Natural Language Moment Retrieval On Tacos
评估指标
R@1,IoU=0.3
R@1,IoU=0.5
R@1,IoU=0.7
mIoU
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | R@1,IoU=0.3 | R@1,IoU=0.5 | R@1,IoU=0.7 | mIoU |
|---|---|---|---|---|
| bam-detr-boundary-aligned-moment-detection | 56.69 | 41.54 | 26.77 | 39.31 |
| learning-grounded-vision-language | 48.29 | 36.07 | - | - |
| learning-grounded-vision-language | 45.92 | 34.57 | - | - |
| saliency-guided-detr-for-moment-retrieval-and | 56.71 | 44.70 | 29.90 | 40.90 |
| ld-detr-loop-decoder-detection-transformer | 57.61 | 44.31 | 26.24 | 40.30 |
| bridging-the-gap-a-unified-video | - | 36.39 | 23.32 | - |
| flashvtg-feature-layering-and-adaptive-score | 53.71 | 41.76 | 24.74 | 37.61 |
| univtg-towards-unified-video-language | 51.44 | 34.97 | 21.07 | 35.76 |
| saliency-guided-detr-for-moment-retrieval-and | 58.10 | 46.40 | 33.90 | 42.40 |
| vlg-net-video-language-graph-matching-network | 45.46 | 34.19 | - | - |
| prior-knowledge-integration-via-llm-encoding | 52.73 | 40.12 | 22.78 | 36.55 |
| correlation-guided-query-dependency | 52.23 | 39.61 | 22.23 | 36.48 |