STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training

no code implementations • 29 Nov 2024 • Haiyi Qiu, Minghe Gao, Long Qian, Kaihang Pan, Qifan Yu, Juncheng Li, Wenjie Wang, Siliang Tang, Yueting Zhuang, Tat-Seng Chua

Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step spatio-temporal inference across object relations, interactions, and events.

Question Answering Video Understanding