| CARVIEW |
 |
Weihua Chen 陈威华
work in Alibaba DAMO Academy. |
News
-
[Paper Accepted] SOLIDER is accepted by CVPR 2023, which achieves state-of-the-art on six downstream human visual tasks, and the project website has been released [link], which has attracted 1.8K+ star.
-
[Code Released] The project website of DAMO-YOLO is released [link], which outperforms state-of-the-art YOLO series and attracts 3.8K+ star on github.
-
[Paper Accepted] One paper is accepted by ECCV 2022, and the code has been released [link].
-
[Paper Accepted] TagPerson is accepted by ACM MM 2022, and the code has been released [link].
-
[Paper Accepted] One paper is accepted by IEEE TIFS.
-
[Paper Accepted] CDTrans is accepted by ICLR 2022, and the code has been released [link].
Biography
-
He joined Alibaba in 2018. Now, he is a senior algorithm engineer in Alibaba DAMO Academy. His current researches are mainly on self-supervised, unsupervised learning and domain adaptation. He has published over 30+ papers in international journals and top conferences such as CVPR, ICCV, ECCV, ICLR and ACM MM. He has received the championships of multiple challenges in top conferences, including 5 champions, 2 runners-up, 1 third runner-up. His current researches are mainly on self-supervised/semi-supervised/unsupervised learning and domain adaptation.
-
Weihua Chen obtained his Ph.D. degree in National Laboratory of Pattern Recognition (NLPR), Institute of Automation Chinese Academy of Sciences (CASIA), as a member of Center for Research on Intelligent Perception and Computing (CRIPAC). And he received the Bachelor and Master degree in Beijing Jiaotong University (BJTU).
Selected Publications (# corresponding, * equal contribution)
-
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks
Weihua Chen, Xianzhe Xu, Jian Jia, Hao Luo, Yaohua Wang, Fan Wang, Rong Jin, Xiuyu Sun
The Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[PDF]
[Project Website]
-
Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty
Yuan Zhang*, Weihua Chen*, Yichen Lu*, Tao Huang, Xiuyu Sun, Jian Cao
The 30th ACM International Conference on Multimedia (ACM MM), 2023.
[PDF]
-
Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Chong Liu, Yuqi Zhang, Hongsong Wang#, Weihua Chen#, Fan Wang, Yan Huang, Yi-Dong Shen, Liang Wang
IEEE Transactions on Image Processing (TIP), 2023.
[PDF]
[Code]
-
Graph Convolution Based Efficient Re-Ranking for Visual Retrieval
Yuqi Zhang, Qi Qian, Hongsong Wang, Chong Liu, Weihua Chen, Fan Wang
IEEE Transactions on Multimedia (TMM), 2023.
[PDF]
[Code]
-
TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification
Kai Chen, Weihua Chen#, Tao He, Rong Du, Fan Wang, Xiuyu Sun, Yuchen Guo, Guiguang Ding
The 29th ACM International Conference on Multimedia (ACM MM), 2022.
[PDF]
[Code]
-
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
Tongkun Xu*, Weihua Chen*, Pichao Wang, Fan Wang, Hao Li, Rong Jin
The International Conference on Learning Representations (ICLR), 2022.
[PDF]
[Code]
[Slides]
-
DAMO-YOLO: A Report on Real-Time Object Detection Design
Xianzhe Xu*, Yiqi Jiang*, Weihua Chen*, Yilun Huang*, Yuan Zhang* and Xiuyu Sun
Arxiv 2211.15444.
[PDF]
[Project Website]
-
Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval
Zhaopeng Dou, Zhongdao Wang, Weihua Chen, Yali Li, and Shengjin Wang
The European Conference on Computer Vision (ECCV), 2022.
[PDF]
[Code]
-
Multi-view Evolutionary Training for Unsupervised Domain Adaptive Person Re-Identification
Jianyang Gu, Weihua Chen, Hao Luo, Fan Wang, Hao Li, Wei Jiang, Weijie Mao
IEEE Transactions on Information Forensics and Security (TIFS), 2022.
[PDF]
-
Exploring the Quality of GAN Generated Images for Person Re-Identification
Yiqi Jiang*, Weihua Chen*, Xiuyu Sun, Xiaoyu Shi, Fan Wang, Hao Li
The 29th ACM International Conference on Multimedia (ACM MM), 2021.
[PDF]
-
Towards discriminative representation learning for unsupervised person re-identification
Takashi Isobe, Dong Li, Lu Tian, Weihua Chen, Yi Shan, Shengjin Wang
The IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
[PDF]
-
Beyond triplet loss: a deep quadruplet network for person re-identification
Weihua Chen, Xiaotang Chen, Jianguo Zhang, Kaiqi Huang
The Conference on Computer Vision and Pattern Recognition (CVPR Spotlight), 2017.
[PDF]
[Slides]
-
A Multi-task Deep Network for Person Re-identification
Weihua Chen, Xiaotang Chen, Jianguo Zhang, Kaiqi Huang
The Thirty-First AAAI Conference on Artificial Intelligence (AAAI Oral), 2017.
[PDF]
[Code]
-
An Equalised Global Graphical Model-Based Approach for Multi-Camera Object Tracking
Weihua Chen, Lijun Cao, Xiaotang Chen, Kaiqi Huang
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2016.
[PDF]
[Code]
[Demo]
Honors and Awards
- Win the 1st place in AICITY Challenge Track3 Multi-camera Vehicle Tracking on CVPR 2021. [PDF] [Code]
- Win the 1st place in AICITY Challenge Track2 Vehicle Re-Identification on CVPR 2021. [PDF] [Code]
- Win the 1st place in Multi-camera Multi-Person tracking on ICCV 2021.
- Win the 1st place Tracking Any Objects (TAO) Challenge on ECCV 2020. [PDF] [Code]
- Win the 1st place Visual Domain Adaptation (VisDA) Challenge on ECCV 2020. [PDF] [Code]
- Win the 2nd (2/263, top1%) place in Google Landmark Retrieval Competition on ICCV 2021 and silver medal in Google Landmark Recognition Competition. [PDF] [Code] [Kaggle Poster] [Slides] [Video]
- Win the 2nd place in RobMOTS: The Ultimate Tracking Challenge on CVPR 2021. [PDF]
- Win the 3rd place in AICITY Challenge Track2 Vehicle Re-Identification on CVPR 2020. [PDF] [Code]
- Organize the Multi-Camera Object Tracking (MCT) Challenge in Visual Surveillance and Re-identification Workshop on ECCV 2014
- Serve as Area Chair for VALSE2023/PRCV2023.
- Serve as Reveiwer for top conferences and journals, such as PAMI/TIP/TIFS/TCSVT/CVPR/ICCV/ECCV/NIPS.
- Serve as Member of Technical Committee on Machine Vision for China Society of Image and Graphics (CSIG).
- Serve as Youth Committee for Beijing Society of Image and Graphics (BSIG).
- Invited tutorial talk in IJCB 2021 with the topic of Human-centric Visual Understanding: From Research to Applications.
