Cross-Modal Information Retrieval on MSCOCO-1k
Metric: Text-to-image R@1 (higher is better)
Metric: Text-to-image R@1 (higher is better)
| # | Model↕ | Text-to-image R@1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | NAPReg | 66.9 | No | - | - | Code |
| 2 | Dual-path CNN | 25.3 | No | Dual-Path Convolutional Image-Text Embeddings wi... | 2017-11-15 | Code |