Wei Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wei Liu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jianlong Wu
Harbin Institute of Technology, Shenzhen, Shenzhen, China and Shenzhen Loop Area Institute, Shenzhen, China
3 shared publications - Bei Wang
Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China and Shenzhen Loop Area Institute, Shenzhen, Guangdong, China
1 shared publication - Chang Wen Chen
Hong Kong Polytechnic University, Hong Kong, China
1 shared publication - Chenghao Ma
China Electronics Standardization Institute, Beijing, China
1 shared publication - Liqiang Nie
Harbin Institute of Technology (Shenzhen), Shenzhen, China
1 shared publication - Meng Liu
School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5398-5407
Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5398-5407
Open AccessContinuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12776-12783
FineBadminton: A Multi-Level Dataset for Fine-Grained Badminton Video Understanding
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12776-12783
Open AccessFineBadminton: A Multi-Level Dataset for Fine-Grained Badminton Video Understanding
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1521-1541
A Survey on Video Temporal Grounding With Multimodal Large Language Model
The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning abilities, VTG approaches based on MLLMs (VTG-MLLMs) are gradually surpassing traditional fine-tuned methods. They not only achieve competitive performance but also excel in generalization across zero-shot, multi-task, and multi-domain settings. Despite extensive surveys on general video-language understanding, comprehensive reviews specifically addressing VTG-MLLMs remain scarce. To fill this gap, this survey systematically examines current research on VTG-MLLMs through a three-dimensional taxonomy: 1) the functional roles of MLLMs, highlighting their architectural significance; 2) training paradigms, analyzing strategies for temporal reasoning and task adaptation; and 3) video feature processing techniques, which determine spatiotemporal representation effectiveness. We further discuss benchmark datasets, evaluation protocols, and summarize empirical findings. Finally, we identify existing limitations and propose promising research directions.
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1521-1541
A Survey on Video Temporal Grounding With Multimodal Large Language Model
The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning abilities, VTG approaches based on MLLMs (VTG-MLLMs) are gradually surpassing traditional fine-tuned methods. They not only achieve competitive performance but also excel in generalization across zero-shot, multi-task, and multi-domain settings. Despite extensive surveys on general video-language understanding, comprehensive reviews specifically addressing VTG-MLLMs remain scarce. To fill this gap, this survey systematically examines current research on VTG-MLLMs through a three-dimensional taxonomy: 1) the functional roles of MLLMs, highlighting their architectural significance; 2) training paradigms, analyzing strategies for temporal reasoning and task adaptation; and 3) video feature processing techniques, which determine spatiotemporal representation effectiveness. We further discuss benchmark datasets, evaluation protocols, and summarize empirical findings. Finally, we identify existing limitations and propose promising research directions.