List your company

Multiple-choice Video Question Answering on IntentQA (test)

66.9AccuracyVideoTree
42.77249.03655.361.564Feb 16, 2024Mar 13, 2024Apr 8, 2024May 4, 2024May 30, 2024Jun 25, 2024Jul 22, 2024

Evaluation results

MethodLinks
VideoTreeLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=SFT2024.0766.9————
SF-LLaVA-34BLLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.0766.5————
LLaVA v1.6Vision Encoder=ViT-L, LLM Size=34B, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0365.3————
IG-VLM (LLAVA-v1.6)LLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.0765.3————
GPT-4VVision Encoder=Unknown, LLM Size=GPT-4, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0364.2————
LLoViVision Encoder=ViT-L, LLM Size=GPT-3.5, Inference Vision=multiple, Inference LLM=multiple, Video Trained=false2024.0364————
LLoViTraining Mode=Zero-shot2024.0264————
LLoViLLM Size=GPT-3.5, Vision Encoder=Unknown, Training Strategy=SFT2024.0764————
Q-ViDTraining Mode=Zero-shot2024.0263.6————
SeViLATraining Mode=Zero-shot2024.0260.9————
LLaVA v1.6Vision Encoder=ViT-L, LLM Size=7B, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0360.3————
IG-VLM LLaVA v1.6Vision Encoder=ViT-L, LLM Size=7B, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0359.7————
CaVIRTraining Mode=Supervised2024.0257.6————
BlindGPTTraining Mode=Supervised2024.0251.6————
VGTTraining Mode=Supervised2024.0251.3————
HQGATraining Mode=Supervised2024.0247.7————
CogAgentVision Encoder=CLIP-E, LLM Size=7B, Inference Vision=single, Inference LLM=single, Video Trained=false2024.0343.7————
BlindGPT2023.11—52.1661.2843.4351.55
CaVIR2023.11—58.465.4650.4857.64
HGA2023.11—44.8850.9739.6244.61
HQGA2023.11—48.2454.3241.7147.66
Vamos2023.11—75.1477.4469.5874.16
VGT2023.11—51.4455.9947.6251.27