Research map / Vision-language and multimodal / Cross-modal learning
Multiform Attack for Transferable Cross-Modal Person Re-Identification
Yunpeng Gong, Can Yang, Qingyuan Zeng, Dejun Xu, Zhiming Luo, Zhenzhong Wang, Min JIANG
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a multiform adversarial attack for cross-modal person re-identification aimed at improving perturbation transferability across modality pairs and domain shifts.
Problem
Adversarial attacks on cross-modal person ReID overfit to the source modality pair, so learned perturbations do not transfer well under heterogeneous domain shifts.
Approach
Argues that source-pair overfitting stems from perturbations becoming entangled with the feature covariance and alignment patterns of the source modality pair, and addresses this with a multiform attack design to reduce that entanglement.
Closest papers by meaning
- Cross-Modality Perturbation Synergy Attack for Person Re-identification (NeurIPS 2024 · similarity 0.89)
- R$^2$TUA: Reconstruction-residual Based Targeted and Untargeted Attack Against Text-Image Person Re-Identification (CVPR 2026 · similarity 0.88)
- Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer (CVPR 2020 · similarity 0.88)
- Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-Identification (CVPR 2020 · similarity 0.88)
- Heterogeneous Test-Time Training for Multi-Modal Person Re-identification (AAAI 2024 · similarity 0.87)
- Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.85)
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.
