Cross Modal Retrieval On Mscoco 1K
評価指標
Image-to-text R@1
Text-to-image R@1
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Image-to-text R@1 | Text-to-image R@1 | Paper Title | Repository |
---|---|---|---|---|
Dual-path CNN | 41.2 | 25.3 | Dual-Path Convolutional Image-Text Embeddings with Instance Loss | |
NAPReg | 81.9 | 66.9 | NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings |
0 of 2 row(s) selected.