CVPR2019 | 03-13日更新16篇论文及代码汇总（行人重识别、人体姿态估计、GAN、手写体识别等）

2019 年 3 月 13 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166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、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

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

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

4、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

5、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

6、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

7、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

8、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

9、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

10、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

11、Dissecting Person Re-identification from the Viewpoint of Viewpoint(行人再识别）
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

12、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

13、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.

14、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

15、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

16、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

*延伸阅读