GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding

Benchmark Model Rank Results
temporal-sentence-grounding-on-activitynet-captions-temporal-localization-val-2GroundVTS-Q (extra data)#6mIoU: 36.0R1@0.5: 33.6R1@0.7: 21.4
moment-retrieval-on-charades-staGroundVTS-Q (extra data)#44R@1 IoU=0.5: 57.5R@1 IoU=0.7: 34.2R@1 IoU=0.3: 71.5mIoU: 50.1