Research map / Vision-language and multimodal / Cross-modal learning
CL-DMDF: Dynamic Multimodal Data Fusion Model Based on Contrastive Learning
Dong Li, Lingling Zhang, Binghao Han, Linlin Ding, Yue Kou
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 dual-dimensional attention (ablation) | CL-DMDF · MM-IMDB | Micro-F1: 63.21 -> 63.25 | No clear effect |
| add dual-dimensional attention (ablation) | CL-DMDF · MM-IMDB | Macro-F1: 53.25 -> 53.28 | No clear effect |
| add entity-centroid contrastive learning (ablation) | CL-DMDF without attention · MM-IMDB | Micro-F1: 62.56 -> 63.21 | Improved |
| add entity-centroid contrastive learning (ablation) | CL-DMDF without attention · MM-IMDB | Macro-F1: 52.45 -> 53.25 | Improved |
| replace static fusion with adaptive fusion (ablation) | CL-DMDF without attention and contrastive · MM-IMDB | Micro-F1: 59.87 -> 62.56 | Improved |
| replace static fusion with adaptive fusion (ablation) | CL-DMDF without attention and contrastive · MM-IMDB | Macro-F1: 50.41 -> 52.45 | Improved |
| replace C-GMVAE contrastive module with entity-centroid contrastive learning (ablation) | CL-DMDF · MM-IMDB | Micro-F1: 63.03 -> 63.25 | Improved |
| replace MulCon contrastive module with entity-centroid contrastive learning (ablation) | CL-DMDF · MM-IMDB | Micro-F1: 62.14 -> 63.25 | Improved |
| replace DynMM with CL-DMDF | fusion model · MM-IMDB | Micro-F1: 60.35 -> 63.25 | Improved |
| replace CEN with CL-DMDF | fusion model · NYU Depth V2 | MIoU: 51.1 -> 52.3 | Improved |
| replace CM-BERT with CL-DMDF | fusion model · CMU-MOSEI | Acc: 84.5 -> 85.4 | Improved |
| replace CM-BERT with CL-DMDF | fusion model · CMU-MOSEI | MAE: 0.729 -> 0.737 | Hurt |
Closest papers by meaning
- Adaptive Multimodal Fusion: Dynamic Attention Allocation for Intent Recognition (AAAI 2025 · similarity 0.88)
- Facilitating Multimodal Classification via Dynamically Learning Modality Gap (NeurIPS 2024 · similarity 0.88)
- Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process (NeurIPS 2025 · similarity 0.88)
- Continual Multimodal Contrastive Learning (NeurIPS 2025 · similarity 0.87)
- What to align in multimodal contrastive learning? (ICLR 2025 · similarity 0.86)
- MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning (NeurIPS 2025 · 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.
