AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

DHCM-CACL: Dynamic Hierarchical Cross-modal Mamba with Confidence-Adaptive Contrastive Learning for Multimodal Emotion Recognition

Baiqiang Wu, Yang Li

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 1 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
fuse facial expressions with EEG instead of EEG only (ablation)DHCM-CACL · DEAP subject-independent valenceaccuracy (%): 66.82 -> 72.89Improved
use DHCM instead of a standard transformer (ablation)DHCM-CACL · DEAP subject-independent valenceaccuracy (%): 67.15 -> 72.89Improved
use CACL instead of standard contrastive learning (ablation)DHCM-CACL · DEAP subject-independent valenceaccuracy (%): 69.82 -> 72.89Improved
use evidence layer instead of softmax classifier (ablation)DHCM-CACL · DEAP subject-independent valenceaccuracy (%): 71.05 -> 72.89Improved
add self-supervised pre-training (ablation)DHCM-CACL · DEAP subject-independent valenceaccuracy (%): 64.27 -> 72.89Improved
use dynamic state matrix instead of static fixed At (ablation)DHCM · DEAP subject-independent valenceaccuracy (%): 70.15 -> 72.89Improved
add forget gate (ablation)DHCM · DEAP subject-independent valenceaccuracy (%): 69.24 -> 72.89Improved
learned state matrices instead of random state matrices (ablation)DHCM · DEAP subject-independent valenceaccuracy (%): 67.58 -> 72.89Improved
set DHCM hierarchical levels L to 3 (ablation)DHCM · DEAP valence and arousalaccuracyImproved
use the method with only 20% annotations for fine-tuningDHCM-CACL vs EEG2Rep · DEAP valence subject-independentaccuracy (%): 61.31 -> 65.72Improved
DHCM-CACL vs PhysioSync in subject-dependent valenceDHCM-CACL · DEAP subject-dependent valenceaccuracy (%): 96.25 -> 95.21Hurt
DHCM-CACL vs EEG2Rep in subject-independent valenceDHCM-CACL · MAHNOB-HCI subject-independent valenceaccuracy (%): 75.52 -> 75.12Hurt

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