AI Paper Atlas

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

CMAD: Correlation-Aware and Modalities-Aware Distillation for Multimodal Sentiment Analysis with Missing Modalities

Yan Zhuang, Minhao Liu, Wei Bai, Yanru Zhang, Xiaoyue Zhang, Jiawen Deng, Fuji Ren

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 3 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 CAFD (correlation-aware feature distillation) (ablation)CMAD · MOSEIavg accuracy/F1: 76.2/75.5 -> 77.0/76.4Improved
add CAFD (ablation)CMAD · IEMOCAPavg accuracy/F1: 78.8/76.8 -> 79.2/77.8Improved
add MAR (modality-aware regularization weights) (ablation)CMAD · MOSEIavg accuracy/F1: 75.5/75.5 -> 77.0/76.4Improved
add MAR (ablation)CMAD · IEMOCAPavg accuracy/F1: 78.9/76.4 -> 79.2/77.8Improved
eliminate sample difficulty when computing modality weights (CMAD vs CMADt)CMAD · MOSEIavg F1: 75.2 -> 76.4Improved
eliminate sample difficulty (CMADw vs MMANet, both focus on hard combinations)CMADw · MOSEIavg F1: 73.2 -> 75.6Improved
use CMAD instead of second-best UMDFCMAD · CHERMAavg improvement: 1.4Improved
combine feature and correlation consistency instead of teacher-teacher to student-student transfer (ablation)CAFD · MOSEIavg accuracy/F1: 76.23/75.43 -> 77.03/76.39Improved
combine feature and correlation consistency instead of teacher-teacher to student-student transfer (ablation)CAFD · IEMOCAPavg accuracy/F1: 77.78/76.39 -> 79.23/77.84Improved
CMAD vs baselines on MUStARD and UR-FUNNYCMAD · MUStARDavg improvement: 1.9%Improved
CMAD vs baselines on UR-FUNNYCMAD · UR-FUNNYavg improvement: 0.5%Improved

Later papers that compared with this method

1 later accepted paper reports CMA-D as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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

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