CVPR2019| 04-22更新19篇论文及代码（2篇oral，含物体检测、动作识别、医学影像等）

2019 年 4 月 22 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491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.ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging(Oral)
作者： Samarth Brahmbhatt, Cusuh Ham, Charles C. Kemp, and James Hays
论文链接：

https://contactdb.cc.gatech.edu/contactdb_paper.pdf
源码链接：

https://github.com/samarth-robo/contactdb_prediction

2.Aggregation Cross-Entropy for Sequence Recognition
作者：Zecheng Xie, Yaoxiong Huang, Yuanzhi Zhu, Lianwen Jin, Yuliang Liu, Lele Xie
论文链接：https://arxiv.org/abs/1904.08364

3.Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
作者：Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon
论文链接：https://arxiv.org/abs/1904.08482

4.Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset
作者：Martin Mundt, Sagnik Majumder, Sreenivas Murali, Panagiotis Panetsos, Visvanathan Ramesh
论文链接：https://arxiv.org/abs/1904.08486

5.Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
作者：Zihao Liu, Xiaowei Xu, Tao Liu, Qi Liu, Yanzhi Wang, Yiyu Shi, Wujie Wen, Meiping Huang, Haiyun Yuan, Jian Zhuang
论文链接：https://arxiv.org/abs/1904.08487

6.Few-Shot Learning with Localization in Realistic Settings
作者：Davis Wertheimer, Bharath Hariharan
论文链接：https://arxiv.org/abs/1904.08502

7.Progressive Attention Memory Network for Movie Story Question Answering
作者：Junyeong Kim, Minuk Ma, Kyungsu Kim, Sungjin Kim, Chang D. Yoo
论文链接：https://arxiv.org/abs/1904.08607

8.Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
作者：Junbao Zhuo, Shuhui Wang, Shuhao Cui, Qingming Huang
论文链接：https://arxiv.org/abs/1904.08631

9.DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
作者：Toby Perrett, Dima Damen
论文链接：https://arxiv.org/abs/1904.08634

10.Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
作者：Devraj Mandal, Sanath Narayan, Saikumar Dwivedi, Vikram Gupta, Shuaib Ahmed, Fahad Shahbaz Khan, Ling Shao
论文链接：https://arxiv.org/abs/1904.08703

11.A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
作者：Thanh-Toan Do, Toan Tran, Ian Reid, Vijay Kumar, Tuan Hoang, Gustavo Carneiro
论文链接：https://arxiv.org/abs/1904.08720

12.Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
作者：Zhe Wu, Li Su, Qingming Huang
论文链接：https://arxiv.org/abs/1904.08739

13.4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
作者：Christopher Choy, JunYoung Gwak, Silvio Savarese
论文链接：https://arxiv.org/abs/1904.08755

14.Attentive Single-Tasking of Multiple Tasks
作者：Kevis-Kokitsi Maninis, Ilija Radosavovic, Iasonas Kokkinos
论文链接：https://arxiv.org/abs/1904.08918

15.Towards VQA Models that can Read
作者：Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, Marcus Rohrbach
论文链接：https://arxiv.org/abs/1904.08920

16.Listen to the Image
作者：Di Hu, Dong Wang, Xuelong Li, Feiping Nie, Qi Wang
论文链接：https://arxiv.org/abs/1904.09115

17.SelFlow: Self-Supervised Learning of Optical Flow
作者：Pengpeng Liu, Michael Lyu, Irwin King, Jia Xu
论文链接：https://arxiv.org/abs/1904.09117

18.Visualizing the decision-making process in deep neural decision forest
作者：Shichao Li, Kwang-Ting Cheng
论文链接：https://arxiv.org/abs/1904.09201
源码链接：

https://github.com/Nicholasli1995/VisualizingNDF

19.STEP: Spatio-Temporal Progressive Learning for Video Action Detection（Oral,视频动作识别）
作者：Xitong Yang, Xiaodong Yang, Ming-Yu Liu, Fanyi Xiao, Larry Davis, Jan Kautz
论文链接：https://arxiv.org/abs/1904.09288