Multimodal Routing: Improving Local and Global Interpretability of Multimodal Language Analysis
Open accessAbstract
, which dynamically adjusts weights between input modalities and output representations differently for each input sample. Multimodal routing can identify relative importance of both individual modalities and cross-modality features. Moreover, the weight assignment by routing allows us to interpret modality-prediction relationships not only globally (i.e. general trends over the whole dataset), but also locally for each single input sample, mean-while keeping competitive performance compared to state-of-the-art methods.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 37 · Cited by 98
Research works printed but not linked: 3
- Degottex Gilles, Kane John, Drugman Thomas, Raitio Tuomo, and Scherer Stefan. 2014. Covarepa collaborative voice analysis repository for speech technologies. In 2014 ieee international conference on acoustics, speech and signal processing (icassp), pages 960– 964. IEEE.
- Engle Randi A. 1998. Not channels but composite signals: Speech, gesture, diagrams and object demonstrations are integrated in multimodal explanations. In Proceedings of the twentieth annual conference of the cognitive science society, pages 321– 326.
- Sabour Sara, Frosst Nicholas, and Hinton Geoffrey E. 2017. Dynamic routing between capsules. In Advances in neural information processing systems, pages 3856– 3866.
- Authors
- Tsai, Y.-H. H., Ma, M., Yang, M., Salakhutdinov, R., & Morency, L.-P.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Published
- 2020
- Volume
- 2020
- Pages
- 1823-1833
- PMC
- PMC8106385
- OpenAlex
- W3089817689
- Cited by
- 98
- References
- 37
- Citations by year
- 2026: 7 · 2025: 15 · 2024: 23 · 2023: 19 · 2022: 20 · 2021: 14
- FWCI
- 4.04
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1750439, 1722822)
- Nvidia
- National Institutes of Health
- Defense Advanced Research Projects Agency
- National Institute of Mental Health (R01MH096951)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- multimodal routing, interpretability
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
