TY - GEN
T1 - FusedVision
T2 - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
AU - Dawoud, Khaled
AU - Zaheer, Muhammad Zaigham
AU - Khan, Mustaqeem
AU - Nandakumar, Karthik
AU - Saddik, Abdulmotaleb El
AU - Khan, Muhammad Haris
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - Object-centric approaches have gained attention as effective one-class classification methods for detecting anomalies in videos. These approaches rely on using an object detector to isolate all objects in the frames and subsequently leveraging either the objects themselves or their interactions to train a learning system. In this study, we put forth a novel perspective towards anomaly detection by proposing a branched network architecture that employs both an object detector and a normalcy learning model, working together in tandem to more effectively identify anomalies within the data. Through extensive experimentation, we analyze the optimal fusion mechanism as well as anomaly scoring proposed in our branched approach. Our approach is more practical towards realworld applications of anomaly detection where infusion of the knowledge about anticipated anomalies may result in better performance while maintaining a baseline performance nonetheless. To evaluate the general applicability of our approach, we integrate it with multiple existing recent anomaly detection methods and assess its efficacy on three widely used anomaly detection datasets: ShanghaiTech, Avenue, and Ped2. Our proposed approach noticeably outperforms existing methods, demonstrating its effectiveness in detecting anomalies across a range of contexts. The implementation of our method is available at https://github.com/kdawoud91/FusedVision.
AB - Object-centric approaches have gained attention as effective one-class classification methods for detecting anomalies in videos. These approaches rely on using an object detector to isolate all objects in the frames and subsequently leveraging either the objects themselves or their interactions to train a learning system. In this study, we put forth a novel perspective towards anomaly detection by proposing a branched network architecture that employs both an object detector and a normalcy learning model, working together in tandem to more effectively identify anomalies within the data. Through extensive experimentation, we analyze the optimal fusion mechanism as well as anomaly scoring proposed in our branched approach. Our approach is more practical towards realworld applications of anomaly detection where infusion of the knowledge about anticipated anomalies may result in better performance while maintaining a baseline performance nonetheless. To evaluate the general applicability of our approach, we integrate it with multiple existing recent anomaly detection methods and assess its efficacy on three widely used anomaly detection datasets: ShanghaiTech, Avenue, and Ped2. Our proposed approach noticeably outperforms existing methods, demonstrating its effectiveness in detecting anomalies across a range of contexts. The implementation of our method is available at https://github.com/kdawoud91/FusedVision.
KW - anomaly detection in surveillance videos
KW - anomaly in videos
UR - https://www.scopus.com/pages/publications/105017855387
UR - https://www.scopus.com/pages/publications/105017855387#tab=citedBy
U2 - 10.1109/CVPRW67362.2025.00388
DO - 10.1109/CVPRW67362.2025.00388
M3 - Conference contribution
AN - SCOPUS:105017855387
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 4036
EP - 4046
BT - Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
PB - IEEE Computer Society
Y2 - 11 June 2025 through 12 June 2025
ER -