Abstract
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.
Funding Information
  • National Natural Science Foundation of China (62376069)
  • National Natural Science Foundation of China (62276004)
  • National Natural Science Foundation of China (62376140)
  • Beijing Natural Science Foundation (L257007)
  • Young Elite Scientists Sponsorship Program by CAST (2023QNRC001)
  • Basic and Applied Basic Research Foundation of Guangdong Province (2024A1515012027)
  • Shenzhen Science and Technology Program (KQTD20240729102207002)
  • Shenzhen Science and Technology Program (ZDSYS20230626091203008)
  • Jiangsu Science and Technology Major Program (BG2024041)
  • Special Fund for Taishan Scholar Project of Shandong Province