Phrase Grounding On Flickr30K Entities Test
평가 지표
R@1
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | R@1 |
|---|---|
| multimodal-compact-bilinear-pooling-for | 48.69 |
| disentangled-motif-aware-graph-learning-for | 78.73 |
| visualbert-a-simple-and-performant-baseline | 71.33 |
| learning-cross-modal-context-graph-for-visual | 76.74 |
| phrase-grounding-by-soft-label-chain | 74.69 |
| natural-language-object-retrieval | 27.8 |
| rethinking-diversified-and-discriminative | 73.3 |
| learning-deep-structure-preserving-image-text | 43.89 |
| glipv2-unifying-localization-and-vision | 87.7 |
| flickr30k-entities-collecting-region-to | 25.30 |
| flickr30k-entities-collecting-region-to | 41.77 |
| mdetr-modulated-detection-for-end-to-end | 84.3 |
| grounded-language-image-pre-training | 87.1 |
| pevl-position-enhanced-pre-training-and | 84.4 |
| flickr30k-entities-collecting-region-to | 30.83 |
| bilinear-attention-networks | 69.69 |
| coarse-to-fine-vision-language-pre-training | 87.4 |
| grounding-of-textual-phrases-in-images-by | 48.38 |