Research map / Vision-language and multimodal / Cross-modal learning
Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| jointly train multimodal and automatically supervised unimodal tasks | Self-MM · MOSI | MAE: 0.731 -> 0.713 | Helped |
| jointly train multimodal and automatically supervised unimodal tasks | Self-MM · MOSEI | Corr: 0.753 -> 0.765 | Helped |
| use automatically generated rather than human-annotated unimodal labels | Self-MM · SIMS | MAE: 0.408 -> 0.419 | Hurt |
| use automatically generated rather than human-annotated unimodal labels | Self-MM · SIMS | Corr: 0.647 -> 0.616 | Hurt |
| add unimodal subtasks (ablation) | Self-MM · MOSEI | MSE: 0.730 -> 0.713 | Helped |
| add vision subtask only (ablation) | Self-MM · MOSEI | MSE: 0.730 -> 0.732 | Hurt |
| add audio subtask only (ablation) | Self-MM · MOSEI | MSE: 0.730 -> 0.728 | Helped |
| add text subtask only (ablation) | Self-MM · MOSEI | MSE: 0.730 -> 0.731 | Hurt |
| add audio and vision subtasks (ablation) | Self-MM · MOSEI | MSE: 0.730 -> 0.719 | Helped |
| add text and vision subtasks (ablation) | Self-MM · MOSEI | MSE: 0.730 -> 0.714 | Helped |
| add text and audio subtasks (ablation) | Self-MM · MOSEI | MSE: 0.730 -> 0.712 | Helped |
Closest papers by meaning
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.90)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.89)
- Seek Common Ground While Reserving Differences: Semi-Supervised Image-Text Sentiment Recognition (CVPR 2025 · similarity 0.88)
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.88)
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.88)
- Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning (AAAI 2025 · similarity 0.87)
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.