Research map / Vision-language and multimodal / Cross-modal learning
Recovering Coherent Affective Patterns: Addressing Modality Missing in Multimodal Sentiment Analysis
Huiting Huang, Tieliang Gong, Kai He, Wen Wen, Weizhan Zhang, Mengling Feng
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 H-CAG generator (ablation) | RECAP · CH-SIMS | F1: 71.52 -> 76.06 | Improved |
| add H-CAG generator (ablation) | RECAP · MOSI | Acc-7: 34.11 -> 35.07 | Improved |
| add FID module (ablation) | RECAP · CH-SIMS | F1: 74.33 -> 76.06 | Improved |
| add FID module (ablation) | RECAP · MOSI | Acc-7: 33.67 -> 35.07 | Improved |
| add FID shared branch (ablation) | RECAP · CH-SIMS | F1: 72.37 -> 76.06 | Improved |
| add FID unique branch (ablation) | RECAP · CH-SIMS | F1: 71.79 -> 76.06 | Improved |
| add FID unique branch (ablation) | RECAP · MOSI | Acc-7: 33.67 -> 35.07 | Improved |
| add language-visual FID pair (ablation) | RECAP · CH-SIMS | F1: 72.14 -> 76.06 | Improved |
| add language-acoustic FID pair (ablation) | RECAP · CH-SIMS | F1: 71.64 -> 76.06 | Improved |
| add acoustic-visual FID pair (ablation) | RECAP · MOSI | Acc-7: 35.13 -> 35.07 | No clear effect |
| add reconstructor (ablation) | RECAP · CH-SIMS | F1: 74.13 -> 76.06 | Improved |
| add MIR fusion (ablation) | RECAP · CH-SIMS | F1: 74.36 -> 76.06 | Improved |
Closest papers by meaning
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.90)
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.90)
- A Multi-Focus-Driven Multi-Branch Network for Robust Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.89)
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.88)
- Enriching Multimodal Sentiment Analysis Through Textual Emotional Descriptions of Visual-Audio Content (AAAI 2025 · similarity 0.88)
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.88)
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.
