AI Paper Atlas

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

Interest-driven Deep Multi-modal Clustering

Guoliang Zou, Tongji Chen, Sijia Li, Jin Qin, Yangdong Ye, Shizhe Hu

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 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 interest-weighted reconstruction loss (ablation)IDMC · Caltech2MACC: 0.647 -> 0.666Improved
add interest-weighted reconstruction loss (ablation)IDMC · CrosstaskACC: 0.605 -> 0.634Improved
add interest-weighted alignment loss (ablation)IDMC · Caltech2MACC: 0.601 -> 0.666Improved
add interest-weighted alignment loss (ablation)IDMC · CrosstaskACC: 0.478 -> 0.634Improved
add interest-weighted KL clustering loss (ablation)IDMC · Caltech2MACC: 0.596 -> 0.666Improved
add interest-weighted KL clustering loss (ablation)IDMC · CrosstaskACC: 0.563 -> 0.634Improved
add DDC loss (ablation)IDMC · Caltech2MACC: 0.239 -> 0.666Improved
add DDC loss (ablation)IDMC · CrosstaskACC: 0.218 -> 0.634Improved
add DDC loss (ablation)IDMC · MIRFlickrACC: 0.176 -> 0.579Improved
add interest value weighting (ablation)IDMC · Crosstask, Captionsclustering accuracyImproved
use adaptive Bayesian fusion instead of average fusion (ablation)IDMC · Crosstask, Captionsclustering accuracyImproved
add interest-weighted reconstruction loss (ablation)IDMC · CaptionsACC: 0.781 -> 0.800Improved

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