AI Paper Atlas

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

Rethinking Attention Reallocation for Multimodal Emotion Recognition

Yazhe Lyu, Yixiong Zou, Jinghan Hu, Yuhua Li, Ruixuan Li

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 0 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 shallow layer guidance (ablation)AffectGPT baseline · MER-UniBench (video+audio+text)MER-UniBench avg: 74.34 -> 76.48Improved
add residual refinement on top of shallow guidance (ablation)AffectGPT baseline · MER-UniBench (video+audio+text)MER-UniBench avg: 76.48 -> 78.08Improved
replace residual injection with shallow layer replacement (ablation)Ours · MER-UniBench (video+audio+text)MER-UniBench avg: 78.08 -> 77.68Hurt
replace shallow prior with uniform prior injection (ablation)Ours · MER-UniBench (video+audio+text)MER-UniBench avg: 78.08 -> 77.27Hurt
aggregate multiple shallow layers instead of single selected layer (ablation)Ours · MER-UniBench (video+audio+text)MER-UniBench avg: 78.08 -> 76.01Hurt
reallocate attention from generated to modality tokensAffectGPT · MER2023 two-modalityscore: 78.17 -> 79.04Improved
reallocate attention from generated to modality tokensAffectGPT · MER2023 three-modalityscore: 76.52 -> 76.52Hurt
reallocate attention from modality to generated tokensAffectGPT · MER2023 three-modalityscore: 76.52 -> 80.53Improved
add length-constrained decoding to baselineAffectGPT · MER-UniBench (video+audio+text)MER-UniBench avg: 74.34 -> 71.67Hurt
add DeCo-style layer-guided logit refinementAffectGPT · MER-UniBench (video+audio+text)MER-UniBench avg: 74.34 -> 74.33No clear effect
add our method without pre-fusion module (ablation)AffectGPT w/o fused token · MER-UniBench w/o fused tokenMER-UniBench avg: 73.47 -> 74.81Improved
add DoLAAffectGPT · MER-UniBench (video+audio+text)MER-UniBench avg: 74.34 -> 68.38Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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