Research map / Vision-language and multimodal / Cross-modal learning
TMDC: A Two-Stage Modality Denoising and Complementation Framework for Multimodal Sentiment Analysis with Missing and Noisy Modalities
Yan Zhuang, Minhao Liu, Yanru Zhang, Jiawen Deng, Fuji Ren
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add two-stage denoising and complementation (TMDC vs MoMKE) | TMDC · MOSI (avg of 7 conditions) | accuracy (%): +0.59 accuracy | Improved |
| Remove inter-modality complementation stage (ablation) | TMDC · IEMOCAP (avg) | WA (%): 66.05 -> 73.77 | Improved |
| Add intra-modality denoising stage (ablation) | TMDC · MOSI (avg) | accuracy (%): 74.48 -> 77.64 | Improved |
| Add modality-specific denoising module (ablation) | TMDC · MOSI (avg) | accuracy (%): 74.76 -> 77.64 | Improved |
| Add modality-common denoising module (ablation) | TMDC · MOSI (avg) | accuracy (%): 75.67 -> 77.64 | Improved |
| Use TMDC rather than MoMKE with Gaussian noise 10 | TMDC · Noisy MOSEI | accuracy (%): 61.2 -> 71.2 | Improved |
| Use TMDC rather than MoMKE with Gaussian noise 20 | TMDC · Noisy MOSI | accuracy (%): 52.7 -> 53.0 | No clear effect |
| Increase Gaussian noise intensity from none to 20 | TMDC · IEMOCAP | accuracy/WA (%): 73.8 -> 37.1 | Hurt |
| Use TMDC rather than MoMKE with only audio on MOSI | TMDC · MOSI audio only | accuracy (%): 63.19 -> 62.35 | Hurt |
Later papers that compared with this method
1 later accepted paper reports TMDC as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- General Incomplete Multimodal Learning via Dynamic Quality Perception (ECCV 2026 · better on 11 of 11 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.91)
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.91)
- Towards Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2024 · similarity 0.90)
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.90)
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.89)
- Gradient-Guided Modality Decoupling for Missing-Modality Robustness (AAAI 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
