Picture-text Matching
Picture-Text Matching is a computational task in multimodal learning that identifies correspondences between visual content in images and semantically aligned textual descriptions by jointly modeling cross-modal representations to determine their mutual relevance.
32
Publications
1.2K
Citations
104
Authors
59
Institutions
Publications per year
2017–2026
14
Variants
Image-text Matching
Parents
32
Cross-Modal Retrieval in the Cooking Context
Micael Carvalho, Rémi Cadène, David Picard et al. · 2018 · 169 citations · Full text
1–5 of 32
104
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 104
59
University of Pennsylvania
Philadelphia, United States
3 h-index
3 publications
141 citations
University of Sheffield
Sheffield, United Kingdom
2 h-index
4 publications
100 citations
University College London
London, United Kingdom
2 h-index
2 publications
146 citations

University of Edinburgh
Edinburgh, United Kingdom
2 h-index
4 publications
205 citations
Qingdao University of Science and Technology
Qingdao, China
2 h-index
8 publications
200 citations
New York University
New York, United States
1 h-index
1 publications
23 citations

Harvard University Press
Cambridge, United States
1 h-index
1 publications
10 citations
University of Washington Tacoma
Tacoma, United States
1 h-index
1 publications
16 citations
1–8 of 59
3 publications · 46 citations
3
h-index
2 publications · 195 citations
2
h-index
1 publications · 13 citations
1
h-index
1 publications · 21 citations
1
h-index
Repository · 1 publications · 14 citations
1
h-index
1–5