{"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/mulde-multiscale-log-density-estimation-via","title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","arxiv_id":"2403.14497","date":"2024-03-21","proceeding":"CVPR 2024 1","authors":["Jakub Micorek","Horst Possegger","Dominik Narnhofer","Horst Bischof","Mateusz Kozinski"],"abstract":"We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this distribution with a neural network. This lets us estimate the likelihood of test videos and detect video anomalies by thresholding the likelihood estimates. We train our video anomaly detector using a modification of denoising score matching, a method that injects training data with noise to facilitate modeling its distribution. To eliminate hyperparameter selection, we model the distribution of noisy video features across a range of noise levels and introduce a regularizer that tends to align the models for different levels of noise. At test time, we combine anomaly indications at multiple noise scales with a Gaussian mixture model. Running our video anomaly detector induces minimal delays as inference requires merely extracting the features and forward-propagating them through a shallow neural network and a Gaussian mixture model. Our experiments on five popular video anomaly detection benchmarks demonstrate state-of-the-art performance, both in the object-centric and in the frame-centric setup.","url_abs":"https://arxiv.org/abs/2403.14497v1","url_pdf":"https://arxiv.org/pdf/2403.14497v1.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":"mulde-multiscale-log-density-estimation-via","repo_url":"https://github.com/jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":"denoising","task_name":"Denoising"},{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"video-anomaly-detection","task_name":"Video Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-chuk-avenue","task":"Anomaly Detection","dataset":"CUHK Avenue","model":"MULDE-object-centric-micro","rank_in_archive_order":1,"of":35,"metrics":{"AUC":"94.3%"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-shanghaitech","task":"Anomaly Detection","dataset":"ShanghaiTech","model":"MULDE-object-centric-micro","rank_in_archive_order":2,"of":31,"metrics":{"AUC":"86.7%"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-shanghaitech","task":"Anomaly Detection","dataset":"ShanghaiTech","model":"MULDE-frame-centric-micro","rank_in_archive_order":17,"of":31,"metrics":{"AUC":"81.3%"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-ubnormal","task":"Anomaly Detection","dataset":"UBnormal","model":"MULDE-frame-centric-micro-one-class-classification","rank_in_archive_order":2,"of":14,"metrics":{"AUC":"72.8%"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-ucf-crime-1","task":"Anomaly Detection","dataset":"UCF-Crime","model":"MULDE-frame-centric-micro-one-class-classification","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"78.5%"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-ucsd-ped2","task":"Anomaly Detection","dataset":"UCSD Ped2","model":"MULDE-object-centric-micro","rank_in_archive_order":2,"of":14,"metrics":{"AUC":"99.7%"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on","task":"Anomaly Detection In Surveillance Videos","dataset":"UCF-Crime","model":"MULDE-frame-centric-micro-one-class-classification","rank_in_archive_order":17,"of":21,"metrics":{"ROC AUC":"78.5%"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-chuk-avenue","task":"Video Anomaly Detection","dataset":"CHUK Avenue","model":"MULDE-object-centric-micro","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"94.3%"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-shanghaitech-4","task":"Video Anomaly Detection","dataset":"ShanghaiTech","model":"MULDE-object-centric-micro","rank_in_archive_order":1,"of":7,"metrics":{"AUC":"86.7%"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-shanghaitech-4","task":"Video Anomaly Detection","dataset":"ShanghaiTech","model":"MULDE-frame-centric-micro","rank_in_archive_order":4,"of":7,"metrics":{"AUC":"81.3%"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-ubnormal","task":"Video Anomaly Detection","dataset":"UBnormal","model":"MULDE-frame-centric-micro-one-class-classification","rank_in_archive_order":2,"of":4,"metrics":{"AUC":"72.8%"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-ucf-crime-2","task":"Video Anomaly Detection","dataset":"UCF-Crime","model":"MULDE-frame-centric-micro-one-class-classification","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"78.5%"},"uses_additional_data":false},{"leaderboard":"/sota/video-anomaly-detection-on-ucsd-ped2-1","task":"Video Anomaly Detection","dataset":"UCSD Ped2","model":"MULDE-object-centric-micro","rank_in_archive_order":1,"of":3,"metrics":{"AUC":"99.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.14497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14497"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"1a900a73c757a312","entry":"ScoreOrLogDensityNetwork","repo":"jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection","repo_kind":"official","path":"models.py","file_url":"https://github.com/jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a900a73c757a312"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}