juan-Manuel Pérez-Rúa, Valentin Vielzeuf, Stéphane Pateux, Moez Baccouche, Frédéric Jurie
论文链接:https://arxiv.org/abs/1903.06496


68、SimulCap : Single-View Human Performance Capture with Cloth Simulation
作者:Tao Yu, Zerong Zheng, Yuan Zhong, Jianhui Zhao, Qionghai Dai, Gerard Pons-Moll, Yebin Liu
论文链接:https://arxiv.org/abs/1903.06323



69、Learning to Reconstruct People in Clothing from a Single RGB Camera
作者:Thiemo Alldieck, Marcus Magnor, Bharat Lal Bhatnagar, Christian Theobalt, Gerard Pons-Moll
论文链接:https://arxiv.org/abs/1903.05885


70、Pluralistic Image Completion
作者:Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai
论文链接:https://arxiv.org/abs/1903.04227
源码链接:https://github.com/lyndonzheng/Pluralistic-Inpainting
项目链接:http://www.chuanxiaz.com/publication/pluralistic/


71、Snapshot Distillation: Teacher-Student Optimization in One Generation(金山云)
作者:Chenglin Yang, Lingxi Xie, Chi Su, Alan L. Yuille
论文链接:https://arxiv.org/abs/1812.00123v1
论文简要:本文引见了第一种可以在训练单个模型的条件下完成教员-先生优化的办法——快照蒸馏(Snapshot Distillation),在不引入过多的计算耗费状况下,完成了继续的功能提升。


72、Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning(金山云)
作者:Chen Wei, Lingxi Xie, Xutong Ren, Yingda Xia, Chi Su, Jiaying Liu, Qi Tian, Alan L. Yuille
论文链接:https://arxiv.org/abs/1812.00329
论文简要:本文提出一种适用于恣意网格尺寸与维度的“拼图”成绩的新办法,同时提出了一个根本且具有普遍意义的准绳,即在无监视场景中较弱的信息更容易被学习,且具有更好的可迁移性。


73、Learning Correspondence from the Cycle-Consistency of Time
作者:Xiaolong Wang, Allan Jabri, Alexei A. Efros
论文链接:https://arxiv.org/abs/1903.07593
项目链接:https://ajabri.github.io/timecycle/


74、Understanding the Limitations of CNN-based Absolute Camera Pose Regression
作者:Torsten Sattler, Qunjie Zhou, Marc Pollefeys, Laura Leal-Taixe
论文链接:https://arxiv.org/abs/1903.07504


75、Semantic Image Synthesis with Spatially-Adaptive Normalization(Oral, 英伟达)
作者:Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu
论文链接:https://arxiv.org/abs/1903.07291


76、Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection
作者:Jia-Xing Zhong, Nannan Li, Weijie Kong, Shan Liu, Thomas H. Li, Ge Li
论文链接:https://arxiv.org/abs/1903.07256


77、QATM: Quality-Aware Template Matching For Deep Learning
作者:Jiaxin Cheng, Yue Wu, Wael Abd-Almageed, Premkumar Natarajan
论文链接:https://arxiv.org/abs/1903.07254


78、AdaGraph: Unifying Predictive and ContinuousDomain Adaptation through Graphs(Oral)
作者:Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci
论文链接:https://arxiv.org/abs/1903.07062


79、Unsupervised Part-Based Disentangling of Object Shape and Appearance(Oral)
作者:Dominik Lorenz, Leonard Bereska, Timo Milbich, Björn Ommer
论文链接:https://arxiv.org/abs/1903.06946


80、Fast Interactive Object Annotation with Curve-GCN
作者:Huan Ling, Jun Gao, Amlan Kar, Wenzheng Chen, Sanja Fidler
论文链接:https://arxiv.org/abs/1903.06874


81、Domain Generalization by Solving Jigsaw Puzzles
作者:Fabio Maria Carlucci, Antonio D'Innocente, Silvia Bucci, Barbara Caputo, Tatiana Tommasi
论文链接:https://arxiv.org/abs/1903.06864


82、Learning Correspondence from the Cycle-Consistency of Time
作者:Xiaolong Wang, Allan Jabri, Alexei A. Efros
论文链接:https://arxiv.org/abs/1903.07593
项目链接:https://ajabri.github.io/timecycle/


83、Understanding the Limitations of CNN-based Absolute Camera Pose Regression
作者:Torsten Sattler, Qunjie Zhou, Marc Pollefeys, Laura Leal-Taixe
论文链接:https://arxiv.org/abs/1903.07504


84、Semantic Image Synthesis with Spatially-Adaptive Normalization(Oral, 英伟达)
作者:Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu
论文链接:https://arxiv.org/abs/1903.07291


85、Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection
作者:Jia-Xing Zhong, Nannan Li, Weijie Kong, Shan Liu, Thomas H. Li, Ge Li
论文链接:https://arxiv.org/abs/1903.07256


86、QATM: Quality-Aware Template Matching For Deep Learning
作者:Jiaxin Cheng, Yue Wu, Wael Abd-Almageed, Premkumar Natarajan
论文链接:https://arxiv.org/abs/1903.07254


87、AdaGraph: Unifying Predictive and ContinuousDomain Adaptation through Graphs(Oral)
作者:Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci
论文链接:https://arxiv.org/abs/1903.07062


88、Unsupervised Part-Based Disentangling of Object Shape and Appearance(Oral)
作者:Dominik Lorenz, Leonard Bereska, Timo Milbich, Björn Ommer
论文链接:https://arxiv.org/abs/1903.06946


89、Fast Interactive Object Annotation with Curve-GCN
作者:Huan Ling, Jun Gao, Amlan Kar, Wenzheng Chen, Sanja Fidler
论文链接:https://arxiv.org/abs/1903.06874


90、Domain Generalization by Solving Jigsaw Puzzles
作者:Fabio Maria Carlucci, Antonio D'Innocente, Silvia Bucci, Barbara Caputo, Tatiana Tommasi
论文链接:https://arxiv.org/abs/1903.06864


91、Neural Sequential Phrase Grounding (SeqGROUND)
作者:Pelin Dogan, Leonid Sigal, Markus Gross
论文链接:https://arxiv.org/abs/1903.07669


92、Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
作者:Kun Yi, Jianxin Wu
论文链接:https://arxiv.org/abs/1903.07788


93、MagicVO: End-to-End Monocular Visual Odometry through Deep Bi-directional Recurrent Convolutional Neural Network(单目视觉测距)
作者:Jian Jiao, Jichao Jiao, Yaokai Mo, Weilun Liu, Zhongliang Deng
论文链接:https://arxiv.org/abs/1811.10964
论文摘要:本文提出了一种解决单眼视觉测距问题的新框架,称为MagicVO。 基于卷积神经网络(CNN)和双向LSTM(Bi-LSTM),MagicVO在摄像机的每个位置输出6-DoF绝对标度姿势,并以一系列连续单目图像作为输入。


94、Hierarchical Discrete Distribution Decomposition for Match Density Estimation(立体匹配)
作者:Zhichao Yin, Trevor Darrell, Fisher Yu
论文链接:https://arxiv.org/abs/1812.06264
论文简要:在本文中,我们提出了分层离散分布分解,称为HD3,以学习概率点和区域匹配。它不仅可以模拟匹配不确定性,还可以模拟区域传播。


95、Learning Linear Transformations for Fast Arbitrary Style Transfer
作者:Xueting Li, Sifei Liu, Jan Kautz, Ming-Hsuan Yang
论文链接:https://arxiv.org/pdf/1808.04537v1.pdf


96、Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses(Oral)
作者:Jérôme Rony, Luiz G. Hafemann, Luiz S. Oliveira, Ismail Ben Ayed, Robert Sabourin, Eric Granger
论文链接:https://arxiv.org/abs/1811.09600
代码链接:https://github.com/jeromerony/fast_adversarial


97、Graphical Contrastive Losses for Scene Graph Generation
作者:Ji Zhang, Kevin J. Shih, Ahmed Elgammal, Andrew Tao, Bryan Catanzaro
论文链接:https://arxiv.org/abs/1903.02728
代码链接:https://github.com/NVIDIA/ContrastiveLosses4VRD


98、Pay attention! - Robustifying a Deep Visuomotor Policy through Task-Focused Attention
作者:Pooya Abolghasemi, Amir Mazaheri, Mubarak Shah, Ladislau Bölöni
论文链接:https://arxiv.org/abs/1809.10093


99、Cross-task weakly supervised learning from instructional videos
作者:Dimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis, David Fouhey, Ivan Laptev, Josef Sivic
论文链接:https://arxiv.org/abs/1903.08225


100、Explainable and Explicit Visual Reasoning over Scene Graphs
作者:Jiaxin Shi, Hanwang Zhang, Juanzi Li
论文链接:https://arxiv.org/abs/1812.01855
代码链接:https://github.com/shijx12/XNM-Net


101、Single Image Deraining: A Comprehensive Benchmark Analysis
作者:Siyuan Li, Iago Breno Araujo, Wenqi Ren, Zhangyang Wang, Eric K. Tokuda, Roberto Hirata Junior, Roberto Cesar-Junior, Jiawan Zhang, Xiaojie Guo, Xiaochun Cao
论文链接:https://arxiv.org/abs/1903.08558
代码链接:https://github.com/lsy17096535/Single-Image-Deraining


102、Im2Pencil: Controllable Pencil Illustration from Photographs
作者:Yijun Li, Chen Fang, Aaron Hertzmann, Eli Shechtman, Ming-Hsuan Yang
论文链接:https://arxiv.org/abs/1903.08682


103、Towards Robust Curve Text Detection with Conditional Spatial Expansion
作者:Zichuan Liu, Guosheng Lin, Sheng Yang, Fayao Liu, Weisi Lin, Wang Ling Goh
论文链接:https://arxiv.org/abs/1903.08836


104、DSFD: Dual Shot Face Detector(腾讯优图)
作者:Jian Li, Yabiao Wang, Changan Wang, Ying Tai
论文链接:https://arxiv.org/abs/1810.10220
代码链接:https://github.com/TencentYoutuResearch/FaceDetection-DSFD
微信公众号介绍链接:https://mp.weixin.qq.com/s/0rTCeHumVSv07hMCaCd7EA


105、Attention-aware Multi-stroke Style Transfer
作者:Yuan Yao, Jianqiang Ren, Xuansong Xie, Weidong Liu, Yong-Jin Liu, Jun Wang
论文链接:https://arxiv.org/abs/1901.05127
项目链接:https://sites.google.com/view/yuanyao/attention-aware-multi-stroke-style-transfer


106、Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach
作者:Amir Atapour-Abarghouei, Toby P. Breckon
论文链接:https://arxiv.org/abs/1903.10764


107、Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection
作者:Zhiwei Liu, Xiangyu Zhu, Guosheng Hu, Haiyun Guo, Ming Tang, Zhen Lei, Neil M. Robertson, Jinqiao Wang
论文链接:https://arxiv.org/abs/1903.10661


108、Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
作者:Xi Shen, Alexei A. Efros, Mathieu Aubry
论文链接:https://arxiv.org/abs/1903.02678


109、DeeperLab: Single-Shot Image Parser
作者:Tien-Ju Yang, Maxwell D. Collins, Yukun Zhu, Jyh-Jing Hwang, Ting Liu, Xiao Zhang, Vivienne Sze, George Papandreou, Liang-Chieh Chen
论文链接:https://arxiv.org/abs/1902.05093
代码链接:https://github.com/tensorflow/models/tree/master/research/deeplab/evaluation
项目链接:http://deeperlab.mit.edu/


110、Im2Pencil: Controllable Pencil Illustration from Photographs(Adobe与谷歌云等)
作者:Yijun Li,Chen Fang, Aaron Hertzmann, Eli Shechtman, Ming-Hsuan Yang
论文链接:https://drive.google.com/file/d/1sl5IBD36bMWAvKH7Uz7An0mcrIOmlopv/view
代码链接:https://github.com/Yijunmaverick/Im2Pencil


111、Unsupervised Image Captioning
作者:Yang Feng, Lin Ma, Wei Liu, Jiebo Luo
论文链接:https://arxiv.org/abs/1811.10787
代码链接:https://github.com/fengyang0317/unsupervised_captioning


112、An End-to-End Network for Generating Social Relationship Graphs
作者:Arushi Goel, Keng Teck Ma, Cheston Tan
论文链接:https://arxiv.org/abs/1903.09784


113、f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
作者:Yongqin Xian, Saurabh Sharma, Bernt Schiele, Zeynep Akata
论文链接:https://arxiv.org/abs/1903.10132


114、Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation
作者:Jaime Spencer, Richard Bowden, Simon Hadfield
论文链接:https://arxiv.org/abs/1903.10427


115、Learning Attraction Field Reprensentation for Robust Line Segment Detection
作者:Nan Xue, Song Bai, Fudong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang
论文链接:https://arxiv.org/abs/1812.02122
代码链接:https://github.com/cherubicXN/afm_cvpr2019


116、Feature Denoising for Improving Adversarial Robustness
作者:Cihang Xie, Yuxin Wu, Laurens van der Maaten, Alan Yuille, Kaiming He
论文链接:https://arxiv.org/abs/1812.03411v2
代码链接:https://github.com/facebookresearch/ImageNet-Adversarial-Training


117、DynTypo: Example-based Dynamic Text Effects Transfer
作者:Yifang Men Zhouhui Lian Yingmin Tang Jianguo Xiao
项目链接:https://menyifang.github.io/projects/DynTypo/DynTypo.html


118、Progressive Image Deraining Networks: A Better and Simpler Baseline
作者:Dongwei Ren, Wangmeng Zuo, Qinghua Hu, Pengfei Zhu, Deyu Meng
论文链接:https://arxiv.org/abs/1901.09221
代码链接:https://github.com/csdwren/PReNet


119、Transferable Interactiveness Prior for Human-Object Interaction Detection
作者:Yong-Lu Li, Siyuan Zhou, Xijie Huang, Liang Xu, Ze Ma, Hao-Shu Fang, Yan-Feng Wang, Cewu Lu
论文链接:https://arxiv.org/abs/1811.08264
代码链接:https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network


120、Speed Invariant Time Surface for Learning to Detect Corner Points with Event-Based Cameras
作者:Jacques Manderscheid, Amos Sironi, Nicolas Bourdis, Davide Migliore, Vincent Lepetit
论文链接:https://arxiv.org/abs/1903.11332


121、Self-Supervised Learning via Conditional Motion Propagation
作者:Xiaohang Zhan, Xingang Pan, Ziwei Liu, Dahua Lin, Chen Change Loy
论文链接:https://arxiv.org/abs/1903.11412


122、Privacy Protection in Street-View Panoramas using Depth and Multi-View Imagery
作者:Ries Uittenbogaard, Clint Sebastian, Julien Vijverberg, Bas Boom, Dariu M. Gavrila, Peter H.N. de With
论文链接:https://arxiv.org/abs/1903.11532

Copyright © 2010-2022 ngui.cc 版权所有 |关于我们| 联系方式| 豫B2-20100000