{"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/holmes-vau-towards-long-term-video-anomaly","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","arxiv_id":"2412.06171","date":"2024-12-09","proceeding":"CVPR 2025 1","authors":["Huaxin Zhang","Xiaohao Xu","Xiang Wang","Jialong Zuo","Xiaonan Huang","Changxin Gao","Shanjun Zhang","Li Yu","Nong Sang"],"abstract":"How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies. To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-automated annotation engine that efficiently scales high-quality annotations by combining manual video segmentation with recursive free-text annotation using large language models (LLMs). This results in over 70,000 multi-granular annotations organized at clip-level, event-level, and video-level segments. For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS). ATS integrates an anomaly scorer with a density-aware sampler to adaptively select frames based on anomaly scores, ensuring that the multimodal LLM concentrates on anomaly-rich regions, which significantly enhances both efficiency and accuracy. Extensive experiments demonstrate that our hierarchical instruction data markedly improves anomaly comprehension. The integrated ATS and visual-language model outperform traditional methods in processing long videos. Our benchmark and model are publicly available at https://github.com/pipixin321/HolmesVAU.","url_abs":"https://arxiv.org/abs/2412.06171v1","url_pdf":"https://arxiv.org/pdf/2412.06171v1.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":"holmes-vau-towards-long-term-video-anomaly","repo_url":"https://github.com/pipixin321/holmesvau","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":"text-annotation","task_name":"text annotation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.06171","atlas_url":"https://app.syntology.ai/?focus=2412.06171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06171"}},"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/pipixin321/holmesvau","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"ran_fixture":1,"ran_honours":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"57e95166ade5f25c","entry":"build_transform","repo":"pipixin321/holmesvau","repo_kind":"official","path":"holmesvau/internvl_utils.py","file_url":"https://github.com/pipixin321/holmesvau/blob/HEAD/holmesvau/internvl_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"code_sha256_prefix":"6dc77bb22fb9d660","entry":"dynamic_preprocess","repo":"pipixin321/holmesvau","repo_kind":"official","path":"holmesvau/internvl_utils.py","file_url":"https://github.com/pipixin321/holmesvau/blob/HEAD/holmesvau/internvl_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6dc77bb22fb9d660"}},{"code_sha256_prefix":"bd77f5f8067f18e9","entry":"find_closest_aspect_ratio","repo":"pipixin321/holmesvau","repo_kind":"official","path":"holmesvau/internvl_utils.py","file_url":"https://github.com/pipixin321/holmesvau/blob/HEAD/holmesvau/internvl_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd77f5f8067f18e9"}},{"code_sha256_prefix":"21d247685c39adc6","entry":"norm","repo":"pipixin321/holmesvau","repo_kind":"official","path":"holmesvau/ATS/anomaly_scorer.py","file_url":"https://github.com/pipixin321/holmesvau/blob/HEAD/holmesvau/ATS/anomaly_scorer.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21d247685c39adc6"}},{"code_sha256_prefix":"6ba8cee9f5daea41","entry":"pair","repo":"pipixin321/holmesvau","repo_kind":"official","path":"holmesvau/ATS/anomaly_scorer.py","file_url":"https://github.com/pipixin321/holmesvau/blob/HEAD/holmesvau/ATS/anomaly_scorer.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ba8cee9f5daea41"}},{"code_sha256_prefix":"04b172bb0c32a0de","entry":"get_conv_template","repo":"pipixin321/holmesvau","repo_kind":"official","path":"internvl_chat/internvl/conversation.py","file_url":"https://github.com/pipixin321/holmesvau/blob/HEAD/internvl_chat/internvl/conversation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04b172bb0c32a0de"}},{"code_sha256_prefix":"5b5314952400cb9f","entry":"get_vid_list","repo":"pipixin321/holmesvau","repo_kind":"official","path":"HIVAU-70k/split_video.py","file_url":"https://github.com/pipixin321/holmesvau/blob/HEAD/HIVAU-70k/split_video.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b5314952400cb9f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}