activity
20242026
most citedSubspace-Guided Feature Reconstruction for Unsupervised Anomaly Localization

1 citations · 1 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV2026

VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment

Zi Wang, Katsuya Hotta, Yawen Zou +4

Few-shot cross-category 3D anomaly detection aims to determine whether an unknown point cloud belongs to a target normal category using only a few normal references. Existing train…

cs.CV20261 cited

Subspace-Guided Feature Reconstruction for Unsupervised Anomaly Localization

Katsuya Hotta, Chao Zhang, Yoshihiro Hagihara +1

Unsupervised anomaly localization aims to identify anomalous regions that deviate from normal sample patterns. Most recent methods perform feature matching or reconstruction for th…

cs.CV2026

DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samples

Zi Wang, Katsuya Hotta, Koichiro Kamide +4

Cross-category anomaly detection for 3D point clouds aims to determine whether an unseen object belongs to a target category using only a few normal examples. Most existing methods…

cs.CV2025

3D Human-Human Interaction Anomaly Detection

Shun Maeda, Chunzhi Gu, Koichiro Kamide +3

Human-centric anomaly detection (AD) has been primarily studied to specify anomalous behaviors in a single person. However, as humans by nature tend to act in a collaborative manne…

cs.CV2025

3DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering

Zi Wang, Katsuya Hotta, Koichiro Kamide +3

High-resolution 3D point clouds are highly effective for detecting subtle structural anomalies in industrial inspection. However, their dense and irregular nature imposes significa…

cs.CV2024

Diverse Code Query Learning for Speech-Driven Facial Animation

Chunzhi Gu, Shigeru Kuriyama, Katsuya Hotta

Speech-driven facial animation aims to synthesize lip-synchronized 3D talking faces following the given speech signal. Prior methods to this task mostly focus on pursuing realism w…