profile.jpeg

Long Chen

Assistant Professor
Department of Computer Science and Engineering
The Hong Kong University of Science and Technology (HKUST)
Clear Water Bay, Kowloon, Hong Kong
Office: Room 3508 (via Lift 25 & 26), Academic Building
Email: longchen A~T ust.hk

Dr. Long CHEN (Chinese Name: 陈隆) is a tenure-track Assistant Professor in the CSE department, The Hong Kong University of Science and Technology (2023 - present). Before joining HKUST, he was a postdoctoral research scientist at the DVMM Lab, Columbia University working with Prof. Shih-Fu Chang (2021 - 2023). 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, Prof. Shih-Fu Chang from Columbia 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 working with Dr. Wei Liu (2020 - 2021).

We are looking for a few Ph.D./MPhil. students starting from 24 Fall (and also 24 Spring). Please read the information for prospective students before emailing me.


Research Interest

His primary research interest 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, i.e., right for the right reasons.

2) Robust: The model should be robust to some situations with only low-quality training data (e.g., training samples are biased, noisy, or limited).

3) Universal: The model design is relatively universal, i.e., it is expected to be effective for various tasks.

Meanwhile, with the rapid development in other AI areas, such as the appearance of Large Language Models (LLMs) in the Natural Language Processing community, we are also very interested in several releveant cutting-edge directions:

4) Building more explainable, robust, and universal vision models with the help of LLMs.

5) Designing more efficient and stronger multimodal LLMs.

6) The inherent weaknesses in existing LLMs.


News

Jun, 2023 I will serve as an Area Chair for CVPR 2024 and a Senior PC for AAAI 2024.
Mar, 2023 I will serve as an Area Chair for NeurIPS 2023 and an Area Chair for BMVC 2023.
Nov, 2022 I will serve as a Senior PC for IJCAI 2023 and an Action Editor for ACL Rolling Review (ARR).
Oct, 2022 I will serve as an Area Chair for CVPR 2023.
Jul, 2022 I will serve as an Area Chair for BMVC 2022 and a Senior PC for AAAI 2023.
Apr, 2022 My dissertation was reported by the official wechat account of ZJU.
Nov, 2021 I won the 2020 Outstanding Doctoral Dissertation Award at Zhejiang Province.
Oct, 2021 We won the best paper award of the 2nd HUMA Workshop in ACM Multimedia 2021.
Sep, 2021 I won the 2020 Outstanding Doctoral Dissertation Award at Zhejiang University (Only 1 recipient in ZJU EE/CS).
Jul, 2021 We won the 1st place in the 3rd Video Relation Understanding Challenge. The report and codes are released.

Recent Publications

  1. arXiv
    [New!!] UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory
    Haiwen Diao, Bo Wan, Ying Zhang, Xu Jia, Huchuan Lu, and Long Chen
    arXiv preprint (arXiv) , arXiv , Codes
  2. arXiv
    [New!!] A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future
    Chaoyang Zhu, and Long Chen
    arXiv preprint (arXiv) , arXiv
  3. arXiv
    [New!!] IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models
    Haoxuan You, Rui Sun, Zhecan Wang, Long Chen, Gengyu Wang, Hammad A. Ayyubi, Kai-Wei Chang, and Shih-Fu Chang
    arXiv preprint (arXiv) , arXiv , Codes
  4. NeurIPS
    Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models
    Lin Li, Jun Xiao, Guikun Chen, Jian Shao, Yueting Zhuang, and Long Chen
    Neural Information Processing Systems (NeurIPS) , 2023
  5. ICCV
    Compositional Feature Augmentation for Unbiased Scene Graph Generation
    Lin Li, Guikun Chen, Jun Xiao, Yi Yang, Chunping Wang, and Long Chen
    International Conference on Computer Vision (ICCV) , 2023 , Codes
  6. ACL Findings
    Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs
    Mingyang Zhou, Yi R. Fung, Long Chen, Christopher Thomas, Heng Ji, and Shih-Fu Chang
    Annual Meeting of the Association for Computational Linguistics (ACL Findings) , 2023 , Codes
  7. ICLR
    Video Scene Graph Generation from Single-Frame Weak Supervision
    Siqi Chen, Jun Xiao, and Long Chen
    International Conference on Learning Representations (ICLR) , 2023 , Codes
  8. ICLR
    Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
    Kaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao, and Qianru Sun
    International Conference on Learning Representations (ICLR) , 2023 , Codes
  9. ICLR
    TempCLR: Temporal Alignment Representation with Contrastive Learning
    Yuncong Yang, Jiawei Ma, Shiyuan Huang, Long Chen, Xudong Lin, Guangxing Han, and Shih-Fu Chang
    International Conference on Learning Representations (ICLR) , 2023 , Codes
  10. TPAMI
    Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering
    Long Chen, Yuhang Zheng, Yulei Niu, Hanwang Zhang, and Jun Xiao
    IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI) , 2023 , extension of CVPR’20 work