activity
20232026
collaborators

6 papers

cs.CV2026

Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling

Xuhai Chen, Zhi Cen, Huaijin Pi +3

Generating realistic reactive motions, in which one person reacts to the fixed motions of others, is challenging due to strict interaction constraints and a limited feasible soluti…

cs.CV2024

Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection

Yuanpeng Tu, Boshen Zhang, Liang Liu +6

Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples. Recently, numerous 2D anomaly detection…

cs.CV2023

DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection

Haoyang He, Jiangning Zhang, Hongxu Chen +6

Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection. The exceptional image reconstruction capabilities of recently popular diffusion models have…

cs.CV2023

Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection

Jiangning Zhang, Xuhai Chen, Yabiao Wang +5

This work studies a challenging and practical issue known as multi-class unsupervised anomaly detection (MUAD). This problem requires only normal images for training while simultan…

cs.CV2023

GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection

Jiangning Zhang, Haoyang He, Xuhai Chen +5

Large Multimodal Model (LMM) GPT-4V(ision) endows GPT-4 with visual grounding capabilities, making it possible to handle certain tasks through the Visual Question Answering (VQA) p…

cs.CV2023

CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection

Xuhai Chen, Jiangning Zhang, Guanzhong Tian +5

This paper considers zero-shot Anomaly Detection (AD), performing AD without reference images of the test objects. We propose a framework called CLIP-AD to leverage the zero-shot c…