Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models
Open paper
Benchmark
Model
Rank
Results
video-question-answering-on-activitynet-qa
AVS
–
Accuracy: 52.7
zeroshot-video-question-answer-on-activitynet-qa
AVS
–
Accuracy: 52.7
Rank counts only results with a code link.