MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding

Open paper
Benchmark Model Rank Results
moment-retrieval-on-qvhighlightsMASRA–mAP: 47.94mAP@0.5: 68.16mAP@0.75: 48.58

Rank counts only results with a code link.