Image Retrieval With Multi Modal Query On Mit
평가 지표
Recall@1
Recall@10
Recall@5
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Recall@1 | Recall@10 | Recall@5 | Paper Title | Repository |
|---|---|---|---|---|---|
| Show and Tell | 11.9 | 42.0 | 31.0 | Show and Tell: A Neural Image Caption Generator | - |
| TIRG | 12.2 | 43.1 | 31.9 | Composing Text and Image for Image Retrieval - An Empirical Odyssey | - |
| FiLM | 10.1 | 38.3 | 27.7 | FiLM: Visual Reasoning with a General Conditioning Layer | - |
| Attribute as Operator | 8.8 | 39.1 | 27.3 | Attributes as Operators: Factorizing Unseen Attribute-Object Compositions | - |
| ComposeAE | 13.9 | 47.9 | 35.5 | Compositional Learning of Image-Text Query for Image Retrieval | - |
0 of 5 row(s) selected.