CVPR2019| 04-30更新23篇论文及代码合集（3篇oral，含3D目标检测/语义分割/动作识别等）

2019 年 4 月 30 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532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.Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation
作者：Fengda Zhu, Linchao Zhu, Yi Yang
论文链接：https://arxiv.org/abs/1904.03895

2.Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
作者：Hao Zhu, Xinxin Zuo, Sen Wang, Xun Cao, Ruigang Yang
论文链接：https://arxiv.org/abs/1904.10506v1
源码链接：https://github.com/zhuhao-nju/hmd.git

3.Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration(Oral)
作者：Yang He, Ping Liu, Ziwei Wang, Zhilan Hu, Yi Yang
论文链接：https://arxiv.org/abs/1811.00250
源码链接：https://github.com/he-y/filter-pruning-geometric-median

4.Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
作者：Shiyi Lan, Ruichi Yu, Gang Yu, Larry S. Davis
论文链接：https://arxiv.org/abs/1811.07782

5.Progressive Pose Attention Transfer for Person Image Generation
作者：Zhen Zhu, Tengteng Huang, Baoguang Shi, Miao Yu, Bofei Wang, Xiang Bai
论文链接：https://arxiv.org/abs/1904.03349
源码链接：https://github.com/tengteng95/Pose-Transfer

6.Universal Domain Adaptation
作者：Kaichao You, Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael . Jordan
论文链接：

https://youkaichao.github.io/files/cvpr2019/1628.pdf
源码链接：https://github.com/thuml/Universal-Domain-Adaptation

7.STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
作者：Ming Liu, Yukang Ding, Min Xia, Xiao Liu, Errui Ding, Wangmeng Zuo, Shilei Wen
论文链接：https://arxiv.org/abs/1904.09709
源码链接：https://github.com/csmliu/STGAN

9.D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
作者：Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler
论文链接：https://dsmn.ml/publications/d2-net.html
源码链接：https://github.com/mihaidusmanu/d2-net

10.DeepCaps: Going Deeper with Capsule Networks
作者：Jathushan Rajasegaran, Vinoj Jayasundara, Sandaru Jayasekara, Hirunima Jayasekara, Suranga Seneviratne, Ranga Rodrigo
论文链接：https://arxiv.org/abs/1904.09546
源码链接：https://github.com/brjathu/deepcaps

11.Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
作者：Chunfeng Song, Yan Huang, Wanli Ouyang, Liang Wang
论文链接：https://arxiv.org/abs/1904.11693

12.Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning
作者：Kshitij Dwivedi, Gemma Roig
论文链接：https://arxiv.org/abs/1904.11740
源码链接：https://github.com/kshitijd20/RSA-CVPR19-release

13.Translate-to-Recognize Networks for RGB-D Scene Recognition
作者：Dapeng Du, Limin Wang, Huiling Wang, Kai Zhao, Gangshan Wu
论文链接：https://arxiv.org/abs/1904.12254
源码链接：

https://ownstyledu.github.io/Translate-to-Recognize-Networks/

14.RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion
作者：Muhammad Sarmad, Hyunjoo Jenny Lee, Young Min Kim
论文链接：https://arxiv.org/abs/1904.12304
源码链接：https://github.com/iSarmad/RL-GAN-Net

15.Bidirectional Learning for Domain Adaptation of Semantic Segmentation
作者：Yunsheng Li, Lu Yuan, Nuno Vasconcelos
论文链接：https://arxiv.org/abs/1904.10620
源码链接：https://github.com/liyunsheng13/BDL

16.Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis
作者：Yu Yu, Gang Liu, Jean-Marc Odobez
论文链接：https://arxiv.org/abs/1904.10638

17.Learning the Depths of Moving People by Watching Frozen People（Oral）
作者：Zhengqi Li, Tali Dekel, Forrester Cole, Richard Tucker, Noah Snavely, Ce Liu, William T. Freeman
论文链接：https://arxiv.org/abs/1904.11111

18.Transferrable Prototypical Networks for Unsupervised Domain Adaptation（Oral）
作者：Yingwei Pan, Ting Yao, Yehao Li, Yu Wang, Chong-Wah Ngo, Tao Mei
论文链接：https://arxiv.org/abs/1904.11227

19.Exploring Object Relation in Mean Teacher for Cross-Domain Detection
作者：Qi Cai, Yingwei Pan, Chong-Wah Ngo, Xinmei Tian, Lingyu Duan, Ting Yao
论文链接：https://arxiv.org/abs/1904.11245

20.Pointing Novel Objects in Image Captioning
作者：Yehao Li, Ting Yao, Yingwei Pan, Hongyang Chao, Tao Mei
论文链接：https://arxiv.org/abs/1904.11251

21. Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
作者：Maosen Li, Siheng Chen, Xu Chen, Ya Zhang, Yanfeng Wang, and Qi Tian
论文链接：https://arxiv.org/pdf/1904.12659.pdf

22.Deep Fitting Degree Scoring Network for Monocular 3D Object Detection
作者：Lijie Liu1, Jiwen Lu, Chunjing Xu, Qi Tian, Jie Zhou
论文链接：https://arxiv.org/pdf/1904.12681.pdf

23.Style Transfer by Relaxed Optimal Transport and Self-Similarity
作者：Nicholas Kolkin, Jason Salavon, Gregory Shakhnarovich
论文链接：https://arxiv.org/pdf/1904.12785.pdf
源码链接：

https://github.com/nkolkin13/STROTSS

*延伸阅读