5 papers
AnomalyCraft-700K: Component-Level Controllable and Verifiable Synthetic Anomalies for Fine-Grained Video Anomaly Understanding
Yuzhou Long, Haodong Zhang, Yunpeng Yang +2
Progress in video anomaly understanding (VAU) has long been limited by inherent deficiencies of real-world anomaly videos, which are hard to collect and offer little control over t…
Rethinking Auxiliary Modalities in Multimodal Zero-shot Anomaly Detection: From Semantic Fusion to Conditional Modulation
Peng Wu, Xin Ge, Yujia Sun +1
Recent foundation model-based methods have endowed RGB images with strong zero-shot anomaly detection (ZSAD) through vision-language pretraining. However, RGB observations alone re…
AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection
Peng Wu, Wanshun Su, Guansong Pang +4
With the increasing adoption of video anomaly detection in intelligent surveillance domains, conventional visual-based detection approaches often struggle with information insuffic…
SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Model
Zongcan Ding, Haodong Zhang, Peng Wu +4
Video anomaly detection (VAD) aims to identify unexpected events in videos and has wide applications in safety-critical domains. While semi-supervised methods trained on only norma…
AssistPDA: An Online Video Surveillance Assistant for Video Anomaly Prediction, Detection, and Analysis
Zhiwei Yang, Chen Gao, Jing Liu +3
The rapid advancements in large language models (LLMs) have spurred growing interest in LLM-based video anomaly detection (VAD). However, existing approaches predominantly focus on…