BAM-DETR (w/ audio)

Reported on 5 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision5 results

Moment RetrievalonQVHighlights
R@1 IoU=0.5· 2023-11-30
64.07
best: 76.59 (LLaVA-MR)
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos arXiv:2312.00083
Moment RetrievalonQVHighlights
R@1 IoU=0.7· 2023-11-30
48.12
best: 61.48 (LLaVA-MR)
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos arXiv:2312.00083
Moment RetrievalonQVHighlights
mAP· 2023-11-30
46.91
best: 58.8 (SG-DETR (w/ PT))
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos arXiv:2312.00083
Moment RetrievalonQVHighlights
mAP@0.5· 2023-11-30
65.61
best: 76.2 (SG-DETR (w/ PT))
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos arXiv:2312.00083
Moment RetrievalonQVHighlights
mAP@0.75· 2023-11-30
47.51
best: 60.8 (SG-DETR (w/ PT))
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos arXiv:2312.00083