Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
Open paper
Benchmark
Model
Rank
Results
moment-retrieval-on-charades-sta
Grounded-VideoLLM Phi-3.5 (task-tuned) (extra data)
#51
R@1 IoU=0.5: 55.9
R@1 IoU=0.7: 33.2
R@1 IoU=0.3: 70.2
mIoU: 49.4
Rank counts only results with a code link.