CVPR2019| 南开大学、Facebook等13篇CVPR论文及源码推荐（显著性检测/实例分割/人脸识别/视频动作识别等）

2019 年 5 月 23 日 极市平台

加入极市专业CV交流群，与6000+来自腾讯，华为，百度，北大，清华，中科院等名企名校视觉开发者互动交流！更有机会与李开复老师等大牛群内互动！

同时提供每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流。点击文末“阅读原文”立刻申请入群~

前段时间，计算机视觉顶会CVPR 2019 公布了接收结果，极市也对此做了相关报道：1300篇！CVPR2019接收结果公布，你中了吗？。目前官方已公布了接收论文列表，极市已汇总目前公开的所有论文链接及code（目前已更新653篇），今日更新论文如下：

CVPR2019 全部论文汇总：

https://github.com/extreme-assistant/cvpr2019

CVPR2019 论文解读

http://bbs.cvmart.net/topics/287/cvpr2019

1.Disentangling Adversarial Robustness and Generalization
作者：David Stutz, Matthias Hein, Bernt Schiele
论文链接：https://arxiv.org/abs/1812.00740

2.S4Net: Single Stage Salient-Instance Segmentation（南开大学）
作者：Ruochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang, Shi-Min Hu
论文链接：

http://mftp.mmcheng.net/Papers/19cvprS4Net.pdf
源码链接：https://github.com/RuochenFan/S4Net
项目链接：https://mmcheng.net/s4net/

3.An Iterative and Cooperative Top-down and Bottom-up Inference Network for Salient Object Detection(南开大学)
作者：Wenguan Wang, Jianbing Shen, Ming-Ming Cheng, Ling Shao
论文链接：

http://mftp.mmcheng.net/Papers/19cvprIterativeSOD.pdf

4.Deep Face Recognition via Exclusive Regularization(南开大学，人脸识别)
作者：Kai Zhao, Jingyi Xu, Ming-Ming Cheng
论文链接：

http://mftp.mmcheng.net/Papers/19cvprRegularFace.pdf

5.DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition(Facebook)
作者：Zheng Shou, Xudong Lin, Yannis Kalantidis, Laura Sevilla-Lara, Marcus Rohrbach, Shih-Fu Chang, Zhicheng Yan
论文链接：https://research.fb.com/wp-content/uploads/2019/05/DMC-Net-Generating-Discriminative-Motion-Cues-for-Fast-Compressed-Video-Action-Recognition.pdf

6.Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition(Facebook)
作者：Zizhao Zhang, Adriana Romero, Matthew J. Muckley, Pascal Vincent, Lin Yang, Michal Drozdzal
论文链接：https://research.fb.com/wp-content/uploads/2019/05/Reducing-Uncertainty-in-Undersampled-MRI-Reconstruction-with-Active-Acquisition.pdf

7.Kernel Transformer Networks for Compact Spherical Convolution(Facebook)
作者：Yu-Chuan Su, Kristen Grauman
论文链接：https://research.fb.com/wp-content/uploads/2019/05/Kernel-Transformer-Networks-for-Compact-Spherical-Convolution.pdf

8.3D human pose estimation in video with temporal convolutions and semi-supervised training(Facebook)
作者：Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli
论文链接：https://research.fb.com/wp-content/uploads/2019/05/3D-human-pose-estimation-in-video-with-temporal-convolutions-and-semi-supervised-training.pdf

9.Graph-Based Global Reasoning Networks(Facebook)
作者：Yunpeng Chen, Marcus Rohrbach, Zhicheng Yan, Shuicheng Yan, Jiashi Feng, Yannis Kalantidis
论文链接：https://research.fb.com/wp-content/uploads/2019/05/Graph-Based-Global-Reasoning-Networks.pdf

10.Learning 3D Human Dynamics from Video
作者：Angjoo Kanazawa, Jason Y. Zhang, Panna Felsen, Jitendra Malik
论文链接：https://arxiv.org/abs/1812.01601
项目链接：

https://akanazawa.github.io/human_dynamics/
源码链接：

https://github.com/akanazawa/human_dynamics

11.Multi-Level Context Ultra-Aggregation for Stereo Matching（南开大学）
作者：Guang-Yu Nie, Ming-Ming Cheng, Yun Liu, Zhengfa Liang
论文链接：

http://dpfan.net/wp-content/uploads/09CVPR_StereoMatching_CameraReady_V12_final.pdf
项目链接：http://mmcheng.net/zh/mcua/

12.Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection（南开大学）
作者：Jiaxing Zhao*, Yang Cao*, Deng-Ping Fan*, Xuan-Yi Li, Le Zhang, Ming-Ming Cheng. (* co-first author)
论文链接：http://dpfan.net/wp-content/uploads/19cvprRrbdSOD-cameraReady.pdf
项目链接：https://mmcheng.net/rgbdsalpyr/

13.Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
作者：Hsueh-Ying Lai, Yi-Hsuan Tsai, Wei-Chen Chiu
论文链接：https://arxiv.org/abs/1905.09265
源码链接：