VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
Open paper
Benchmark
Model
Rank
Results
temporal-sentence-grounding-on-activitynet-captions-temporal-localization-val-2
VideoLLaMA2 + VidChain (extra data)
#4
mIoU: 44.1
R1@0.5: 44.8
R1@0.7: 25.2
Rank counts only results with a code link.