Long Chen

Postdoctoral Research Scientist
Digital Video and Multimedia (DVMM) Lab
Fu Foundation School of Engineering and Applied Science
Columbia University
Email (zjuchenlong A~T gmail.com)
[Résumé] [WeChat]

Long Chen is a postdoctoral research scientist at DVMM Lab, Columbia University in the City of New York working with Prof. Shih-Fu Chang (2021 - present). He obtained his Ph.D. degree in Computer Science from Zhejiang University and his Ph.D. advisor is Prof. Jun Xiao (2015 - 2020). During his Ph.D. period, he also worked closely with Prof. Hanwang Zhang from Nanyang Technological University and Prof. Tat-Seng Chua from National University of Singapore. He obtained his B.Eng. degree in Electronic Information Engineering from Dalian University of Technology (2011 - 2015). He was a senior research scientist at Tencent AI Lab (Shenzhen) working with Dr. Wei Liu (2020 - 2021).

Research Interest

His primary research interests are Computer Vision, Machine Learning, and Multimedia. Specifically, he aims to build an efficient vision system that can understand complex visual scenes as humans. By “human-like”, we mean that the vision systems should be equipped with three types of abilities:

1) Explainable: The model should rely on (right) explicit evidences when making decisions, ie, right for the right reasons.
Related Work: SCA-CNN (CVPR’17), CMAT (ICCV’19 Oral), SituFormer (AAAI’22), BIG (CVPR’22)

2) Robust: The model should be robust to some situations with only low-quality training data (eg, training samples are biased, noisy, or limited).
Related Work: CSS (CVPR’20), KDDAug (ECCV’22), NICE (CVPR’22 Oral), SP-AEN (CVPR’18), FCT (CVPR’22 Oral)

3) Universal: The model design is relatively universal, ie, it is expected to be effective for various tasks.
Related Work: CrossFormer (ICLR’22), GTR (EMNLP’21 Oral)

Selected Publications

1. arXiv
arXiv preprint (arXiv) , arXiv , extension of CVPR’22 work
2. arXiv
arXiv preprint (arXiv) , arXiv , extension of CVPR’20 work
3. ECCV
European Conference on Computer Vision (ECCV) , 2022 , Codes
4. ECCV
European Conference on Computer Vision (ECCV) , 2022 , Codes
5. CVPR
Computer Vision and Pattern Recognition (CVPR) , 2022 , Oral presentation
6. CVPR
Computer Vision and Pattern Recognition (CVPR) , 2022 , Codes , Oral presentation
7. CVPR
Computer Vision and Pattern Recognition (CVPR) , 2022 , Codes
8. ICLR
International Conference on Learning Representations (ICLR) , 2022 , Codes
9. EMNLP
Empirical Methods in Natural Language Processing (EMNLP) , 2021 , Codes , Oral presentation
10. EMNLP
Empirical Methods in Natural Language Processing (EMNLP) , 2021 , Codes
11. CVPR
Computer Vision and Pattern Recognition (CVPR) , 2021 , Codes
12. CVPR
Computer Vision and Pattern Recognition (CVPR) , 2020 , Codes
13. EMNLP
Empirical Methods in Natural Language Processing (EMNLP) , 2019 , Oral presentation
14. ICCV
International Conference on Computer Vision (ICCV) , 2019 , Oral presentation
15. CVPR
Computer Vision and Pattern Recognition (CVPR) , 2018 , Codes
16. CVPR
Computer Vision and Pattern Recognition (CVPR) , 2017 , Codes , Google citations over 1000+ times
Top-100 Most Cited Paper within 5 Years in CVPR, Google Scholar 2021&2022