{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-temporal-regularity-in-video","title":"Learning Temporal Regularity in Video Sequences","arxiv_id":"1604.04574","date":"2016-04-15","proceeding":"CVPR 2016 6","authors":["Mahmudul Hasan","Jonghyun Choi","Jan Neumann","Amit K. Roy-Chowdhury","Larry S. Davis"],"abstract":"Perceiving meaningful activities in a long video sequence is a challenging\nproblem due to ambiguous definition of 'meaningfulness' as well as clutters in\nthe scene. We approach this problem by learning a generative model for regular\nmotion patterns, termed as regularity, using multiple sources with very limited\nsupervision. Specifically, we propose two methods that are built upon the\nautoencoders for their ability to work with little to no supervision. We first\nleverage the conventional handcrafted spatio-temporal local features and learn\na fully connected autoencoder on them. Second, we build a fully convolutional\nfeed-forward autoencoder to learn both the local features and the classifiers\nas an end-to-end learning framework. Our model can capture the regularities\nfrom multiple datasets. We evaluate our methods in both qualitative and\nquantitative ways - showing the learned regularity of videos in various aspects\nand demonstrating competitive performance on anomaly detection datasets as an\napplication.","url_abs":"http://arxiv.org/abs/1604.04574v1","url_pdf":"http://arxiv.org/pdf/1604.04574v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-temporal-regularity-in-video","repo_url":"https://github.com/alexisbdr/warehouse-anomaly","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-temporal-regularity-in-video","repo_url":"https://github.com/tnybny/Frame-level-anomalies-in-videos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"abnormal-event-detection-in-video","task_name":"Abnormal Event Detection In Video"},{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"semi-supervised-anomaly-detection","task_name":"Semi-supervised Anomaly Detection"},{"task_slug":"video-anomaly-detection","task_name":"Video Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/abnormal-event-detection-in-video-on-ubi","task":"Abnormal Event Detection In Video","dataset":"UBI-Fights","model":"Hasan et al.","rank_in_archive_order":6,"of":6,"metrics":{"AUC":"0.528","Decidability":"0.194","EER":"0.466"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-anomaly-detection-on-ubi","task":"Semi-supervised Anomaly Detection","dataset":"UBI-Fights","model":"Hasan et al.","rank_in_archive_order":7,"of":7,"metrics":{"AUC":"0.528","Decidability":"0.194","EER":"0.466"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-accident-detection-on-a3d","task":"Traffic Accident Detection","dataset":"A3D","model":"Conv-AE","rank_in_archive_order":2,"of":3,"metrics":{"AUC":"49.5"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-accident-detection-on-sa","task":"Traffic Accident Detection","dataset":"SA","model":"Conv-AE","rank_in_archive_order":2,"of":3,"metrics":{"AUC":"50.4"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-hr-avenue","task":"Video Anomaly Detection","dataset":"HR-Avenue","model":"Conv-AE","rank_in_archive_order":9,"of":11,"metrics":{"AUC":"84.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-hr-shanghaitech","task":"Video Anomaly Detection","dataset":"HR-ShanghaiTech","model":"Conv-AE","rank_in_archive_order":14,"of":14,"metrics":{"AUC":"69.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1604.04574","atlas_url":"https://app.syntology.ai/?focus=1604.04574","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}