AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

CKDA: Cross-modality Knowledge Disentanglement and Alignment for Visible-Infrared Lifelong Person Re-identification

Zhenyu Cui, Jiahuan Zhou, Yuxin Peng

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 1 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 Modality-Common Prompting (ablation)Base · VI-LReID averagemAP: 31.8 -> 33.4Improved
add Modality-Specific Prompting on top of MCP (ablation)Base + MCP · VI-LReID averagemAP: 33.4 -> 34.6Improved
add Cross-modality Knowledge Aligning (ablation)Base · VI-LReID averagemAP: 31.8 -> 34.9Improved
add MCP and MSP to CKA (ablation)Base + CKA · VI-LReID averagemAP: 34.9 -> 36.3Improved
CKDA vs best non-replay baseline LSTKC (ViT)CKDA · VI-LReID averagemAP: 30.6 -> 36.3Improved
CKDA vs replay method PP-IPGCKDA · VI-LReID averagemAP: 42.8 vs 36.3Hurt
CKDA vs LSTKC on LLCMCKDA · LLCMRank-1: 35.1 vs 31.5Hurt
CKDA vs non-replay baselines on forgettingCKDA · VI-LReIDAF(mAP): 8.5 -> 5.1Improved

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