{"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/vadclip-adapting-vision-language-models-for","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","arxiv_id":"2308.11681","date":"2023-08-22","proceeding":null,"authors":["Peng Wu","Xuerong Zhou","Guansong Pang","Lingru Zhou","Qingsen Yan","Peng Wang","Yanning Zhang"],"abstract":"The recent contrastive language-image pre-training (CLIP) model has shown great success in a wide range of image-level tasks, revealing remarkable ability for learning powerful visual representations with rich semantics. An open and worthwhile problem is efficiently adapting such a strong model to the video domain and designing a robust video anomaly detector. In this work, we propose VadCLIP, a new paradigm for weakly supervised video anomaly detection (WSVAD) by leveraging the frozen CLIP model directly without any pre-training and fine-tuning process. Unlike current works that directly feed extracted features into the weakly supervised classifier for frame-level binary classification, VadCLIP makes full use of fine-grained associations between vision and language on the strength of CLIP and involves dual branch. One branch simply utilizes visual features for coarse-grained binary classification, while the other fully leverages the fine-grained language-image alignment. With the benefit of dual branch, VadCLIP achieves both coarse-grained and fine-grained video anomaly detection by transferring pre-trained knowledge from CLIP to WSVAD task. We conduct extensive experiments on two commonly-used benchmarks, demonstrating that VadCLIP achieves the best performance on both coarse-grained and fine-grained WSVAD, surpassing the state-of-the-art methods by a large margin. Specifically, VadCLIP achieves 84.51% AP and 88.02% AUC on XD-Violence and UCF-Crime, respectively. Code and features are released at https://github.com/nwpu-zxr/VadCLIP.","url_abs":"https://arxiv.org/abs/2308.11681v3","url_pdf":"https://arxiv.org/pdf/2308.11681v3.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":"vadclip-adapting-vision-language-models-for","repo_url":"https://github.com/nwpu-zxr/vadclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"video-anomaly-detection","task_name":"Video Anomaly Detection"},{"task_slug":"weakly-supervised-video-anomaly-detection","task_name":"Weakly-supervised Video Anomaly Detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-video-anomaly-detection-on","task":"Weakly-supervised Video Anomaly Detection","dataset":"ShanghaiTech Weakly Supervised","model":"VadCLIP","rank_in_archive_order":7,"of":16,"metrics":{"AUC-ROC":"97.49"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-video-anomaly-detection-on-1","task":"Weakly-supervised Video Anomaly Detection","dataset":"UBnormal","model":"VadCLIP","rank_in_archive_order":8,"of":11,"metrics":{"AUC-ROC":"62.32"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.11681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11681"}},"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/nwpu-zxr/vadclip","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"722deffccfe046dc","entry":"CLAS2","repo":"nwpu-zxr/vadclip","repo_kind":"official","path":"src/ucf_train.py","file_url":"https://github.com/nwpu-zxr/vadclip/blob/HEAD/src/ucf_train.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"722deffccfe046dc"}},{"code_sha256_prefix":"39a9a85ba0b976d9","entry":"CLAS2","repo":"nwpu-zxr/vadclip","repo_kind":"official","path":"src/xd_train.py","file_url":"https://github.com/nwpu-zxr/vadclip/blob/HEAD/src/xd_train.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39a9a85ba0b976d9"}},{"code_sha256_prefix":"8126e661e2da6d6e","entry":"image_crop","repo":"nwpu-zxr/vadclip","repo_kind":"official","path":"src/crop.py","file_url":"https://github.com/nwpu-zxr/vadclip/blob/HEAD/src/crop.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8126e661e2da6d6e"}},{"code_sha256_prefix":"2b5eff3ede9ce667","entry":"video_crop","repo":"nwpu-zxr/vadclip","repo_kind":"official","path":"src/crop.py","file_url":"https://github.com/nwpu-zxr/vadclip/blob/HEAD/src/crop.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2b5eff3ede9ce667"}},{"code_sha256_prefix":"be63c876347199d0","entry":"CLASM","repo":"nwpu-zxr/vadclip","repo_kind":"official","path":"src/ucf_train.py","file_url":"https://github.com/nwpu-zxr/vadclip/blob/HEAD/src/ucf_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be63c876347199d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}