Multimodal Input Processing
Multimodal Input Processing is a cognitive and computational framework that integrates and interprets linguistic and non-linguistic input from multiple sensory modalities—such as visual, auditory, and textual sources—during real-time comprehension tasks, particularly in sight translation, by coordinating modality-specific representations into a unified mental representation to facilitate meaning construction.
210
Publications
16.4K
Citations
725
Authors
306
Institutions
Publications per year
2017–2026
84
210
Integrating Multimodal Information in Large Pretrained Transformers
Wasifur Rahman, Md. Kamrul Hasan, Sangwu Lee et al. · 2020 · 604 citations · Full text
Embodiment in conversational interfaces
Justine Cassell, Timothy Bickmore, Mark Billinghurst et al. · 1999 · 561 citations
1–5 of 210
725
10
h-index
4
h-index
3
h-index
Institute for Research on Population and Social Policies, Italy
3 publications · 45 citations
3
h-index
3
h-index
1–5 of 725
306
University College London
London, United Kingdom
8 h-index
15 publications
815 citations
Oregon Health & Science University
Portland, United States
8 h-index
17 publications
1.3K citations
Bielefeld University
Bielefeld, Germany
7 h-index
17 publications
550 citations

Radboud University Nijmegen
Nijmegen, The Netherlands
6 h-index
7 publications
194 citations
Massachusetts Institute of Technology
Cambridge, United States
4 h-index
4 publications
516 citations

Centre National de la Recherche Scientifique
Paris, France
4 h-index
5 publications
169 citations
Max Planck Institute for Psycholinguistics
Nijmegen, The Netherlands
4 h-index
6 publications
211 citations
Google (United States)
Mountain View, United States
4 h-index
10 publications
534 citations
1–8 of 306
Repository · 11 publications · 510 citations
10
h-index
4 publications · 159 citations
4
h-index
Repository · 4 publications · 72 citations
4
h-index
3 publications · 129 citations
3
h-index
3 publications · 91 citations
3
h-index
1–5