AI Paper Atlas

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

PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment Analysis

Kang He, Boyu Chen, Yuzhe Ding, Fei Li, Chong Teng, Donghong Ji

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 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 Shapley-based gradient modulation (SGM) (ablation)PaSE · CMU-MOSIAcc-2 (neg/pos): 85.47 -> 88.32Improved
add prototype-guided calibration (PCL) (ablation)PaSE · CMU-MOSIAcc-2 (neg/pos): 87.25 -> 88.32Improved
add cross-modal entropic OT alignment (CAL) (ablation)PaSE · CMU-MOSIAcc-2 (neg/pos): 86.80 -> 88.32Improved
add Shapley-based gradient modulation (ablation)PaSE · IEMOCAPweighted accuracy: 76.80 -> 80.47Improved
use prototype-gated fusion instead of sum (ablation)PaSE · IEMOCAPweighted accuracy: 78.43 -> 80.47Improved
use prototype-gated fusion instead of concatenation or attention (ablation)PaSE · IEMOCAPweighted accuracy: 79.16 (Con), 78.75 (Att) -> 80.47Improved
add audio and visual modalities to text (ablation)PaSE · CMU-MOSIAcc-2 (neg/pos): 84.70 -> 88.32Improved
add SGM to reduce text dominance (ablation)PaSE · MOSI, MOSEI, IEMOCAP contributionsmodality contribution balanceImproved
use general LLMs/MLLMs instead of specialised PaSEmultimodal sentiment analysis · IEMOCAPweighted accuracy: 80.47 -> 46.33 (GPT-4o-mini)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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