VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
Open paper
Benchmark
Model
Rank
Results
moment-retrieval-on-charades-sta
MMDuet (zero-shot) (extra data)
#68
R@1 IoU=0.5: 42.4
R@1 IoU=0.7: 18.0
Rank counts only results with a code link.