AI Paper Atlas

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

A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identification

Yunpeng Gong, Yongjie Hou, Jiangming Shi, Kim Long Diep, Min Jiang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 5 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 alignment augmentation (AA) (ablation)KTCAA · Market-Sketch-1KRank-1: 12.1 -> 18.0Improved
add KTC adversarial perturbation (ablation)KTCAA · Market-Sketch-1KRank-1: 18.0 -> 23.2Improved
add alignment loss Lalign (ablation)KTCAA · Market-Sketch-1KRank-1: 23.2 -> 24.9Improved
add AA+KTC components on PKU-Sketch (ablation)KTCAA · PKU-SketchRank-1: 68.2 -> 93.6Improved
use KTCAA with 40% training data instead of UNIReIDKTCAA · PKU-Sketch (40% data)Rank-1: 44.0 ± 0.7 -> 68.2 ± 0.3Improved
add KTCAA to SS-reIDSS-reID · Market-Sketch-1KRank-1: 16.9 -> 25.1Improved
CLIP-Align alignment module vs noneSS-reID · Market-Sketch-1KRank-1: 16.9 -> 21.4Improved
use local instead of global sketch augmentation (ablation)KTCAA · Market-Sketch-1KgeneralizationImproved

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