Memorize, Associate and Match : Embedding Enhancement via Fine-Grained Alignment for Image-Text Retrieval
Image-text retrieval aims to capture the semantic correlation between images and texts. Existing image-text retrieval methods can be roughly categorized into embedding learning paradigm and pair-wise learning paradigm. The former paradigm fails to capture the fine-grained correspondence between imag...
| Publié dans: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 05., Seite 9193-9207 |
|---|---|
| Auteur principal: | |
| Autres auteurs: | , , |
| Format: | Article en ligne |
| Langue: | English |
| Publié: |
2021
|
| Accès à la collection: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
| Sujets: | Journal Article |
| Accès en ligne |
Volltext |