Deyu Zeng — accepted AI-conference papers

2025

HyperTrans: Efficient Hypergraph-Driven Cross-Domain Pattern Transfer in Image Anomaly Detection

Tengyu Zhang, Deyu Zeng, Baoqiang Li, Wei Wang, Wei Liu, Zongze Wu

IJCAI 2025

Anomaly detection plays a pivotal role in industrial quality assurance processes, with cross-domain problems, exemplified by the model upgrade from RGB to 3D, being prevalent in real-world scenarios yet remaining systematically underexplored. To address the severe challenges posed by the extreme lac

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Multi-view Subspace Classification: A Hierarchical Contrastive Approach and Low-rank Latent Representation

Deyu Zeng, Tengyu Zhang, Zongze Wu, Wei Liu, Chris Ding

ICASSP 2025accepted

Effective multi-view subspace learning is crucial for enhancing classification performance on multi-view data. In this paper, we propose CMvLSCN, a novel end-to-end framework addressing multi-view classification at view, sample, and subspace levels. The key innovations are: Strengthening inter-view…

Cited by 0 Source ↗Scholar ↗