Research map / Vision-language and multimodal / Cross-modal learning
TPFN: Applying Outer Product along Time to Multimodal Sentiment Analysis Fusion on Incomplete Data
Binghua Li, Chao Li, Feng Duan, Ning Zheng, Qibin Zhao
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 low-rank Frobenius-norm regularization (ablation) | TPFN · CMU-MOSI random drop, high (p=0.9) | ACC-2: 0.5845 -> 0.6559 | Improved |
| add low-rank regularization (ablation) | TPFN · CMU-MOSI structured drop, high (p=0.9) | ACC-2: 0.6151 -> 0.6516 | Improved |
| add low-rank regularization (ablation) | TPFN · CMU-MOSEI random drop, high (p=0.9) | ACC-2: 0.7156 -> 0.7334 | Improved |
| add low-rank regularization (ablation) | TPFN · CMU-MOSEI structured drop, high (p=0.9) | ACC-2: 0.7007 -> 0.7301 | Improved |
| add low-rank regularization (ablation) | TPFN · CMU-MOSI structured drop, low (p=0.1) | ACC-2: 0.7682 -> 0.7594 | Hurt |
| add low-rank regularization (ablation) | TPFN · CMU-MOSEI structured drop, low (p=0.1) | ACC-2: 0.7437 -> 0.7386 | Hurt |
| add low-rank regularization (ablation) | TPFN · CMU-MOSI random drop, low (p=0.1) | ACC-2: 0.7638 -> 0.7915 | Improved |
| use TPFN instead of T2FN | T2FN · CMU-MOSI random drop, high (p=0.9) | ACC-2: 0.5962 -> 0.6559 | Improved |
| use TPFN instead of T2FN | T2FN · CMU-MOSI structured drop, low (p=0.1) | ACC-2: 0.7478 -> 0.7594 | Improved |
| use TPFN instead of T2FN | T2FN · CMU-MOSEI random drop, medium (p=0.5) | ACC-2: 0.7382 -> 0.7367 | No clear effect |
| use TPFN instead of T2FN in parameter count (random drop) | T2FN · CMU-MOSI random drop | Params: 19,737 -> 19,488 | No clear effect |
| use TPFN instead of T2FN in parameter count (structured drop) | T2FN · CMU-MOSI structured drop | Params: 19,737 -> 7,344 | Improved |
Closest papers by meaning
- A Multi-Focus-Driven Multi-Branch Network for Robust Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.88)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.87)
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.86)
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.86)
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.86)
- Towards Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2024 · 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.
