activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Cognition-Inspired Dual-Stream Semantic Enhancement for Vision-Based Dynamic Emotion Modeling

Huanzhen Wang, Ziheng Zhou, Zeng Tao +5

The human brain constructs emotional percepts not by processing facial expressions in isolation, but through a dynamic, hierarchical integration of sensory input with semantic and…

cs.CV2025

Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory

Yuxuan Lin, Hanjing Yan, Xuan Tong +6

Few-shot multimodal industrial anomaly detection is a critical yet underexplored task, offering the ability to quickly adapt to complex industrial scenarios. In few-shot settings,…

cs.CV2025

Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection

Xuan Tong, Yang Chang, Qing Zhao +9

Anomaly detection is critical in industrial manufacturing for ensuring product quality and improving efficiency in automated processes. The scarcity of anomalous samples limits tra…

cs.CV2024

A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Image Anomaly Detection

Yuxuan Lin, Yang Chang, Xuan Tong +8

In the advancement of industrial informatization, unsupervised anomaly detection technology effectively overcomes the scarcity of abnormal samples and significantly enhances the au…

cs.CV2024

Suppressing Uncertainties in Degradation Estimation for Blind Super-Resolution

Junxiong Lin, Zeng Tao, Xuan Tong +10

The problem of blind image super-resolution aims to recover high-resolution (HR) images from low-resolution (LR) images with unknown degradation modes. Most existing methods model…

cs.CV2024

Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution

Junxiong Lin, Yan Wang, Zeng Tao +10

Pre-trained diffusion models utilized for image generation encapsulate a substantial reservoir of a priori knowledge pertaining to intricate textures. Harnessing the potential of l…