AI Paper Atlas

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

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add dual-dimensional attention (ablation)CL-DMDF · MM-IMDBMicro-F1: 63.21 -> 63.25No clear effect
add dual-dimensional attention (ablation)CL-DMDF · MM-IMDBMacro-F1: 53.25 -> 53.28No clear effect
add entity-centroid contrastive learning (ablation)CL-DMDF without attention · MM-IMDBMicro-F1: 62.56 -> 63.21Improved
add entity-centroid contrastive learning (ablation)CL-DMDF without attention · MM-IMDBMacro-F1: 52.45 -> 53.25Improved
replace static fusion with adaptive fusion (ablation)CL-DMDF without attention and contrastive · MM-IMDBMicro-F1: 59.87 -> 62.56Improved
replace static fusion with adaptive fusion (ablation)CL-DMDF without attention and contrastive · MM-IMDBMacro-F1: 50.41 -> 52.45Improved
replace C-GMVAE contrastive module with entity-centroid contrastive learning (ablation)CL-DMDF · MM-IMDBMicro-F1: 63.03 -> 63.25Improved
replace MulCon contrastive module with entity-centroid contrastive learning (ablation)CL-DMDF · MM-IMDBMicro-F1: 62.14 -> 63.25Improved
replace DynMM with CL-DMDFfusion model · MM-IMDBMicro-F1: 60.35 -> 63.25Improved
replace CEN with CL-DMDFfusion model · NYU Depth V2MIoU: 51.1 -> 52.3Improved
replace CM-BERT with CL-DMDFfusion model · CMU-MOSEIAcc: 84.5 -> 85.4Improved
replace CM-BERT with CL-DMDFfusion model · CMU-MOSEIMAE: 0.729 -> 0.737Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy