Unsupervised Video Anomaly Detection Based on Similarity with Predefined Text Descriptions.

Kim, Jaehyun; Yoon, Seongwook; Choi, Taehyeon; Sull, Sanghoon

Kim, Jaehyun; Yoon, Seongwook; Choi, Taehyeon; Sull, Sanghoon.

Affiliation

Kim J; School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea.
Yoon S; School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea.
Choi T; School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea.
Sull S; School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea.

Sensors (Basel) ; 23(14)2023 Jul 09.

Article in En | MEDLINE | ID: mdl-37514551

Key words

CLIP; abnormal video; embedding space; fine-tuning of pre-trained models; large language models; large vision and language models; similarity measure; text descriptions; unsupervised video anomaly detection

Fulltext

XML

PubMed Links

Search on Google

Full text: 1 Collection: 01-internacional Database: MEDLINE Type of study: Diagnostic_studies / Prognostic_studies Language: En Journal: Sensors (Basel) Year: 2023 Type: Article

Fulltext

XML

PubMed Links

Search on Google