Mingjv Peng

Mingjv Peng

Auto-generated profile, based on publicly available information

Mingjv Peng

Northeastern University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 December 2022 in Transactions on Emerging Telecommunications Technologies
Verified
Journal Article
Closed access
XSXin Song
Xin Song
JZJiahui Zhu
Jiahui Zhu
RZRunfeng Zhang
Runfeng Zhang
MPMingjv Peng
Mingjv Peng
SXSiyang Xu
Siyang Xu

16 July 2026 in Measurement Science and Technology
Verified
Journal Article
Closed access
MPMingjv Peng
Mingjv Peng
XSXin Song
Xin Song
QZQiyue Zuo
Qiyue Zuo
SXSiyang Xu
Siyang Xu
YYYang Yue
Yang Yue
Zero-shot anomaly detection (ZSAD) aims to identify anomalies without requiring any target-domain data, making it important for ensuring product quality in industrial manufacturing. Recently, Contrastive Vision-Language Pretraining models have attracted widespread attention in ZSAD. However, existing single-level text prompts need to trade off between classification and segmentation, which abnormal characteristics at different levels are difficult to capture. Meanwhile, general contrastive language-image pre-training (CLIP) models focus on global visual semantics, whereas the anomaly detection task requires fine-grained local visual semantics. To address these issues, we propose a novel ZSAD framework to enhance the semantic discriminability, namely hyperbolic prompt learning (HPL)-CLIP, which fine-tunes text prompts to match multi-level visual features in hyperbolic space. Specifically, we first propose the hyperbolic prompt learning mechanism to learn generic states of normality and abnormality. These generic states are aligned with global and local visual features to capture anomalies. Then, the adaptive pixel-alignment adapter module is designed to extract fine-grained local image details. Finally, we derive a hierarchical enhanced hinge loss to sharpen the boundary between normal and abnormal pixels while encouraging a more compact score distribution for pixels under the same state. Experiments indicate that HPL-CLIP accurately detects anomalous images and localizes anomalous regions. For example, HPL-CLIP outperforms AnomalyCLIP on MVTec AD by 2.1%/0.8% at the image-level AUROC/AP and 0.3%/4.9% at the pixel-level AUROC/PRO, respectively.