List your company
ResearchFormerly WizWand

Multiple-choice Video Question Answering on TVQA (test)

57.8AccuracyGPT-4V
35.02440.93746.8552.763Mar 27, 2024
Updated 8mo ago

Evaluation results

MethodLinks
GPT-4VVision Encoder=Unknown, LLM Size=GPT-4, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0357.8
LLaVA v1.6Vision Encoder=ViT-L, LLM Size=34B, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0351.1
IG-VLM LLaVA v1.6Vision Encoder=ViT-L, LLM Size=7B, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0344.5
LLaVA v1.6Vision Encoder=ViT-L, LLM Size=7B, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0342.1
VideoChat2Vision Encoder=UMT-L, LLM Size=7B, Inference Vision=multiple, Inference LLM=single, Video Trained=true2024.0340.6
CogAgentVision Encoder=CLIP-E, LLM Size=7B, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0338.6
SevillaVision Encoder=ViT-L, LLM Size=2.85B, Inference Vision=multiple, Inference LLM=multiple, Video Trained=true2024.0338.2
InternVideoVision Encoder=ViT-L, LLM Size=1.3B, Inference Vision=multiple, Inference LLM=single, Video Trained=true2024.0335.9