AI Paper Atlas

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

Sample-specific Modality Diagnosis and Cross-modal Enhancement for Incomplete Multimodal Representations

Junsong Chen, Jiyuan Liu, Suyuan Liu, Wei Zhang, Ao Li, En Zhu, Xinwang Liu

AAAI 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 DMFD on the visual modality (besides audio) (ablation)SMCIR · CMU-MOSIMAE: 0.709 -> 0.696Improved
add DMFD on the audio modality (besides visual) (ablation)SMCIR · CMU-MOSIMAE: 0.726 -> 0.696Improved
add DMFD on the audio modality (besides visual) (ablation)SMCIR · CMU-MOSEIMAE: 0.539 -> 0.523Improved
add mutual information and similarity to entropy indicator (ablation)DMFD · CMU-MOSEIMAE: 0.529 -> 0.523Improved
add entropy to mutual information + similarity (ablation)DMFD · CMU-MOSEIMAE: 0.528 -> 0.523Improved
add mutual information to entropy (ablation)DMFD · CMU-MOSEIF1 (neg/non-neg): 83.95 -> 83.42Hurt
add CMCG module (ablation)SMCIR · CMU-MOSIMAEImproved
use MSSE alone without other modules (ablation)SMCIR · CMU-MOSIMAEHurt
use SMCIR instead of GCNet under missing modalitiesSMCIR · CMU-MOSIF1 avg: 82.14 -> 83.57Improved
use SMCIR instead of GCNet under missing modalitiesSMCIR · CMU-MOSEIF1 avg: 82.58 -> 84.87Improved
use SMCIR instead of SMIL with all modalitiesSMCIR · CMU-MOSEIF1 {L,V,A}: 81.56 -> 85.78Improved
use SMCIR instead of EMT with full modalitiesSMCIR · CMU-MOSEIMAE: 0.527 -> 0.523Improved

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