Multimodal Embedding
Multimodal Embedding is a representational framework that integrates semantic information from multiple modalities—such as visual, textual, and auditory—into a shared, unified vector space where cross-modal correspondences and interactions can be explicitly modeled and computationally reasoned.
213
Publications
21.6K
Citations
819
Authors
258
Institutions
Publications per year
2017–2026
184
Parents
213
Feature Generating Networks for Zero-Shot Learning
Yongqin Xian, Tobias Lorenz, Bernt Schiele et al. · 2018 · 1.1K citations
1–5 of 213
819
6
h-index
5
h-index
5
h-index
5
h-index
5
h-index
1–5 of 819
258
Carnegie Mellon University
Pittsburgh, United States
7 h-index
24 publications
4.7K citations

Sun Yat-sen University
Guangzhou, China
6 h-index
15 publications
1.1K citations

Alibaba Group (China)
Hangzhou, China
6 h-index
14 publications
418 citations
Stanford University
Stanford, United States
6 h-index
14 publications
14.5K citations
Georgia Institute of Technology
Atlanta, United States
5 h-index
6 publications
210 citations

Hefei University of Technology
Hefei, China
5 h-index
23 publications
1.3K citations

Chinese Academy of Sciences
Beijing, China
5 h-index
11 publications
788 citations
University of Cambridge
Cambridge, United Kingdom
5 h-index
8 publications
811 citations
1–8 of 258
Repository · 37 publications · 3.5K citations
22
h-index
Conference · 9 publications · 1.2K citations
9
h-index
TPAMI · 6 publications · 1.3K citations
6
h-index
5 publications · 310 citations
5
h-index
TOMCCAP · 4 publications · 627 citations
4
h-index
1–5