Multimodal Fusion
Multimodal Fusion is a computational framework that integrates heterogeneous data streams from multiple modalities, such as visual, textual, and auditory inputs, into a unified representation by exploiting their complementary and synergistic relationships to enhance joint understanding in tasks like Visual Question Answering.
2.4K
Publications
163.8K
Citations
9.8K
Authors
1.8K
Institutions
Publications per year
2017–2026
1.9K
2.4K
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
Hao Tan, Mohit Bansal · 2019 · 2.3K citations · Full text
Joint 3D Proposal Generation and Object Detection from View Aggregation
Jason S. Ku, Melissa Mozifian, Jungwook Lee et al. · 2018 · 1.7K citations
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
Akira Fukui, Dong Huk Park, Daylen Yang et al. · 2016 · 1.4K citations · Full text
1–5 of 2.4K
9.8K
24
h-index
18
h-index
17
h-index
14
h-index
13
h-index
1–5 of 9.8K
1.8K

Chinese Academy of Sciences
Beijing, China
46 h-index
318 publications
21.8K citations
University of Chinese Academy of Sciences
Beijing, China
40 h-index
220 publications
17.8K citations
Tsinghua University
Beijing, China
38 h-index
145 publications
13.1K citations
National University of Singapore
Singapore, Singapore
30 h-index
109 publications
9.9K citations
Institute of Automation
Beijing, China
27 h-index
131 publications
9.3K citations
Carnegie Mellon University
Pittsburgh, United States
26 h-index
88 publications
19.6K citations

Peking University
Beijing, China
26 h-index
103 publications
5.6K citations

Sun Yat-sen University
Guangzhou, China
26 h-index
91 publications
7.1K citations
1–8 of 1.8K
Repository · 194 publications · 10.5K citations
47
h-index
Conference · 64 publications · 4.6K citations
38
h-index
54 publications · 4.8K citations
36
h-index
60 publications · 3.8K citations
35
h-index
50 publications · 3.7K citations
33
h-index
1–5