LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
Open paper
Benchmark
Model
Rank
Results
moment-retrieval-on-charades-sta
LLaVA-ST (extra data)
#63
R@1 IoU=0.5: 44.8
R@1 IoU=0.7: 23.4
R@1 IoU=0.3: 63.1
mIoU: 42.4
Rank counts only results with a code link.