{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/normalizing-flows-for-human-pose-anomaly","title":"Normalizing Flows for Human Pose Anomaly Detection","arxiv_id":"2211.10946","date":"2022-11-20","proceeding":"ICCV 2023 1","authors":["Or Hirschorn","Shai Avidan"],"abstract":"Video anomaly detection is an ill-posed problem because it relies on many parameters such as appearance, pose, camera angle, background, and more. We distill the problem to anomaly detection of human pose, thus decreasing the risk of nuisance parameters such as appearance affecting the result. Focusing on pose alone also has the side benefit of reducing bias against distinct minority groups. Our model works directly on human pose graph sequences and is exceptionally lightweight (~1K parameters), capable of running on any machine able to run the pose estimation with negligible additional resources. We leverage the highly compact pose representation in a normalizing flows framework, which we extend to tackle the unique characteristics of spatio-temporal pose data and show its advantages in this use case. The algorithm is quite general and can handle training data of only normal examples as well as a supervised setting that consists of labeled normal and abnormal examples. We report state-of-the-art results on two anomaly detection benchmarks - the unsupervised ShanghaiTech dataset and the recent supervised UBnormal dataset.","url_abs":"https://arxiv.org/abs/2211.10946v2","url_pdf":"https://arxiv.org/pdf/2211.10946v2.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":"normalizing-flows-for-human-pose-anomaly","repo_url":"https://github.com/orhir/stg-nf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"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":"anomaly-detection-in-surveillance-videos","task_name":"Anomaly Detection In Surveillance Videos"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"video-anomaly-detection","task_name":"Video Anomaly Detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-shanghaitech","task":"Anomaly Detection","dataset":"ShanghaiTech","model":"STG-NF","rank_in_archive_order":4,"of":31,"metrics":{"AUC":"85.9%"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-ubnormal","task":"Anomaly Detection","dataset":"UBnormal","model":"STG-NF - Supervised","rank_in_archive_order":1,"of":14,"metrics":{"AUC":"79.2%"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-ubnormal","task":"Anomaly Detection","dataset":"UBnormal","model":"STG-NF - Unsupervised","rank_in_archive_order":4,"of":14,"metrics":{"AUC":"71.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.10946","atlas_url":"https://app.syntology.ai/?focus=2211.10946","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2211.10946"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2211.10946\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2211.10946"},"call":"get_concepts_for_paper(arxiv_id=\"2211.10946\")"}],"by_repo":[{"repo":"orhir/stg-nf","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"524a4c52bfdb173d5000be2044126a4691f34306b7f35ca4c7d4fa5265a536cc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}