CoPA is proposed, an object-agnostic contextual prompt learning framework that keeps the normal prompt branch static and dynamically adapts only the abnormal branch, producing anomaly semantics conditioned on image-specific local evidence while preserving category independence.
Yu-Hao Zhao, Jun-Jian Huang, Hang-Jun Che et al.· Proceedings of the 34th ACM...· 1 citation
Zero-shot anomaly detection (ZSAD) aims to identify anomalous images and segment anomalous regions in unseen target domains without access to target-domain training data. Although CLIP provides strong zero-shot transferability, its pretraining primarily focuses on aligning images with object-level textual semantics, wh...
Yu-Hao Zhao, Jun-Jian Huang, Hang-Jun Che et al.· Proceedings of the 34th ACM...· 0 citations
Numerical simulations demonstrate that the proposed scheme achieves bipartite fixed-time consensus within approximately 0.4 s under event-triggered communication (0.26 s without ETM), while the average communication saving rate is 44.67%, validating the effectiveness of the theoretical results.
Wei Zhang, Yi-Yue Zhang, Jun-Jian Huang et al.· ISA transactions· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.