Natural Language Moment Retrieval On Mad
평가 지표
R@1,IoU=0.1
R@1,IoU=0.3
R@1,IoU=0.5
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | R@1,IoU=0.1 | R@1,IoU=0.3 | R@1,IoU=0.5 |
|---|---|---|---|
| revisionllm-recursive-vision-language-model | 17.3 | 12.7 | 6.7 |
| rgnet-a-unified-retrieval-and-grounding | 12.43 | 9.48 | 5.61 |
| mad-a-scalable-dataset-for-language-grounding | 3.50 | 2.63 | 1.61 |
| localizing-moments-in-long-video-via | 5.60 | 4.28 | 2.48 |
| mad-a-scalable-dataset-for-language-grounding | 0.09 | 0.04 | 0.01 |
| mad-a-scalable-dataset-for-language-grounding | 6.57 | 3.13 | 1.39 |
| localizing-moments-in-long-video-via | 9.3 | 4.65 | 2.16 |