List your company

Video Question Answering on EgoSchema 3 min (test)

66.2AccuracyVideoTree
39.1646.1853.260.22Aug 13, 2025

Evaluation results

MethodLinks
VideoTreeVenue=CVPR’25, LLM Size=GPT-4, Frames=63.22025.0866.2
Qwen2-VL w/ OursVenue=-, LLM Size=7B, Frames=Avg 92025.0865.6
LLaVA-OV w/ OursVenue=-, LLM Size=7B, Frames=Avg 92025.0865.2
Qwen2.5-VL w/ OursVenue=-, LLM Size=7B, Frames=Avg 92025.0864.4
BOLTVenue=CVPR’25, LLM Size=7B, Frames=162025.0861.8
LLaVA-OV‡Venue=ArXiv’24, LLM Size=7B, Frames=162025.0861.4
Qwen2-VL‡Venue=ArXiv’24, LLM Size=7B, Frames=162025.0861.2
VideoAgentVenue=ECCV’24, LLM Size=GPT-4, Frames=8.42025.0860.2
MVUVenue=ICLR’25, LLM Size=7B, Frames=162025.0860.2
Qwen2.5-VL‡Venue=ArXiv’25, LLM Size=7B, Frames=162025.0860.2
Qwen2-VL‡Venue=ArXiv’24, LLM Size=7B, Frames=82025.0859.6
LLoViVenue=EMNLP’24, LLM Size=GPT-3.5, Frames=902025.0857.6
Qwen2.5-VL‡Venue=ArXiv’25, LLM Size=7B, Frames=82025.0856.4
VideoChat2Venue=CVPR’24, LLM Size=7B, Frames=162025.0854.4
VideoLLaMaVenue=ICCV’25, LLM Size=7B, Frames=82025.0853.8
VideoLLaMA2Venue=ArXiv’24, LLM Size=7B, Frames=82025.0853.1
PLLaVAVenue=ArXiv’24, LLM Size=7B, Frames=162025.0845.6
VideoLLaVAVenue=EMNLP’24, LLM Size=7B, Frames=82025.0840.2