CVPR2019| 04-10更新34篇论文及代码（6篇oral、含FAIR工作、视频跟踪、人脸识别、动作识别等）

2019 年 4 月 10 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？。目前官方只公布了接收论文ID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395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.Large-Scale Long-Tailed Recognition in an Open World（Oral)

作者：Ziwei Liu*, Zhongqi Miao*, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu
论文链接：

https://github.com/ofsoundof/3D_Appearance_SR/blob/master/code/scripts/3d_appearance_sr.pdf
源码链接：

https://github.com/zhmiao/OpenLongTailRecognition-OLTR

2.3D Appearance Super-Resolution with Deep Learning
作者：待补充
论文链接：

https://github.com/ofsoundof/3D_Appearance_SR/blob/master/code/scripts/3d_appearance_sr.pdf
源码链接：

https://github.com/ofsoundof/3D_Appearance_SR

3.High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection（行人检测）
作者：Zhao-Min Chen, Xiu-Shen Wei Peng Wang3Yanwen Guo1
论文链接：

https://github.com/liuwei16/CSP/blob/master/docs/2019CVPR-CSP.pdf
源码链接：https://github.com/liuwei16/CSP

4.Multi-Label Image Recognition with Graph Convolutional Networks（多标记图像识别）
作者：Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, Yanwen Guo
论文链接：https://arxiv.org/abs/1904.03582
源码链接：

https://github.com/chenzhaomin123/ML_GCN
简介：本工作针对多标记识别的核心问题，即“如何有效建模标记间的协同关系”进行探索，提出基于图卷积（GCN）的端到端系统，通过data-driven方式建立标记间有向图（directed graph）并由GCN将类别标记映射（mapping）为对应类别分类器，以此建模类别关系，同时可提升表示学习能力。此外针对GCN中的关键元素correlation matrix进行了深入分析和重设计，使其更胜任多标记问题。

5.Cycle-Consistency for Robust Visual Question Answering（VQA)
作者：Gao Peng, Zhengkai Jiang, Haoxuan You, Zhengkai Jiang, Pan Lu, Steven Hoi, Xiaogang Wang, Hongsheng Li
论文链接：https://arxiv.org/pdf/1812.05252.pdf

6.Data augmentation using learned transformsfor 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/pdf/1902.09383.pdf
源码链接：

https://github.com/xamyzhao/brainstorm

7.DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency (Oral )
作者：Kuang-Jui Hsu, Yen-Yu Lin, Yung-Yu Chuang
论文链接：

http://cvlab.citi.sinica.edu.tw/images/paper/cvpr-hsu19.pdf
源码链接：

https://github.com/KuangJuiHsu/DeepCO3

8.Calibration of Asynchronous Camera Networks for Object Reconstruction Tasks

作者：Amy Tabb, Henry Medeiros
论文链接：https://arxiv.org/abs/1903.06811

9.LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks
作者：Sudhakar Kumawat, Shanmuganathan Raman
论文链接：https://arxiv.org/abs/1904.03498

10.A Variational Auto-Encoder Model for Stochastic Point Processes

作者：Nazanin Mehrasa, Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, Greg Mori
论文链接：https://arxiv.org/abs/1904.03273

11.2.5D Visual Sound（FAIR Oral)
作者：Ruohan Gao, Kristen Grauman
论文链接：https://arxiv.org/abs/1812.04204
项目链接：

http://vision.cs.utexas.edu/projects/2.5D_visual_sound/
源码链接：

https://github.com/facebookresearch/FAIR-Play

12.DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality
作者：Chloe LeGendre, Wan-Chun Ma, Graham Fyffe, John Flynn, Laurent Charbonnel, Jay Busch, Paul Debevec
论文链接：https://arxiv.org/abs/1904.01175

13.Kervolutional Neural Networks
作者：Chen Wang, Jianfei Yang, Lihua Xie, Junsong Yuan
论文链接：https://arxiv.org/abs/1904.03955

14.SoDeep: a Sorting Deep net to learn ranking loss surrogates
作者：Martin Engilberge, Louis Chevallier, Patrick Pérez, Matthieu Cord
论文链接：https://arxiv.org/abs/1904.04272

15.3D Local Features for Direct Pairwise Registration
作者：Haowen Deng, Tolga Birdal, Slobodan Ilic
论文链接：https://arxiv.org/abs/1904.04281

16.Neural Rerendering in the Wild(Oral)
作者：Moustafa Meshry, Dan B Goldman, Sameh Khamis, Hugues Hoppe, Rohit Pandey, Noah Snavely, Ricardo Martin-Brualla
论文链接：https://arxiv.org/abs/1904.04290

17.End-to-end Projector Photometric Compensation
作者：Bingyao Huang, Haibin Ling
论文链接：https://arxiv.org/abs/1904.04335

18.What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
作者：Paritosh Parmar, Brendan Tran Morris
论文链接：https://arxiv.org/abs/1904.04346

19.Towards Universal Object Detection by Domain Attention
作者：Xudong Wang, Zhaowei Cai, Dashan Gao, Nuno Vasconcelos
论文链接：https://arxiv.org/abs/1904.04402
项目链接：

http://www.svcl.ucsd.edu/projects/universal-detection/

20.Efficient Decision-based Black-box Adversarial Attacks on Face Recognition（人脸识别）
作者：Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, Jun Zhu
论文链接：https://arxiv.org/abs/1904.04433

21.Reliable and Efficient Image Cropping: A Grid Anchor based Approach
作者：Hui Zeng, Lida Li, Zisheng Cao, Lei Zhang
论文链接：https://arxiv.org/abs/1904.04441
代码链接：https://github.com/HuiZeng/Grid-Anchor-based-Image-Cropping

22.SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking（视觉跟踪）
作者：Guangting Wang, Chong Luo, Zhiwei Xiong, Wenjun Zeng
论文链接：https://arxiv.org/abs/1904.04452

23.Graphonomy: Universal Human Parsing via Graph Transfer Learning
作者：Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin
论文链接：https://arxiv.org/abs/1904.04536
源码链接：

https://github.com/Gaoyiminggithub/Graphonomy

24.Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks
作者：Eunwoo Kim, Chanho Ahn, Philip H.S. Torr, Songhwai Oh
论文链接：https://arxiv.org/abs/1904.04562

25.Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning from Radiology Reports and Label Ontology（Oral)
作者：Ke Yan, Yifan Peng, Veit Sandfort, Mohammadhadi Bagheri, Zhiyong Lu, Ronald M. Summers
论文链接：https://arxiv.org/abs/1904.04661

26.Domain-Symmetric Networks for Adversarial Domain Adaptation
作者：Yabin Zhang, Hui Tang, Kui Jia, Mingkui Tan
论文链接：https://arxiv.org/abs/1904.04663

27.Action Recognition from Single Timestamp Supervision in Untrimmed Videos（动作识别）
作者：Davide Moltisanti, Sanja Fidler, Dima Damen
论文链接：https://arxiv.org/abs/1904.04689

28.Label Propagation for Deep Semi-supervised Learning
作者：Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum
论文链接：https://arxiv.org/abs/1904.04717

29.Cross-Modal Self-Attention Network for Referring Image Segmentation
作者：Linwei Ye, Mrigank Rochan, Zhi Liu, Yang Wang
论文链接：https://arxiv.org/abs/1904.04745

30.Leveraging the Invariant Side of Generative Zero-Shot Learning
作者：Jingjing Li, Mengmeng Jin, Ke Lu, Zhengming Ding, Lei Zhu, Zi Huang
论文链接：https://arxiv.org/abs/1904.04092

31.Learning monocular depth estimation infusing traditional stereo knowledge
作者：Fabio Tosi, Filippo Aleotti, Matteo Poggi, Stefano Mattoccia
论文链接：https://arxiv.org/abs/1904.04144
代码链接：

https://github.com/fabiotosi92/monoResMatch-Tensorflow

32.Unsupervised learning of action classes with continuous temporal embedding
作者：Anna Kukleva, Hilde Kuehne, Fadime Sener, Juergen Gall
论文链接：https://arxiv.org/abs/1904.04189

33.Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering
作者：Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
论文链接：https://arxiv.org/abs/1904.04196

34.Relational Action Forecasting(oral)
作者：Chen Sun, Abhinav Shrivastava, Carl Vondrick, Rahul Sukthankar, Kevin Murphy, Cordelia Schmid
论文链接：https://arxiv.org/abs/1904.04231

*延伸阅读