AI Paper Atlas

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

A Text-Routed Sparse Mixture-of-Experts Model with Explanation and Temporal Alignment for Multi-Modal Sentiment Analysis

Dongning Rao, Yunbiao Zeng, Zhihua Jiang, Jujian Lv

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
remove MLLM-generated explanations (ablation)TEXT · MOSEIMAE: 0.569 -> 0.528Improved
replace temporal alignment block with concatenation (ablation)TEXT · MOSEIMAE: 0.580 -> 0.528Improved
use proposed temporal alignment instead of Mamba (ablation)TEXT · MOSEIMAE: 0.562 -> 0.528Improved
use proposed temporal alignment instead of TCA (ablation)TEXT · MOSEIMAE: 0.565 -> 0.528Improved
use text-routed SMoE instead of Transformer (ablation)TEXT · MOSEIMAE: 0.573 -> 0.528Improved
add gate fusion (ablation)TEXT · MOSEIMAE: 0.571 -> 0.528Improved
add explanation alignment instead of linear layer (ablation)TEXT · MOSEIAcc-7: 48.21 -> 52.29Improved
fuse text with audio and video rather than text alone (ablation)TEXT · MOSEIAcc-7: 52.84 -> 52.29No clear effect
TEXT versus KuDA on fine-grained accuracyTEXT · MOSIAcc-7: 47.08 -> 45.92Hurt
TEXT versus strongest baselines on MAETEXT · CH-SIMSMAE: 0.408 -> 0.353Improved

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