AI Paper Atlas

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

Incentive Noise and Structural Prior Infusion for Multi-Modal Object Re-Identification

Weixiang Zhou, Yuhao Wang, Xingguo Xu, Cong Wang, Weizhen Zhou, Zhixun Su, Jinshan Pan

ECCV 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 CASF (ablation)CLIP baseline · RGBNT201mAP: 70.3 -> 76.5Improved
add SPA (ablation)Baseline + CASF · RGBNT201mAP: 76.5 -> 78.6Improved
add SCM (ablation)Baseline + CASF + SPA · RGBNT201mAP: 78.6 -> 80.6Improved
add CASF (ablation)CLIP baseline · MSVR310mAP: 40.4 -> 55.8Improved
add SPA (ablation)Baseline + CASF · MSVR310mAP: 55.8 -> 61.1Improved
add SCM (ablation)Baseline + CASF + SPA · MSVR310mAP: 61.1 -> 65.0Improved
use task-aware pi-noise instead of Gaussian noise (ablation)SCM · RGBNT201mAP: 76.1 -> 80.6Improved
use conditioned pi-noise instead of dropout (ablation)SCM · RGBNT201mAP: 75.7 -> 80.6Improved
use gated cross-attention instead of standard cross-attention (ablation)SCM · RGBNT201mAP: 79.4 -> 80.6Improved
initialize prompts with DINOv3 instead of randomly (ablation)SPA · RGBNT201mAP: 78.0 -> 80.6Improved
use MoE routing instead of linear fusion (ablation)CASF · RGBNT201mAP: 78.5 -> 80.6Improved
feed noise-enhanced global tokens to MoE instead of raw tokens (ablation)CASF · RGBNT201mAP: 78.6 -> 80.6Improved

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