AI Paper Atlas

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

Recovering Coherent Affective Patterns: Addressing Modality Missing in Multimodal Sentiment Analysis

Huiting Huang, Tieliang Gong, Kai He, Wen Wen, Weizhan Zhang, Mengling Feng

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 4 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 H-CAG generator (ablation)RECAP · CH-SIMSF1: 71.52 -> 76.06Improved
add H-CAG generator (ablation)RECAP · MOSIAcc-7: 34.11 -> 35.07Improved
add FID module (ablation)RECAP · CH-SIMSF1: 74.33 -> 76.06Improved
add FID module (ablation)RECAP · MOSIAcc-7: 33.67 -> 35.07Improved
add FID shared branch (ablation)RECAP · CH-SIMSF1: 72.37 -> 76.06Improved
add FID unique branch (ablation)RECAP · CH-SIMSF1: 71.79 -> 76.06Improved
add FID unique branch (ablation)RECAP · MOSIAcc-7: 33.67 -> 35.07Improved
add language-visual FID pair (ablation)RECAP · CH-SIMSF1: 72.14 -> 76.06Improved
add language-acoustic FID pair (ablation)RECAP · CH-SIMSF1: 71.64 -> 76.06Improved
add acoustic-visual FID pair (ablation)RECAP · MOSIAcc-7: 35.13 -> 35.07No clear effect
add reconstructor (ablation)RECAP · CH-SIMSF1: 74.13 -> 76.06Improved
add MIR fusion (ablation)RECAP · CH-SIMSF1: 74.36 -> 76.06Improved

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