SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability
Open paper
Benchmark
Model
Rank
Results
moment-retrieval-on-charades-sta
SpaceVLLM 7B (extra data)
#22
R@1 IoU=0.5: 63.6
R@1 IoU=0.7: 38.5
Rank counts only results with a code link.