Open-vocabulary video anomaly detection

• Main Authors: WU, Peng, ZHOU, Xuerong, PANG, Guansong, SUN, Yujia, LIU, Jing, WANG, Peng, ZHANG, Yanning
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Video anomaly detection; Anomalies categorization; Open-vocabulary video anomaly detection; Semantic knowledge injection; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/9761; https://ink.library.smu.edu.sg/context/sis_research/article/10761/viewcontent/2311.07042v3.pdf
• Institution: Singapore Management University

Current video anomaly detection (VAD) approaches with weak supervisions are inherently limited to a closed-set setting and may struggle in open-world applications where there can be anomaly categories in the test data unseen during training. A few recent studies attempt to tackle a more realistic se...