Research map / Vision-language and multimodal / Cross-modal learning
Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalities
Jindi Bao, Jianjun Qian, Mengkai Yan, Jian Yang
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 Progressive Interaction module (ablation) | PRLF · CMU-MOSI (inter-modality missing) | F1: 71.32 -> 77.11 | Improved |
| add Adaptive Modality Reliability Estimator (ablation) | PRLF · CMU-MOSI (inter-modality missing) | F1: 74.96 -> 77.11 | Improved |
| add confidence-based modality importance (CMI) (ablation) | PRLF · CMU-MOSI (inter-modality missing) | F1: 76.12 -> 77.11 | Improved |
| add Fisher information-based modality importance (FIMI) (ablation) | PRLF · CMU-MOSI (inter-modality missing) | F1: 76.09 -> 77.11 | Improved |
| add feature uniformity loss (ablation) | PRLF · CMU-MOSI (inter-modality missing) | F1: 75.73 -> 77.11 | Improved |
| add phase consistency loss (ablation) | PRLF · CMU-MOSI (inter-modality missing) | F1: 76.63 -> 77.11 | Improved |
| add Progressive Interaction module (ablation) | PRLF · CMU-MOSI (full modality {l,a,v}) | F1: 79.33 -> 85.78 | Improved |
| increase iteration step from 1 to 4 (ablation) | PRLF · CMU-MOSI (inter-modality missing) | F1: 72.29 -> 77.11 | Improved |
| increase iteration step from 4 to 5 (ablation) | PRLF · CMU-MOSI (inter-modality missing) | F1: 77.11 -> 75.80 | Hurt |
| increase iteration step from 1 to 4 (ablation) | PRLF · CMU-MOSI (intra-modality missing, p=0.9) | F1: 55.37 -> 58.64 | Improved |
| increase iteration step from 4 to 5 (ablation) | PRLF · CMU-MOSI (intra-modality missing, p=0.9) | F1: 58.64 -> 57.48 | Hurt |
| PRLF vs HRLF | PRLF · CMU-MOSI (inter-modality missing) | F1: 76.74 -> 77.02 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EMOE — EMOE: Modality-Specific Enhanced Dynamic Emotion Experts (CVPR 2025) · better on 7 of 7 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
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.93)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.91)
- Hyper-Modality Enhancement for Multimodal Sentiment Analysis with Missing Modalities (NeurIPS 2025 · 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)
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.
