activity
20242026
collaborators

7 papers

cs.CV2026

TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning

Shuangqing Zhang, Lei-Lei Ma, Zhao Wang +5

Visual data is typically a prerequisite for training existing video anomaly detection (VAD) methods. However, obtaining sufficient annotated anomaly data for training is challengin…

cs.CV2026

Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection

Runzhi Deng, Yundi Hu, Yiming Zhong +5

Large Multimodal Models (LMMs) show strong few-shot generalization, but industrial anomaly detection remains difficult because defects are small, input resolution is limited, and t…

cs.CV2026

CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection

Wen Dong, Zhao Wang, Shuangqing Zhang +5

Multimodal Large Language Models (MLLMs) excel in diverse vision tasks, but full-parameter retraining is computationally expensive as real-world knowledge evolves. Existing continu…

cs.CV2025

Foundation Model for Skeleton-Based Human Action Understanding

Hongsong Wang, Wanjiang Weng, Junbo Wang +4

Human action understanding serves as a foundational pillar in the field of intelligent motion perception. Skeletons serve as a modality- and device-agnostic representation for huma…

cs.CV2025

LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection

Weijia Li, Guanglei Chu, Jiong Chen +3

Recent advances in industrial anomaly detection have highlighted the need for deeper logical anomaly analysis, where unexpected relationships among objects, counts, and spatial con…

cs.CV2025

Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection

Fenfang Tao, Guo-Sen Xie, Fang Zhao +1

Few-shot anomaly detection (FSAD) aims to detect unseen anomaly regions with the guidance of very few normal support images from the same class. Existing FSAD methods usually find…