Research map / Vision-language and multimodal / Cross-modal learning
PSA-MF: Personality-Sentiment Aligned Multi-Level Fusion for Multimodal Sentiment Analysis
Heng Xie, Kang Zhu, Zhengqi Wen, Jianhua Tao, Xuefei Liu, Ruibo Fu, Changsheng Li
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 personality feature extraction (ablation) | PSA-MF · CMU-MOSI | Acc2: 84.60 -> 86.43 | Improved |
| add BERT-based multimodal pre-fusion (ablation) | PSA-MF · CMU-MOSI | Acc2: 84.76 -> 86.43 | Improved |
| add enhanced fusion module (serial plus parallel fusion) (ablation) | PSA-MF · CMU-MOSI | Acc7: 37.3 -> 46.5 | Improved |
| add personalized sentiment constraint loss Lps (ablation) | PSA-MF · CMU-MOSI | Acc2: 83.99 -> 86.43 | Improved |
| add cross-modal contrastive loss Lclm (ablation) | PSA-MF · CMU-MOSI | Acc7: 40.8 -> 46.5 | Improved |
| apply personality-sentiment alignment at layer 12 (unfused audio-visual) instead of layer 11 (ablation) | PSA-MF · CMU-MOSI | Acc2 and F1 | Hurt |
| replace prior SOTA with PSA-MF on Acc7 | PSA-MF vs FGTI · CMU-MOSI | Acc7: 48.0 -> 46.5 | Hurt |
| PSA-MF vs best prior on MOSEI Corr and Acc2/F1 | PSA-MF · CMU-MOSEI | Corr: 0.776 -> 0.774 | Mixed |
Closest papers by meaning
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.88)
- 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 0.87)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.87)
- A Multi-Focus-Driven Multi-Branch Network for Robust Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.87)
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.86)
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.
