Multimodal fusion for multimedia analysis: a survey
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Encoder-decoder methods efficiently represent scene semantics through encoding, interaction, and decoding.
“The encoder-decoder method [48] efficiently represents scene semantics through encoding, interaction, and decoding.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [48]
The citation lists haven’t been fetched yet
References 162 · Cited by 1,279
- Authors
- Atrey, P. K., Hossain, M. A., El Saddik, A., & Kankanhalli, M. S.
- Affiliations
- The University of Winnipeg (CA)
- University of Ottawa (CA)
- National University of Singapore (SG)
- Corresponding author
- Atrey, Pradeep K.
- Venue
- Multimedia Systems
- Published
- 2010-04-04
- Volume
- 16
- Issue
- 6
- Pages
- 345-379
- ISSN
- 0942-4962 (ISSN-L)
- 1432-1882
- OpenAlex
- W2053101950
- Cited by
- 1,279
- References
- 162
- Citations by year
- 2026: 109 · 2025: 124 · 2024: 77 · 2023: 79 · 2022: 110 · 2021: 96 · 2020: 72 · 2019: 87 · 2018: 76 · 2017: 85 · 2016: 82 · 2015: 81 · 2014: 86 · 2013: 51 · 2012: 43
- FWCI
- 42.71
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Multimedia Systems (publishedVersion)
- National University of Singapore (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Analysis and Summarization
- Keywords
- multimodal fusion, multimedia analysis, feature-level fusion, decision fusion, hybrid fusion, confidence level, contextual information, modality selection, fusion strategies
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
