AI Paper Atlas

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

FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification

Xuanhao Qi, Tom H. Luan, Yukang Zhang, Jinkai Zheng, su zhou, Shuwei Li, Lei Tan

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modal object re-identification · 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 Cross-Modal Alignment Module (CAM) (ablation)shared ViT baseline · RGBNT201mAP: 76.0 -> 77.2Improved
add Cross-Modal Alignment Module (CAM) (ablation)shared ViT baseline · RGBNT201Rank-1: 77.8 -> 80.4Improved
add Spectral Decomposition Module (SDM) (ablation)shared ViT baseline · RGBNT201mAP: 76.0 -> 79.7Improved
add Spectral Decomposition Module (SDM) (ablation)shared ViT baseline · RGBNT201Rank-1: 77.8 -> 82.1Improved
add CAM on top of SDM (ablation)SDM model · RGBNT201mAP: 79.7 -> 80.8Improved
use all three frequency bands (0.3, 0.3, 0.3) instead of low band only (ablation)SDM · RGBNT201mAP: 75.4 -> 79.7Improved
use mid band only instead of low band only (ablation)SDM · RGBNT201mAP: 75.4 -> 72.2Hurt
add frequency consistency loss with lambda_freq=0.1 (ablation)FUSE · RGBNT201mAP: 80.8 -> 81.4Improved
add frequency consistency loss with lambda_freq=0.1 (ablation)FUSE · RGBNT201Rank-1: 84.1 -> 86.1Improved
increase lambda_freq from 0.1 to 0.3 (ablation)FUSE · RGBNT201mAP: 81.4 -> 79.9Hurt
use kernel size 7,7,7 instead of 3,3,3 (ablation)FUSE · RGBNT201mAP: 81.4 -> 79.3Hurt
use mixed kernel sizes 3,5,7 instead of 3,3,3 (ablation)FUSE · RGBNT201mAP: 81.4 -> 78.8Hurt

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