List your company
ResearchFormerly WizWand

Open-Ended VideoQA on ANet-QA

64.4AccuracyLLaVA-NeXT-Video-DPO
10.3224.3638.452.44Jul 22, 2024Aug 10, 2024Aug 30, 2024Sep 19, 2024Oct 8, 2024Oct 28, 2024Nov 17, 2024
Updated 8mo ago

Evaluation results

MethodLinks
LLaVA-NeXT-Video-DPOLLM Size=34B, Vision Encoder=CLIP-L2024.0764.43.6
LLaVA-NeXT-Video-DPOLLM Size=34B, Vision Encoder=CLIP-L, Training-free=false2024.1164.43.6
PLLaVALLM Size=34B, Vision Encoder=CLIP-L2024.0760.93.7
PLLAVALLM Size=34B, Vision Encoder=CLIP-L, Training-free=false2024.1160.93.7
LLaVA-NeXT-Video-DPOLLM Size=7B, Vision Encoder=CLIP-L, Training-free=false2024.1160.23.5
SF-LLaVA-34BLLM Size=34B, Vision Encoder=CLIP-L2024.0759.23.5
SF-LLAVALLM Size=34B, Vision Encoder=CLIP-L, Training-free=true2024.1159.23.5
TS-LLAVALLM Size=34B, Vision Encoder=CLIP-L, Training-free=true2024.1158.93.5
LLaVA-NeXT-VideoLLM Size=34B, Vision Encoder=CLIP-L2024.0758.83.4
LLaVA-NeXT-VideoLLM Size=34B, Vision Encoder=CLIP-L, Training-free=false2024.1158.83.4
IG-VLM (LLaVA-v1.6)LLM Size=34B, Vision Encoder=CLIP-L2024.0758.43.5
IG-VLMLLM Size=34B, Vision Encoder=CLIP-L, Training-free=true2024.1158.43.5
TS-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training-free=true2024.1156.73.4
PLLAVALLM Size=7B, Vision Encoder=CLIP-L, Training-free=false2024.1156.33.5
LLaVA-NeXT-ImageLLM Size=34B, Vision Encoder=CLIP-L2024.0755.63.3
LLaVA-NeXT-ImageLLM Size=34B, Vision Encoder=CLIP-L, Training-free=true2024.1155.63.3
SF-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training-free=true2024.1155.53.4
IG-VLMLLM Size=7B, Vision Encoder=CLIP-L, Training-free=true2024.1154.33.4
LLaVA-NeXT-ImageLLM Size=7B, Vision Encoder=CLIP-L, Training-free=true2024.1153.83.2
LLaVA-NeXT-VideoLLM Size=7B, Vision Encoder=CLIP-L, Training-free=false2024.1153.53.2
FreeVALLM Size=7B, Vision Encoder=CLIP-L, Training-free=true2024.1151.23.5
VideoGPT+LLM Size=3.8B, Vision Encoder=CLIP-L, Training-free=false2024.1150.63.6
Video-LLaMA2LLM Size=46.7B, Vision Encoder=CLIP-L2024.0750.33.4
Video-LLaMA2LLM Size=7B, Vision Encoder=CLIP-L, Training-free=false2024.1150.23.3
DeepStack-LLLM Size=7B, Vision Encoder=CLIP-L, Training-free=true2024.1149.33.1
VideoChat2LLM Size=7B, Vision Encoder=UMT-L, Training-free=false2024.1149.13.3
Vista-LLaMALLM Size=7B, Vision Encoder=CLIP-G, Training-free=false2024.1148.33.3
MovieChat+LLM Size=7B, Vision Encoder=CLIP-G, Training-free=false2024.1148.13.4
LLaMA-VIDLLM Size=13B, Vision Encoder=CLIP-G, Training-free=false2024.1147.43.3
MovieChatLLM Size=7B, Vision Encoder=CLIP-G, Training-free=false2024.1145.73.4
Video-LLaVALLM Size=7B, Vision Encoder=ViT-L, Training-free=false2024.1145.33.3
Video-ChatGPTLLM Size=7B, Vision Encoder=CLIP-L, Training-free=false2024.1135.22.7
VideoChatLLM Size=7B, Vision Encoder=CLIP-G, Training-free=false2024.1126.52.2
Video-LLaMALLM Size=7B, Vision Encoder=CLIP-G, Training-free=false2024.1112.41.1