List your company

Multiple Choice Video-QA on Perception (test)

63.4AccuracyVideoChat2-HD-F16
43.53648.69353.8559.007Mar 22, 2024May 4, 2024Jun 16, 2024Jul 29, 2024Sep 10, 2024Oct 23, 2024Dec 5, 2024

Evaluation results

MethodLinks
VideoChat2-HD-F16ViEncoder=InternVideo2_S3-1B, LLM=Mistral-7B, Frames=162024.0363.4
VideoChat2-HDViEncoder=InternVideo2_S3-1B, LLM=Mistral-7B2024.0360.1
Divot-LLMLLM size=7B, Video-Gen=true2024.1258.3
PLLAVALLM size=34B, Video-Gen=false2024.1258.1
VideoLLaMA2LLM size=72B, Video-Gen=false2024.1257.5
Gemini 1.0 Ultra2024.0354.7
VideoChat2ViEncoder=InternVideo2_S3-1B, LLM=Mistral-7B2024.0353
VideoLLaMA2ViEncoder=CLIP-L-336, LLM=Mistral-8*7B2024.0352.2
VideoLLaMA2ViEncoder=CLIP-L-336, LLM=Mistral-7B2024.0351.4
VideoLLaMA2LLM size=7B, Video-Gen=false2024.1251.4
Gemini 1.0 Pro2024.0351.1
Gemini 1.0 ProVideo-Gen=false2024.1251.1
LLaVA-Next-VideoViEncoder=CLIP-L, LLM=Vicuna-7B2024.0348.8
LLaVA-NeXT-VideoLLM size=7B, Video-Gen=false2024.1248.8
Video-LaVITLLM size=7B, Video-Gen=true2024.1247.9
VideoChat2LLM size=7B, Video-Gen=false2024.1247.3
LLaMA-VIDLLM size=7B, Video-Gen=false2024.1244.6
Video-LLaVALLM size=7B, Video-Gen=false2024.1244.3