{"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/mist-multiple-instance-self-training","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","arxiv_id":"2104.01633","date":"2021-04-04","proceeding":"CVPR 2021 1","authors":["Jia-Chang Feng","Fa-Ting Hong","Wei-Shi Zheng"],"abstract":"Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insufficient video representations. In this work, we develop a multiple instance self-training framework (MIST)to efficiently refine task-specific discriminative representations with only video-level annotations. In particular, MIST is composed of 1) a multiple instance pseudo label generator, which adapts a sparse continuous sampling strategy to produce more reliable clip-level pseudo labels, and 2) a self-guided attention boosted feature encoder that aims to automatically focus on anomalous regions in frames while extracting task-specific representations. Moreover, we adopt a self-training scheme to optimize both components and finally obtain a task-specific feature encoder. Extensive experiments on two public datasets demonstrate the efficacy of our method, and our method performs comparably to or even better than existing supervised and weakly supervised methods, specifically obtaining a frame-level AUC 94.83% on ShanghaiTech.","url_abs":"https://arxiv.org/abs/2104.01633v1","url_pdf":"https://arxiv.org/pdf/2104.01633v1.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":"mist-multiple-instance-self-training","repo_url":"https://github.com/fjchange/MIST_VAD","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":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"weakly-supervised-video-anomaly-detection","task_name":"Weakly-supervised Video Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on-1","task":"Anomaly Detection In Surveillance Videos","dataset":"ShanghaiTech Weakly Supervised","model":"MIST","rank_in_archive_order":9,"of":12,"metrics":{"AUC-ROC":"94.83"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on","task":"Anomaly Detection In Surveillance Videos","dataset":"UCF-Crime","model":"MIST","rank_in_archive_order":14,"of":21,"metrics":{"ROC AUC":"82.30"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-video-anomaly-detection-on","task":"Weakly-supervised Video Anomaly Detection","dataset":"ShanghaiTech Weakly Supervised","model":"MIST","rank_in_archive_order":14,"of":16,"metrics":{"AUC-ROC":"94.83","FAR-Normal":"0.05"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-video-anomaly-detection-on-1","task":"Weakly-supervised Video Anomaly Detection","dataset":"UBnormal","model":"MIST","rank_in_archive_order":5,"of":11,"metrics":{"AUC-ROC":"65.32"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.01633","atlas_url":"https://app.syntology.ai/?focus=2104.01633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01633"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/fjchange/MIST_VAD","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jx-zhong-for-academic-purpose/GCN-Anomaly-Detection","reach":{"status":"ok"}}],"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":"5409afe9906f76e1","entry":"Self_Guided_Attention_Branch_Module","repo":"fjchange/MIST_VAD","repo_kind":"official","path":"models/Attention.py","file_url":"https://github.com/fjchange/MIST_VAD/blob/HEAD/models/Attention.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5409afe9906f76e1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}