List your company

Video Question Answering on MSVD (test)

76.4AccuracyDivot-LLM
32.04443.559555.07566.5905Nov 22, 2022Mar 26, 2023Jul 28, 2023Nov 29, 2023Apr 1, 2024Aug 3, 2024Dec 5, 2024

Evaluation results

MethodLinks
Divot-LLMLLM size=7B, Video-Gen=true2024.1276.4
VILA-ULLM size=7B, Video-Gen=true2024.1275.3
Video-LaVITLLM size=7B, Video-Gen=true2024.1273.2
VideoLLaMA2LLM size=72B, Video-Gen=false2024.1271
VideoLLaMA2LLM size=7B, Video-Gen=false2024.1270.9
Video-LLaVALLM size=7B, Video-Gen=false2024.1270.7
VideoChat2LLM size=7B, Video-Gen=false2024.1270
LLaMA-VIDLLM size=7B, Video-Gen=false2024.1269.7
LLaVA-NeXT-VideoLLM size=7B, Video-Gen=false2024.1267.8
Video-ChatGPTLLM size=7B, Video-Gen=false2024.1264.9
LWMLLM size=7B, Video-Gen=true2024.1255.9
X2-VLM (large)# Params=593M, mode=fine-tuning2022.1154.6
X2-VLM (base)# Params=255M, mode=fine-tuning2022.1152.8
OmniVL# Params=288M, mode=fine-tuning2022.1151
OmniVLPreTrain VLData=18M2024.0351
VIOLET# Params=163M, mode=fine-tuning2022.1147.9
All-in-one# Params=110M, mode=fine-tuning2022.1147.9
OmniViD2024.0347.7
JustAskPreTrain VLData=69M2024.0346.3
ALPRO# Params=513M, mode=fine-tuning2022.1145.9
ALIPROPreTrain VLData=5.5M2024.0345.9
VA³Backbone=HQGA2024.0744.46
CoMVTPreTrain VLData=100M2024.0342.6
VA³Backbone=HGA2024.0741.24
HQGA2024.0741.23
JustAsk2024.0341.2
VA³Backbone=HME2024.0738.51
HGA2024.0736.71
HCRN2024.0336.1
HME2024.0733.75