I am a final-year Ph.D. student in Computer Science at KAUST, advised by Prof. Bernard Ghanem. Prior to that, I obtained my master degree from Shanghai Jiao Tong University, and bachelor degree from Xi’an JiaoTong University.
My research centers on Long-Form Video Understanding, with expertise in:
- Video-Language Models, such as video-language pre-training, video-language foundation models.
- Long-Form Video Understanding, such as temporal action detection, action recognition, and video grounding.
📢 I am actively seeking full-time research positions. Feel free to reach out if you have any opportunities: shuming.liu[at]kaust.edu.sa
🔥 News
- 2025.06: I start my Internship at Meta as Research Scientist Intern.
- 2025.05: I am awarded the Dean’s List Award of KAUST for 2025.
- 2025.04: OpenTAD is accepted to CVPR Workshop 2025.
- 2025.02: BOLT is accepted by CVPR 2025.
- 2025.01: I will join Meta as Research Scientist Intern in Summer 2025!
- 2024.07: One co-authored paper is accepted by ECCV 2024.
- 2024.06: We rank 1st in the Action Recognition, Action Detection, and Audio-Based Interaction Detection tasks of the EPIC-KITCHENS-100 2024 Challenge, as well as 1st place in the Moment Queries task of the Ego4D 2024 Challenge by using OpenTAD!
- 2024.06: I am awarded the Dean’s List Award of KAUST for 2024.
- 2024.05: We release the OpenTAD, which is currently the largest TAD codebase.
- 2024.02: Two papers are accepted by CVPR 2024.
- 2024.01: One paper is accepted by ICLR 2024.
- 2023.02: One paper is accepted by CVPR 2023 and one paper is accepted by CVPRW 2023.
📝 Publications
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Shuming Liu, Bernard Ghanem, Vikas Chandra, Yunyang Xiong, et al.
Arxiv 2026, [Project Page] [Code]
BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
Shuming Liu, Chen Zhao, Tianqi Xu, Bernard Ghanem
CVPR 2025, [Code]
OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection
Shuming Liu, Chen Zhao, Bernard Ghanem, et al.
CVPRW 2025, [Code]
Harnessing Temporal Causality for Advanced Temporal Action Detection
Shuming Liu, Lin Sui, Chen-Lin Zhang, Fangzhou Mu, Chen Zhao, Bernard Ghanem
Technical Report, [Code]
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
Shuming Liu, Chen-Lin Zhang, Chen Zhao, Bernard Ghanem
CVPR 2024, [Code]
ETAD: Training Action Detection End to End on a Laptop
Shuming Liu, Mengmeng Xu, Chen Zhao, Xu Zhao, Bernard Ghanem
CVPRW 2023, [Code]
-
Arxiv 2025Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
Haozhe Liu, Ding Liu, Mingchen Zhuge, Zijian Zhou, Tian Xie, Sen He, Yukang Yang, Shuming Liu, Yuren Cong, Jiadong Guo, Hongyu Xu, Ke Xu, Kam-Woh Ng, Juan C Pérez, Tao Xiang, Wei Liu, Shikun Liu, Jürgen Schmidhuber -
Arxiv 2025TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos
Chen-Lin Zhang*, Lin Sui*, Shuming Liu*, Fangzhou Mu*, Zhangcheng Wang, Bernard Ghanem -
ECCV 2024ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
Carlos Hinojosa, Shuming Liu, Bernard Ghanem [Code] -
CVPR 2024Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam, Jitendra Malik, Bernard Ghanem [Code] -
CVPRW 2024Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition
Hasan Hammoud, Shuming Liu, Mohammed Alkhrashi, Fahad AlBalawi, Bernard Ghanem -
ICLR 2024Boundary-Denoising for Video Activity Localization
Mengmeng Xu, Mattia Soldan, Jialin Gao, Shuming Liu, Juan-Manuel Perez-Rua, Bernard Ghanem [Code] -
CVPR 2023Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Bernard Ghanem [Code] -
TMM 2020Transferable Knowledge Based Multi-Granularity Fusion Network for Weakly Supervised Temporal Action Detection
Haisheng Su, Xu Zhao, Tianwei Lin, Shuming Liu, Zhilan Hu -
ACCV 2020TSI: Temporal Scale Invariant Network for Action Proposal Generation
Shuming Liu, Xu Zhao, Haisheng Su, Zhilan Hu [Code]
📖 Educations
- 2021.09 - now, Ph.D., King Abdullah University of Science and Technology (KAUST), Saudi Arabia.
- 2018.09 - 2021.04, Master, Shanghai Jiao Tong University (SJTU), China.
- 2014.09 - 2018.06, Bachelor, Xi’an JiaoTong University (XJTU), China.
🎖 Honors and Awards
- 2025.05 Dean’s List Award of KAUST (20%)
- 2024.06 Dean’s List Award of KAUST (20%)
- 2021.03 Outstanding Graduate of SJTU
- 2019.12 Scholarship of SJTU (5%)
- 2018.06 Outstanding Undergraduate of XJTU
- 2017.12 Scholarship of XJTU (5%)
💻 Service
Conference Reviewer: CVPR, ICCV, ECCV, ICLR, ICML, NeurIPS, AAAI, WACV, BMVC
Journal Reviewer: TPAMI, IJCV, TIP, TMM, Neurocomputing
Teaching Assistant: Introduction to Computer Vision (KAUST), Computer Vision (SJTU)