8 papers
One Skill Does Not Fit All: Automatic Discovery and Taxonomy-Guided Routing of Frame-Selection Skills for Long-Video Question Answering
Jian Hu, Zixu Cheng, Da Li +3
Long-Video Question Answering (LVQA) requires locating decisive evidence in hour-scale videos under a limited frame budget. Most training-free methods apply the same frame-selectio…
Grounding Video Reasoning in Physical Signals
Alibay Osmanli, Zixu Cheng, Shaogang Gong
Physical video understanding requires more than naming an event correctly. A model can answer a question about pouring, sliding, or collision from textual regularities while still…
GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking
Zixu Cheng, Da Li, Jian Hu +4
Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. Current Multimodal Large Language…
ViSMaP: Unsupervised Hour-long Video Summarisation by Meta-Prompting
Jian Hu, Dimitrios Korkinof, Shaogang Gong +1
We introduce ViSMap: Unsupervised Video Summarisation by Meta Prompting, a system to summarise hour long videos with no-supervision. Most existing video understanding models work w…
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning
Zixu Cheng, Jian Hu, Ziquan Liu +3
Human processes video reasoning in a sequential spatio-temporal reasoning logic, we first identify the relevant frames ("when") and then analyse the spatial relationships ("where")…
CoS: Chain-of-Shot Prompting for Long Video Understanding
Jian Hu, Zixu Cheng, Chenyang Si +2
Multi-modal Large Language Models (MLLMs) struggle with long videos due to the need for excessive visual tokens. These tokens exceed massively the context length of MLLMs, resultin…