VidCtx: Context-aware Video Question Answering with Image Models
Open paper
Benchmark
Model
Rank
Results
zero-shot-video-question-answer-on-star
VidCtx (7B)
#2
Accuracy: 51.1
zero-shot-video-question-answer-on-intentqa
VidCtx (7B)
#3
Accuracy: 67.1
zero-shot-video-question-answer-on-next-qa
VidCtx (7B)
#11
Accuracy: 70.7
Rank counts only results with a code link.