{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T02:58:30Z","timestamp":1781751510729,"version":"3.54.5"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730030","type":"print"},{"value":"9783031730047","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73004-7_18","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:04:18Z","timestamp":1730394258000},"page":"304-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Follow the\u00a0Rules: Reasoning for\u00a0Video Anomaly Detection with\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Yuchen","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwonjoon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Behzad","family":"Dariush","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinzhi","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shao-Yuan","family":"Lo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"18_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Acsintoae, A., et al.: Ubnormal: new benchmark for supervised open-set video anomaly detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Aich, A., Peng, K.C., Roy-Chowdhury, A.K.: Cross-domain video anomaly detection without target domain adaptation. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (2023)","DOI":"10.1109\/WACV56688.2023.00261"},{"key":"18_CR4","unstructured":"Bacon, F.: Novum organum (1620)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Bendale, A., Boult, T.E.: Towards open set deep networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.173"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD\u2013a comprehensive real-world dataset for unsupervised anomaly detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00982"},{"key":"18_CR7","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: Conference on Neural Information Processing Systems (2020)"},{"key":"18_CR8","unstructured":"Cao, Y., Xu, X., Sun, C., Huang, X., Shen, W.: Towards generic anomaly detection and understanding: Large-scale visual-linguistic model (gpt-4v) takes the lead. arXiv preprint arXiv:2311.02782 (2023)"},{"key":"18_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-030-58555-6_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Chang","year":"2020","unstructured":"Chang, Y., Tu, Z., Xie, W., Yuan, J.: Clustering driven deep autoencoder for video anomaly detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 329\u2013345. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_20"},{"key":"18_CR10","unstructured":"Cohen, J., Rosenfeld, E., Kolter, Z.: Certified adversarial robustness via randomized smoothing. In: International Conference on Machine Learning (2019)"},{"key":"18_CR11","unstructured":"Diao, S., Wang, P., Lin, Y., Zhang, T.: Active prompting with chain-of-thought for large language models. arXiv preprint arXiv:2302.12246 (2023)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Elhafsi, A., Sinha, R., Agia, C., Schmerling, E., Nesnas, I.A., Pavone, M.: Semantic anomaly detection with large language models. In: Autonomous Robots (2023)","DOI":"10.1007\/s10514-023-10132-6"},{"key":"18_CR13","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning (2015)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Georgescu, M.I., Ionescu, R.T., Khan, F.S., Popescu, M., Shah, M.: A background-agnostic framework with adversarial training for abnormal event detection in video. IEEE Trans. Pattern Anal. Mach. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3074805"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Gu, Z., Zhu, B., Zhu, G., Chen, Y., Tang, M., Wang, J.: AnomalyGPT: detecting industrial anomalies using large vision-language models. In: AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A.K., Davis, L.S.: Learning temporal regularity in video sequences. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.86"},{"key":"18_CR17","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: International Conference on Learning Representations (2017)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Hirschorn, O., Avidan, S.: Normalizing flows for human pose anomaly detection. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01246"},{"key":"18_CR19","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, G.: Recursion of thought: a divide-and-conquer approach to multi-context reasoning with language models. In: Annual Meeting of the Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.findings-acl.40"},{"key":"18_CR21","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning (2023)"},{"key":"18_CR22","unstructured":"Li, W., Mahadevan, V., Vasconcelos, N.: Anomaly detection and localization in crowded scenes. IEEE Trans. Pattern Anal. Mach. Intell. (2013)"},{"key":"18_CR23","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Conference on Neural Information Processing Systems (2023)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Luo, W., Lian, D., Gao, S.: Future frame prediction for anomaly detection\u2013a new baseline. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00684"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Nie, Y., Long, C., Zhang, Q., Li, G.: A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction. In: IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Lo, S.Y., Oza, P., Chennupati, S., Galindo, A., Patel, V.M.: Spatio-temporal pixel-level contrastive learning-based source-free domain adaptation for video semantic segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01015"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Lo, S.Y., Oza, P., Patel, V.M.: Adversarially robust one-class novelty detection. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3189638"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Lu, C., Shi, J., Jia, J.: Abnormal event detection at 150 fps in matlab. In: IEEE\/CVF International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.338"},{"key":"18_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-58558-7_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Lu","year":"2020","unstructured":"Lu, Y., Yu, F., Reddy, M.K.K., Wang, Y.: Few-shot scene-adaptive anomaly detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 125\u2013141. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_8"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Lv, H., Chen, C., Cui, Z., Xu, C., Li, Y., Yang, J.: Learning normal dynamics in videos with meta prototype network. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01517"},{"key":"18_CR31","unstructured":"Lv, H., Sun, Q.: Video anomaly detection and explanation via large language models. arXiv preprint arXiv:2401.05702 (2024)"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Mao, C., et al.: Doubly right object recognition: a why prompt for visual rationales. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00267"},{"key":"18_CR33","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"ECCV 2022","author":"M Minderer","year":"2022","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Mittal, H., Agarwal, N., Lo, S.Y., Lee, K.: Can\u2019t make an omelette without breaking some eggs: plausible action anticipation using large video-language models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01758"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Morais, R., Le, V., Tran, T., Saha, B., Mansour, M., Venkatesh, S.: Learning regularity in skeleton trajectories for anomaly detection in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01227"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Park, H., Noh, J., Ham, B.: Learning memory-guided normality for anomaly detection. In: IEEE\/CVF Conference Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"18_CR37","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Conference on Neural Information Processing Systems (2019)"},{"key":"18_CR38","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training. OpenAI Blog (2018)"},{"key":"18_CR39","unstructured":"Radford, A., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI Blog (2019)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Safaei, B., Vibashan, V., de\u00a0Melo, C.M., Hu, S., Patel, V.M.: Open-set automatic target recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (2023)","DOI":"10.1109\/ICASSP49357.2023.10095843"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Seel, N.M.: Encyclopedia of the Sciences of Learning (2011)","DOI":"10.1007\/978-1-4419-1428-6"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Sharifi, S., Entesari, T., Safaei, B., Patel, V.M., Fazlyab, M.: Gradient-regularized out-of-distribution detection. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72624-8_26"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Shi, C., Sun, C., Wu, Y., Jia, Y.: Video anomaly detection via sequentially learning multiple pretext tasks. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00948"},{"key":"18_CR44","unstructured":"Su, Y., Lan, T., Li, H., Xu, J., Wang, Y., Cai, D.: Pandagpt: one model to instruction-follow them all. arXiv preprint arXiv:2305.16355 (2023)"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Sun, S., Gong, X.: Hierarchical semantic contrast for scene-aware video anomaly detection. In: IEEE\/CVF Computer Vision and Pattern Recognition Conference (2023)","DOI":"10.1109\/CVPR52729.2023.02188"},{"key":"18_CR46","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"18_CR47","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Hung, W.C., Schulter, S., Sohn, K., Yang, M.H., Chandraker, M.: Learning to adapt structured output space for semantic segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00780"},{"key":"18_CR49","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-031-20080-9_29","volume-title":"ECCV 2022","author":"G Wang","year":"2022","unstructured":"Wang, G., Wang, Y., Qin, J., Zhang, D., Bao, X., Huang, D.: Video anomaly detection by solving decoupled spatio-temporal jigsaw puzzles. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 494\u2013511. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_29"},{"key":"18_CR50","unstructured":"Wang, H., Zhang, X., Yang, S., Zhang, W.: Video anomaly detection by the duality of normality-granted optical flow. arXiv preprint arXiv:2105.04302 (2021)"},{"key":"18_CR51","unstructured":"Wang, W., et\u00a0al.: Cogvlm: visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)"},{"key":"18_CR52","unstructured":"Wei, J., et\u00a0al.: Chain-of-thought prompting elicits reasoning in large language models. In: Conference on Neural Information Processing Systems (2022)"},{"key":"18_CR53","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1007\/978-3-031-19778-9_42","volume-title":"ECCV 2022","author":"JC Wu","year":"2022","unstructured":"Wu, J.C., Hsieh, H.Y., Chen, D.J., Fuh, C.S., Liu, T.L.: Self-supervised sparse representation for video anomaly detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13673, pp. 729\u2013745. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19778-9_42"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Yan, C., Zhang, S., Liu, Y., Pang, G., Wang, W.: Feature prediction diffusion model for video anomaly detection. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00509"},{"key":"18_CR55","unstructured":"You, Z., et al.: A unified model for multi-class anomaly detection. In: Conference on Neural Information Processing Systems (2022)"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Zaheer, M.Z., Mahmood, A., Khan, M.H., Segu, M., Yu, F., Lee, S.I.: Generative cooperative learning for unsupervised video anomaly detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01433"},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-llama: an instruction-tuned audio-visual language model for video understanding. In: Conference on Empirical Methods in Natural Language Processing (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"18_CR58","unstructured":"Zhang, Y., et\u00a0al.: Recognize anything: a strong image tagging model. arXiv preprint arXiv:2306.03514 (2023)"},{"key":"18_CR59","unstructured":"Zhou, D., et\u00a0al.: Least-to-most prompting enables complex reasoning in large language models. In: International Conference on Learning Representations (2023)"},{"key":"18_CR60","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. In: International Conference on Learning Representations (2024)"},{"key":"18_CR61","unstructured":"Zhu, Z., et al.: Large language models can learn rules. arXiv preprint arXiv:2310.07064 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73004-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:08:30Z","timestamp":1730394510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73004-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031730030","9783031730047"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73004-7_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}