The DOI matches its Crossref record.
Incomplete Multimodality-Diffused Emotion Recognition
Abstract
Human multimodal emotion recognition (MER) aims to perceive and understand human emotions via various heterogeneous modalities, such as language, vision, and acoustic. Compared with unimodality, the complementary information in the multimodalities facilitates robust emotion understanding. Nevertheless, in real-world scenarios, the missing modalities hinder multimodal understanding and result in degraded MER performance. In this paper, we propose an Incomplete Multimodality-Diffused emotion recognition (IMDer) method to mitigate the challenge of MER under incomplete multimodalities. To recover the missing modalities, IMDer exploits the score-based diffusion model that maps the input Gaussian noise into the desired distribution space of the missing modalities and recovers missing data abided by their original distributions. Specially, to reduce semantic ambiguity between the missing and the recovered modalities, the available modalities are embedded as the condition to guide and refine the diffusion-based recovering process. In contrast to previous work, the diffusion-based modality recovery mechanism in IMDer allows to simultaneously reach both distribution consistency and semantic disambiguation. Feature visualization of the recovered modalities illustrates the consistent modality-specific distribution and semantic alignment. Besides, quantitative experimental results verify that IMDer obtains state-of-the-art MER accuracy under various missing modality patterns. Codes are released at https://github.com/mdswyz/IMDer .
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“While these methods, particularly advanced ones like diffusion models (Yuanzhi Wang et al., 2023), can achieve high visual fidelity and help maintain performance, their effectiveness is highly dependent on the quality and completeness of the training data, and they often incur substantial computational and storage costs.”
From Multimodal neuroimaging and AI integration in cognitive disorders: advances, challenges, and future directions for precision medicine (2026) · cites this paper as Yuanzhi Wang et al., 2023
Citations
Cites
Still being checked.
Cited by
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
Cheng, Z., Cheng, Z.-Q., He, J.-Y., Sun, J., Wang, K., Lin, Y., Lian, Z., Peng, X., & Hauptmann, A. G. (2024) · neural information processing systems · doi:10.52202/079017-3518 · Cited by 404
Deep Multimodal Learning with Missing Modality: A Survey
Wu, R., Hu, W., Chen, H., & Carneiro, G. (2024) · Transactions on machine learning research · doi:10.48550/arxiv.2409.07825 · Cited by 265
Context-Aware Interaction Network for RGB-T Semantic Segmentation
Lv, Y., Liu, Z., & Li, G. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3349072 · Cited by 165
Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model
Li, W., Zhou, H., Yu, J., Song, Z., & Yang, W. (2024) · neural information processing systems · doi:10.52202/079017-1910 · Cited by 123
Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models
Shen, F., Ye, H., Liu, S., Zhang, J., Wang, C., Han, X., & Wei, Y. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i7.32728 · Cited by 113
Metadata
- Authors
- Wang, Y., Li, Y., & Cui, Z.
- ORCID
- Wang, Yuanzhi
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 17117-17128
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133205100
- Cited by
- 44
- References
- 0
- Citations by year
- 2026: 41 · 2025: 3
- FWCI
- 5.10
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- emotion recognition
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.