CVPR2019行人重识别论文(附链接)

论文题目

1、Joint Discriminative and Generative Learning for Person Re-identification. Zhedong Zheng; Xiaodong Yang; Zhiding Yu; Liang Zheng ; Yi Yang ; Jan Kautz

Motivation

2、Unsupervised Person Re-identification by Soft Multilabel Learning. Hong-Xing Yu ; WEI-SHI ZHENG ; Ancong Wu ; Xiaowei Guo ; Shaogang Gong ; Jian-Huang Lai

Motivation
Contribution

3、Learning Context Graph for Person Search. Yichao Yan ; Qiang Zhang Bingbing Ni; Wendong Zhang ; Minghao Xu; Xiaokang Yang
4、Progressive Pose Attention Transfer for Person Image Generation Zhen Zhu; Tengteng Huang; Baoguang Shi; Miao Yu; Bofei Wang; Xiang Bai
5、Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification. Yifan Sun (Tsinghua University); Ya-Li Li (THU); Qin Xu (Tsinghua University); Chi Zhang (Megvii Inc.); Yikang Li (CUHK); Shengjin Wang (Tsinghua University)*; Jian Sun (Megvii Technology)
6、Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification. Zhun Zhong (Xiamen University)*; Liang Zheng (Australian National University); Zhiming Luo (Xiamen University); Shaozi Li (Xiamen University, China); Yi Yang (UTS)
7、Dissecting Person Re-identification from the Viewpoint of Viewpoint. Xiaoxiao Sun (Singapore University of Technology and Design)*; Liang Zheng (Australian National University)
8、Densely Semantically Aligned Person Re-Identification. Zhizheng Zhang (University of Science and Technology of China); Cuiling Lan (Microsoft Research)*; Wenjun Zeng (Microsoft Research); Zhibo Chen (University of Science and Technology of China)
9、Generalizable Person Re-identification by Domain-Invariant Mapping Network. Jifei Song (Queen Mary, University of London)*; Yongxin Yang (University of Edinburgh ); Yi-Zhe Song (Queen Mary University of London); Tao Xiang (University of Surrey); Timothy Hospedales (Edinburgh University)
10、Re-ranking via Metric Fusion for Object Retrieval and Person Re-identification. Song Bai (University of Oxford)*; Peng Tang (Huazhong University of Science and Technology); Longin Jan Latecki (Temple University); Philip Torr (University of Oxford)
11、Weakly Supervised Person Re-Identification. Jingke Meng (Sun Yat-Sun University); Sheng Wu (Sen Yat-Sun University); WEI-SHI ZHENG (Sun Yat-sen University, China)*
12、Query-guided End-to-End Person Search. Bharti Munjal (OSRAM)*; Sikandar Amin (OSRAM GmbH); Federico Tombari (Technical University of Munich, Germany); Fabio Galasso (OSRAM)
13、Distilled Person Re-identification: Towards a More Scalable System. Ancong Wu (Sun Yat-sen University); WEI-SHI ZHENG (Sun Yat-sen University, China)*; Xiaowei Guo (Tencent Youtu Lab); Jian-Huang Lai (Sun Yat-sen University)
14、Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-Identification. Wenjie Yang (Institute of Automation, Chinese Academy of Sciences)*; Houjing Huang (CASIA); Zhang Zhang (Institute of Automation, Chinese Academy of Sciences); Xiaotang Chen (Institute of Automation, Chinese Academy of Sciences); Kaiqi Huang (Institute of Automation, Chinese Academy of Sciences); Shu Zhang (Deepwise AI Lab)
15、Patch Based Discriminative Feature Learning for Unsupervised Person Re-identification. Qize Yang (Sun Yat-sen University); Hong-Xing Yu (Sun Yat-Sen University); Ancong Wu (Sun Yat-sen University); WEI-SHI ZHENG (Sun Yat-sen University, China)*
16、Unsupervised Person Image Generation with Semantic Parsing Transformation. Sijie Song (Peking University)*; Wei Zhang (JD AI Research); Jiaying Liu (Peking University); Tao Mei (AI Research JD)
17、Text Guided Person Image Synthesis.Xingran Zhou (Zhejiang University); Siyu Huang (Zhejiang University)*; Bin Li (Zhejiang University); Yingming Li (Zhejiang University); Jiachen Li (Nanjing University); Zhongfei Zhang (Zhejiang University)
18、Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification. Yiru Zhao (Shanghai Jiao Tong University)*; Xu Shen (Alibaba Group); Zhongming Jin (Alibaba Group); Hongtao Lu (Shanghai Jiao Tong University); Xiansheng Hua (Damo Academy, Alibaba Group)
19、AANet: Attribute Attentio Network for Person Re-Identification. Chiat Pin Tay (Nanyang Technological University)*; Sharmili Roy (Nanyang Technological University); Kim Yap (Nanyang Technological University)
20、VRSTC: Occlusion-Free Video Person Re-Identification. Ruibing Hou (Institute of Computing Technology，Chinese Academy); Bingpeng MA (UCAS)*; Hong Chang (Chinese Academy of Sciences); Xinqian Gu (University of Chinese Academy of Sciences); Shiguang Shan (Chinese Academy of Sciences); Xilin Chen (China)
21、Adaptive Transfer Network for Cross-Domain Person Re-Identification. Jiawei Liu (University of Science and Technology of China); Zheng-Jun Zha (University of Science and Technology of China)*; Di Chen (University of Science and Technology of China); Richang Hong (HeFei University of Technology); Meng Wang (Hefei University of Technology)
22、Interaction-and-Aggregation Network for Person Re-identification. Ruibing Hou (Institute of Computing Technology，Chinese Academy); Bingpeng MA (UCAS)*; Hong Chang (Chinese Academy of Sciences); Xinqian Gu (University of Chinese Academy of Sciences); Shiguang Shan (Chinese Academy of Sciences); Xilin Chen (China)
23、Re-Identification with Consistent Attentive Siamese Networks. Meng Zheng (Rensselaer Polytechnic Institute); Srikrishna Karanam (Siemens Corporate Technology, Princeton)*; Ziyan Wu (Siemens Corporation); Richard Radke (Rensselaer Polytechnic Institute)
24、Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training. Feng Zheng (Southern University of Science and Technology)*; Rongrong Ji (Xiamen University, China); Cheng Deng (Xidian University); Xing Sun (Tencent); Xinyang Jiang (Tencent); Xiaowei Guo (Tencent Youtu Lab); Zongqiao Yu (Tencent); Feiyue Huang (Tencent)
25、CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification ZHENG TANG (University of Washington)*; Milind Naphade (NVidia); Ming-Yu Liu (NVIDIA); Xiaodong Yang (NVIDIA Research); Stan Birchfield (NVIDIA); Shuo Wang (NVidia); Ratnesh Kumar (NVIDIA); David Anastasiu (SJSU); Jenq-Neng Hwang (University of Washinton)
26、Re-Identification Supervised 3D Texture Generation. Jian Wang (State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences)*; Yunshan Zhong (Peking University); Yachun Li (Zhejiang University); Chi Zhang (Megvii Inc.); Yichen Wei (Megvii Research Shanghai)

1、Joint Discriminative and Generative Learning for Person Re-identification. Zhedong Zheng; Xiaodong Yang; Zhiding Yu; Liang Zheng ; Yi Yang ; Jan Kautz

paper

Motivation

最近，人们对使用生成模型来增强训练数据和增强输入变量中的不变性越来越感兴趣。然而，现有方法中的生成方法与Re-ID特征学习阶段相对独立。相应地，Re-ID模型通常以直接的方式对生成的数据进行训练。在本文中，我们试图通过更好地利用生成的数据来改善所学的Re-ID特征。为此我们提出了一个联合学习框架，将Re-ID学习和数据生成端到端的结合起来。我们的模型包括一个生成模块，它将每个人分别编码为外观编码和结构编码（姿态），以及一个与生成模块共享外观编码器的识别模块。通过切换外观或结构编码，生成模块能够生成高质量的交叉ID的合成图像，在线反馈给外观编码器，用于改进识别模块。提出的联合学习框架在不使用生成数据的情况下显著改善了baseline，从而在多个常用数据集上实现了最好的性能。
CVPR2019行人重识别论文(附链接)

2、Unsupervised Person Re-identification by Soft Multilabel Learning. Hong-Xing Yu ; WEI-SHI ZHENG ; Ancong Wu ; Xiaowei Guo ; Shaogang Gong ; Jian-Huang Lai

paper
code

Motivation

无监督RE-ID由于其在解决有监督模型的可扩展性问题上的潜力而引起了越来越多的研究关注。为了克服无重叠相机中没有成对标签的问题，本文提出了一种无监督RE-ID的软多标签学习的深度模型。通过将未标记行人与辅助域中的一组已知参考行人进行比较，给每个未标记行人学习一种软多标签（类似实值标签的似然向量）。作者提出了软多标签引导的难采样样本挖掘，通过探索视觉特征与未标注目标对软多标签的相似度一致性，来学习一种有判别力的特征描述。由于大多数目标对都是交叉视角对，因此我们设计了一种交叉视角下的一致性软多标签学习方法，以实现软多标签在不同摄像机视角上的一致性。为了实现高效的软多标签学习，我们引入了参考代理学习，在联合嵌入中通过参考代理来表示每个参考人。

Contribution

（1）本文采用一种新的软多标签参考学习方法来解决无监督RE-ID问题，利用辅助源数据集进行参考比较，挖掘出未标记RE-ID数据中潜在的标签信息。
（2）提出了一种新的深度模型，即深度软多标签参考学习(MAR)。MAR实现了将软多标签引导的难样本挖掘、跨视角一致的软多标签学习和参考代理学习统一在一个统一的模型中。
在Market-1501 和DukeMTMC-reID上的实验结果表明，模型达到了state-of-the-art。
CVPR2019行人重识别论文(附链接)

3、Learning Context Graph for Person Search. Yichao Yan ; Qiang Zhang Bingbing Ni; Wendong Zhang ; Minghao Xu; Xiaokang Yang

paper

4、Progressive Pose Attention Transfer for Person Image Generation Zhen Zhu; Tengteng Huang; Baoguang Shi; Miao Yu; Bofei Wang; Xiang Bai

paper

5、Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification. Yifan Sun (Tsinghua University); Ya-Li Li (THU); Qin Xu (Tsinghua University); Chi Zhang (Megvii Inc.); Yikang Li (CUHK); Shengjin Wang (Tsinghua University)*; Jian Sun (Megvii Technology)

paper

6、Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification. Zhun Zhong (Xiamen University)*; Liang Zheng (Australian National University); Zhiming Luo (Xiamen University); Shaozi Li (Xiamen University, China); Yi Yang (UTS)

paper

7、Dissecting Person Re-identification from the Viewpoint of Viewpoint. Xiaoxiao Sun (Singapore University of Technology and Design)*; Liang Zheng (Australian National University)

paper

8、Densely Semantically Aligned Person Re-Identification. Zhizheng Zhang (University of Science and Technology of China); Cuiling Lan (Microsoft Research)*; Wenjun Zeng (Microsoft Research); Zhibo Chen (University of Science and Technology of China)

paper

9、Generalizable Person Re-identification by Domain-Invariant Mapping Network. Jifei Song (Queen Mary, University of London)*; Yongxin Yang (University of Edinburgh ); Yi-Zhe Song (Queen Mary University of London); Tao Xiang (University of Surrey); Timothy Hospedales (Edinburgh University)

paper

10、Re-ranking via Metric Fusion for Object Retrieval and Person Re-identification. Song Bai (University of Oxford)*; Peng Tang (Huazhong University of Science and Technology); Longin Jan Latecki (Temple University); Philip Torr (University of Oxford)

11、Weakly Supervised Person Re-Identification. Jingke Meng (Sun Yat-Sun University); Sheng Wu (Sen Yat-Sun University); WEI-SHI ZHENG (Sun Yat-sen University, China)*

paper

12、Query-guided End-to-End Person Search. Bharti Munjal (OSRAM)*; Sikandar Amin (OSRAM GmbH); Federico Tombari (Technical University of Munich, Germany); Fabio Galasso (OSRAM)

13、Distilled Person Re-identification: Towards a More Scalable System. Ancong Wu (Sun Yat-sen University); WEI-SHI ZHENG (Sun Yat-sen University, China)*; Xiaowei Guo (Tencent Youtu Lab); Jian-Huang Lai (Sun Yat-sen University)

paper

14、Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-Identification. Wenjie Yang (Institute of Automation, Chinese Academy of Sciences)*; Houjing Huang (CASIA); Zhang Zhang (Institute of Automation, Chinese Academy of Sciences); Xiaotang Chen (Institute of Automation, Chinese Academy of Sciences); Kaiqi Huang (Institute of Automation, Chinese Academy of Sciences); Shu Zhang (Deepwise AI Lab)

15、Patch Based Discriminative Feature Learning for Unsupervised Person Re-identification. Qize Yang (Sun Yat-sen University); Hong-Xing Yu (Sun Yat-Sen University); Ancong Wu (Sun Yat-sen University); WEI-SHI ZHENG (Sun Yat-sen University, China)*

16、Unsupervised Person Image Generation with Semantic Parsing Transformation. Sijie Song (Peking University)*; Wei Zhang (JD AI Research); Jiaying Liu (Peking University); Tao Mei (AI Research JD)

paper

17、Text Guided Person Image Synthesis.Xingran Zhou (Zhejiang University); Siyu Huang (Zhejiang University)*; Bin Li (Zhejiang University); Yingming Li (Zhejiang University); Jiachen Li (Nanjing University); Zhongfei Zhang (Zhejiang University)

paper

18、Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification. Yiru Zhao (Shanghai Jiao Tong University)*; Xu Shen (Alibaba Group); Zhongming Jin (Alibaba Group); Hongtao Lu (Shanghai Jiao Tong University); Xiansheng Hua (Damo Academy, Alibaba Group)

19、AANet: Attribute Attentio Network for Person Re-Identification. Chiat Pin Tay (Nanyang Technological University)*; Sharmili Roy (Nanyang Technological University); Kim Yap (Nanyang Technological University)

20、VRSTC: Occlusion-Free Video Person Re-Identification. Ruibing Hou (Institute of Computing Technology，Chinese Academy); Bingpeng MA (UCAS)*; Hong Chang (Chinese Academy of Sciences); Xinqian Gu (University of Chinese Academy of Sciences); Shiguang Shan (Chinese Academy of Sciences); Xilin Chen (China)

21、Adaptive Transfer Network for Cross-Domain Person Re-Identification. Jiawei Liu (University of Science and Technology of China); Zheng-Jun Zha (University of Science and Technology of China)*; Di Chen (University of Science and Technology of China); Richang Hong (HeFei University of Technology); Meng Wang (Hefei University of Technology)

22、Interaction-and-Aggregation Network for Person Re-identification. Ruibing Hou (Institute of Computing Technology，Chinese Academy); Bingpeng MA (UCAS)*; Hong Chang (Chinese Academy of Sciences); Xinqian Gu (University of Chinese Academy of Sciences); Shiguang Shan (Chinese Academy of Sciences); Xilin Chen (China)

23、Re-Identification with Consistent Attentive Siamese Networks. Meng Zheng (Rensselaer Polytechnic Institute); Srikrishna Karanam (Siemens Corporate Technology, Princeton)*; Ziyan Wu (Siemens Corporation); Richard Radke (Rensselaer Polytechnic Institute)

paper

24、Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training. Feng Zheng (Southern University of Science and Technology)*; Rongrong Ji (Xiamen University, China); Cheng Deng (Xidian University); Xing Sun (Tencent); Xinyang Jiang (Tencent); Xiaowei Guo (Tencent Youtu Lab); Zongqiao Yu (Tencent); Feiyue Huang (Tencent)

paper

25、CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification ZHENG TANG (University of Washington)*; Milind Naphade (NVidia); Ming-Yu Liu (NVIDIA); Xiaodong Yang (NVIDIA Research); Stan Birchfield (NVIDIA); Shuo Wang (NVidia); Ratnesh Kumar (NVIDIA); David Anastasiu (SJSU); Jenq-Neng Hwang (University of Washinton)

paper

26、Re-Identification Supervised 3D Texture Generation. Jian Wang (State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences)*; Yunshan Zhong (Peking University); Yachun Li (Zhejiang University); Chi Zhang (Megvii Inc.); Yichen Wei (Megvii Research Shanghai)

paper