{"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/regularity-learning-via-explicit-distribution","title":"Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection","arxiv_id":"2112.03649","date":"2021-12-07","proceeding":null,"authors":["Shoubin Yu","Zhongyin Zhao","Haoshu Fang","Andong Deng","Haisheng Su","Dongliang Wang","Weihao Gan","Cewu Lu","Wei Wu"],"abstract":"Anomaly detection in surveillance videos is challenging and important for ensuring public security. Different from pixel-based anomaly detection methods, pose-based methods utilize highly-structured skeleton data, which decreases the computational burden and also avoids the negative impact of background noise. However, unlike pixel-based methods, which could directly exploit explicit motion features such as optical flow, pose-based methods suffer from the lack of alternative dynamic representation. In this paper, a novel Motion Embedder (ME) is proposed to provide a pose motion representation from the probability perspective. Furthermore, a novel task-specific Spatial-Temporal Transformer (STT) is deployed for self-supervised pose sequence reconstruction. These two modules are then integrated into a unified framework for pose regularity learning, which is referred to as Motion Prior Regularity Learner (MoPRL). MoPRL achieves the state-of-the-art performance by an average improvement of 4.7% AUC on several challenging datasets. Extensive experiments validate the versatility of each proposed module.","url_abs":"https://arxiv.org/abs/2112.03649v2","url_pdf":"https://arxiv.org/pdf/2112.03649v2.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":"regularity-learning-via-explicit-distribution","repo_url":"https://github.com/Yui010206/MoPRL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"anomaly-detection-in-surveillance-videos","task_name":"Anomaly Detection In Surveillance Videos"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"video-anomaly-detection","task_name":"Video Anomaly Detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-corridor","task":"Anomaly Detection","dataset":"Corridor","model":"MoPRL","rank_in_archive_order":2,"of":3,"metrics":{"AUC":"71.63"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-shanghaitech","task":"Anomaly Detection","dataset":"ShanghaiTech","model":"MoPRL","rank_in_archive_order":13,"of":31,"metrics":{"AUC":"83.35"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-hr-shanghaitech","task":"Video Anomaly Detection","dataset":"HR-ShanghaiTech","model":"MoPRL","rank_in_archive_order":2,"of":14,"metrics":{"AUC":"84.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.03649","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}