CVPR2019 | 03-18日更新13篇论文及代码汇总(包括行人重识别、视频、数据集、姿态估计等)
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185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.SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images(金山云大规模X光违禁品安检数据集)
作者:Caijing Miao, Lingxi Xie, Fang Wan, Chi Su, Hongye Liu, Jianbin Jiao, Qixiang Ye
论文链接:https://arxiv.org/abs/1901.00303
论文简要:本文针对X光安检数据集,提出了类别平衡的分层细化模型处置数据集存在的成绩。
2.Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning(金山云)
作者:Chen Wei, Lingxi Xie, Xutong Ren, Yingda Xia, Chi Su, Jiaying Liu, Qi Tian, Alan L. Yuille
论文链接:https://arxiv.org/abs/1812.00329
论文摘要:本文提出一种适用于恣意网格尺寸与维度的“拼图”成绩的新办法,同时提出了一个根本且具有普遍意义的准绳,即在无监视场景中较弱的信息更容易被学习,且具有更好的可迁移性。
3.Snapshot Distillation: Teacher-Student Optimization in One Generation(金山云)
作者:Chenglin Yang, Lingxi Xie, Chi Su, Alan L. Yuille
论文链接:https://arxiv.org/abs/1812.00123v1
论文简要:本文引见了第一种可以在训练单个模型的条件下完成教员-先生优化的办法——快照蒸馏(Snapshot Distillation),在不引入过多的计算耗费状况下,完成了继续的功能提升。
4.Pluralistic Image Completion
作者:Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai
论文链接:https://arxiv.org/abs/1903.04227
源码链接:https://github.com/lyndonzheng/Pluralistic-Inpainting
项目链接:http://www.chuanxiaz.com/publication/pluralistic/
5.Learning to Reconstruct People in Clothing from a Single RGB Camera
作者:Thiemo Alldieck, Marcus Magnor, Bharat Lal Bhatnagar, Christian Theobalt, Gerard Pons-Moll
论文链接:https://arxiv.org/abs/1903.05885
6.Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation(oral)
作者:He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas
论文链接:https://arxiv.org/abs/1901.02970
7.SimulCap : Single-View Human Performance Capture with Cloth Simulation
作者:Tao Yu, Zerong Zheng, Yuan Zhong, Jianhui Zhao, Qionghai Dai, Gerard Pons-Moll, Yebin Liu
论文链接:https://arxiv.org/abs/1903.06323
8.Unsupervised Person Re-identification by Soft Multilabel Learning(行人再识别,Oral)
作者:Hong-Xing Yu, Wei-Shi Zheng, Ancong Wu, Xiaowei Guo, Shaogang Gong, Jian-Huang Lai
论文链接:https://arxiv.org/abs/1903.06325
源码链接:https://github.com/KovenYu/MAR
9.SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representation
作者:Shuaifeng Zhi, Michael Bloesch, Stefan Leutenegger, Andrew J. Davison
论文链接:https://arxiv.org/abs/1903.06482
10.MFAS: Multimodal Fusion Architecture Search
作者:Juan-Manuel Pérez-Rúa, Valentin Vielzeuf, Stéphane Pateux, Moez Baccouche, Frédéric Jurie
论文链接:https://arxiv.org/abs/1903.06496
11.Bringing Blurry Alive at High Frame-Rate with an Event Camera
作者:Liyuan Pan, Richard Hartley, Cedric Scheerlinck, Miaomiao Liu, Xin Yu, Yuchao Dai
论文链接:https://arxiv.org/abs/1903.06531
12.Inserting Videos into Videos
作者:Donghoon Lee, Tomas Pfister, Ming-Hsuan Yang
论文链接:https://arxiv.org/abs/1903.06571
13.Selective Kernel Networks
作者:Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang
论文链接:https://arxiv.org/abs/1903.06586
源码链接:https://github.com/implus/SKNet