Moment Retrieval On Charades Sta
평가 지표
R@1 IoU=0.5
R@1 IoU=0.7
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | R@1 IoU=0.5 | R@1 IoU=0.7 |
|---|---|---|
| video-mamba-suite-state-space-model-as-a | 57.18 | 36.05 |
| saliency-guided-detr-for-moment-retrieval-and | 71.10 | 52.80 |
| timesuite-improving-mllms-for-long-video | 48.7 | 24.0 |
| simvtp-simple-video-text-pre-training-with | 44.7 | 26.3 |
| correlation-guided-query-dependency | 58.44 | 36.34 |
| unloc-a-unified-framework-for-video | 60.8 | 38.4 |
| umt-unified-multi-modal-transformers-for | 49.35 | 26.16 |
| llava-mr-large-language-and-vision-assistant | 70.65 | 49.58 |
| saliency-guided-detr-for-moment-retrieval-and | 70.20 | 49.50 |
| ld-detr-loop-decoder-detection-transformer | 62.58 | 41.56 |
| bridging-the-gap-a-unified-video | 59.25 | 36.64 |
| qvhighlights-detecting-moments-and-highlights | 53.63 | 31.37 |
| umt-unified-multi-modal-transformers-for | 48.31 | 29.25 |
| internvideo2-scaling-video-foundation-models | 70.03 | 48.95 |
| videolights-feature-refinement-and-cross-task | 61.96 | 41.05 |
| internvideo2-scaling-video-foundation-models | 68.36 | 45.03 |
| overcoming-weak-visual-textual-alignment-for | 59.48 | 38.33 |
| unimd-towards-unifying-moment-retrieval-and | 63.98 | 44.46 |
| qvhighlights-detecting-moments-and-highlights | 55.65 | 34.17 |
| unloc-a-unified-framework-for-video | 58.1 | 35.4 |
| bam-detr-boundary-aligned-moment-detection | 59.95 | 39.38 |
| timesuite-improving-mllms-for-long-video | 67.1 | 43.0 |
| prior-knowledge-integration-via-llm-encoding | 58.31 | 36.49 |
| query-dependent-video-representation-for | 57.31 | 32.55 |
| flashvtg-feature-layering-and-adaptive-score | 70.32 | 49.87 |