{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:19:47Z","timestamp":1783055987151,"version":"3.54.6"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125305"],"award-info":[{"award-number":["62125305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62503384"],"award-info":[{"award-number":["62503384"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572384"],"award-info":[{"award-number":["62572384"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20325"],"award-info":[{"award-number":["U24A20325"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["2024PT-ZCK-80"],"award-info":[{"award-number":["2024PT-ZCK-80"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2023ZD0121300"],"award-info":[{"award-number":["2023ZD0121300"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113898","type":"journal-article","created":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T22:50:52Z","timestamp":1777762252000},"page":"113898","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Action hints: Semantic typicality and context uniqueness for generalizable skeleton-based video anomaly detection"],"prefix":"10.1016","volume":"179","author":[{"given":"Canhui","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4100-2304","authenticated-orcid":false,"given":"Sanping","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyue","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113898_b1","doi-asserted-by":"crossref","unstructured":"W. Liu, W. Luo, D. Lian, S. Gao, Future frame prediction for anomaly detection\u2013a new baseline, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6536\u20136545.","DOI":"10.1109\/CVPR.2018.00684"},{"key":"10.1016\/j.patcog.2026.113898_b2","doi-asserted-by":"crossref","unstructured":"W. Sultani, C. Chen, M. Shah, Real-world anomaly detection in surveillance videos, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6479\u20136488.","DOI":"10.1109\/CVPR.2018.00678"},{"key":"10.1016\/j.patcog.2026.113898_b3","series-title":"European Conference on Computer Vision","first-page":"494","article-title":"Video anomaly detection by solving decoupled spatio-temporal jigsaw puzzles","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113898_b4","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Nie, C. Long, Q. Zhang, G. Li, A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13588\u201313597.","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"10.1016\/j.patcog.2026.113898_b5","series-title":"Advancing pre-trained teacher: towards robust feature discrepancy for anomaly detection","author":"Tang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b6","doi-asserted-by":"crossref","unstructured":"O. Hirschorn, S. Avidan, Normalizing flows for human pose anomaly detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 13545\u201313554.","DOI":"10.1109\/ICCV51070.2023.01246"},{"key":"10.1016\/j.patcog.2026.113898_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109335","article-title":"Memory-augmented appearance-motion network for video anomaly detection","volume":"138","author":"Wang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113898_b8","doi-asserted-by":"crossref","unstructured":"M. Cho, M. Kim, S. Hwang, C. Park, K. Lee, S. Lee, Look around for anomalies: weakly-supervised anomaly detection via context-motion relational learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 12137\u201312146.","DOI":"10.1109\/CVPR52729.2023.01168"},{"key":"10.1016\/j.patcog.2026.113898_b9","article-title":"Abnormal ratios guided multi-phase self-training for weakly-supervised video anomaly detection","author":"Shi","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113898_b10","series-title":"ARC: A generalist graph anomaly detector with in-context learning","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b11","doi-asserted-by":"crossref","unstructured":"J. Jeong, Y. Zou, T. Kim, D. Zhang, A. Ravichandran, O. Dabeer, Winclip: Zero-\/few-shot anomaly classification and segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19606\u201319616.","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"10.1016\/j.patcog.2026.113898_b12","series-title":"Filo: Zero-shot anomaly detection by fine-grained description and high-quality localization","author":"Gu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b13","series-title":"Adaclip: Adapting CLIP with hybrid learnable prompts for zero-shot anomaly detection","author":"Cao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b14","unstructured":"Q. Zhou, G. Pang, Y. Tian, S. He, J. Chen, AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.patcog.2026.113898_b15","doi-asserted-by":"crossref","unstructured":"A. Aich, K.-C. Peng, A.K. Roy-Chowdhury, Cross-domain video anomaly detection without target domain adaptation, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 2579\u20132591.","DOI":"10.1109\/WACV56688.2023.00261"},{"key":"10.1016\/j.patcog.2026.113898_b16","doi-asserted-by":"crossref","unstructured":"J. Micorek, H. Possegger, D. Narnhofer, H. Bischof, M. Kozinski, MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18868\u201318877.","DOI":"10.1109\/CVPR52733.2024.01785"},{"key":"10.1016\/j.patcog.2026.113898_b17","doi-asserted-by":"crossref","unstructured":"R. Morais, V. Le, T. Tran, B. Saha, M. Mansour, S. Venkatesh, Learning regularity in skeleton trajectories for anomaly detection in videos, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11996\u201312004.","DOI":"10.1109\/CVPR.2019.01227"},{"key":"10.1016\/j.patcog.2026.113898_b18","article-title":"Regularity learning via explicit distribution modeling for skeletal video anomaly detection","author":"Yu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113898_b19","doi-asserted-by":"crossref","unstructured":"A. Flaborea, L. Collorone, G.M.D. Di Melendugno, S. D\u2019Arrigo, B. Prenkaj, F. Galasso, Multimodal motion conditioned diffusion model for skeleton-based video anomaly detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 10318\u201310329.","DOI":"10.1109\/ICCV51070.2023.00947"},{"issue":"1","key":"10.1016\/j.patcog.2026.113898_b20","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"Openpose: Realtime multi-person 2d pose estimation using part affinity fields","volume":"43","author":"Cao","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"10.1016\/j.patcog.2026.113898_b21","doi-asserted-by":"crossref","first-page":"7157","DOI":"10.1109\/TPAMI.2022.3222784","article-title":"Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time","volume":"45","author":"Fang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113898_b22","doi-asserted-by":"crossref","unstructured":"A. Acsintoae, A. Florescu, M.-I. Georgescu, T. Mare, P. Sumedrea, R.T. Ionescu, F.S. Khan, M. Shah, Ubnormal: New benchmark for supervised open-set video anomaly detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 20143\u201320153.","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"10.1016\/j.patcog.2026.113898_b23","doi-asserted-by":"crossref","unstructured":"C. Cao, Y. Lu, P. Wang, Y. Zhang, A new comprehensive benchmark for semi-supervised video anomaly detection and anticipation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 20392\u201320401.","DOI":"10.1109\/CVPR52729.2023.01953"},{"key":"10.1016\/j.patcog.2026.113898_b24","doi-asserted-by":"crossref","unstructured":"S. Sun, X. Gong, Hierarchical semantic contrast for scene-aware video anomaly detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22846\u201322856.","DOI":"10.1109\/CVPR52729.2023.02188"},{"key":"10.1016\/j.patcog.2026.113898_b25","doi-asserted-by":"crossref","unstructured":"A. Markovitz, G. Sharir, I. Friedman, L. Zelnik-Manor, S. Avidan, Graph embedded pose clustering for anomaly detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10539\u201310547.","DOI":"10.1109\/CVPR42600.2020.01055"},{"key":"10.1016\/j.patcog.2026.113898_b26","series-title":"Frequency-guided diffusion model with perturbation training for skeleton-based video anomaly detection","author":"Tan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b27","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113898_b28","series-title":"DA-flow: Dual attention normalizing flow for skeleton-based video anomaly detection","author":"Wu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b29","article-title":"Zero-shot anomaly detection via batch normalization","volume":"36","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113898_b30","doi-asserted-by":"crossref","unstructured":"T. Aota, L.T.T. Tong, T. Okatani, Zero-shot versus many-shot: Unsupervised texture anomaly detection, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 5564\u20135572.","DOI":"10.1109\/WACV56688.2023.00552"},{"key":"10.1016\/j.patcog.2026.113898_b31","series-title":"A zero-\/fewshot anomaly classification and segmentation method for cvpr 2023 vand workshop challenge tracks 1&2: 1st place on zero-shot ad and 4th place on few-shot ad","author":"Chen","year":"2023"},{"key":"10.1016\/j.patcog.2026.113898_b32","series-title":"Generalized out-of-distribution detection and beyond in vision language model era: A survey","author":"Miyai","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b33","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113898_b34","series-title":"Proceedings of the 2024 SIAM International Conference on Data Mining","first-page":"634","article-title":"Ada-VAD: Domain adaptable video anomaly detection","author":"Guo","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b35","doi-asserted-by":"crossref","unstructured":"L. Zanella, W. Menapace, M. Mancini, Y. Wang, E. Ricci, Harnessing Large Language Models for Training-free Video Anomaly Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18527\u201318536.","DOI":"10.1109\/CVPR52733.2024.01753"},{"key":"10.1016\/j.patcog.2026.113898_b36","doi-asserted-by":"crossref","unstructured":"F. Sato, R. Hachiuma, T. Sekii, Prompt-guided zero-shot anomaly action recognition using pretrained deep skeleton features, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 6471\u20136480.","DOI":"10.1109\/CVPR52729.2023.00626"},{"key":"10.1016\/j.patcog.2026.113898_b37","doi-asserted-by":"crossref","unstructured":"J. Carreira, A. Zisserman, Quo vadis, action recognition? a new model and the kinetics dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6299\u20136308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.patcog.2026.113898_b38","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","volume":"vol. 32","author":"Yan","year":"2018"},{"key":"10.1016\/j.patcog.2026.113898_b39","doi-asserted-by":"crossref","unstructured":"X. Liu, S. Zhou, L. Wang, G. Hua, Parallel attention interaction network for few-shot skeleton-based action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 1379\u20131388.","DOI":"10.1109\/ICCV51070.2023.00133"},{"key":"10.1016\/j.patcog.2026.113898_b40","series-title":"Learning discriminative spatio-temporal representations for semi-supervised action recognition","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113898_b41","series-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113898_b42","doi-asserted-by":"crossref","unstructured":"W. Xiang, C. Li, Y. Zhou, B. Wang, L. Zhang, Generative action description prompts for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 10276\u201310285.","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"10.1016\/j.patcog.2026.113898_b43","doi-asserted-by":"crossref","unstructured":"C. Lu, J. Shi, J. Jia, Abnormal event detection at 150 fps in matlab, in: Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 2720\u20132727.","DOI":"10.1109\/ICCV.2013.338"},{"issue":"1","key":"10.1016\/j.patcog.2026.113898_b44","first-page":"18","article-title":"Anomaly detection and localization in crowded scenes","volume":"36","author":"Li","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113898_b45","doi-asserted-by":"crossref","unstructured":"R. Girdhar, A. El-Nouby, Z. Liu, M. Singh, K.V. Alwala, A. Joulin, I. Misra, Imagebind: One embedding space to bind them all, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15180\u201315190.","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"10.1016\/j.patcog.2026.113898_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103656","article-title":"Ssmtl++: Revisiting self-supervised multi-task learning for video anomaly detection","volume":"229","author":"Barbalau","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.patcog.2026.113898_b47","doi-asserted-by":"crossref","unstructured":"Y. Chen, Z. Zhang, C. Yuan, B. Li, Y. Deng, W. Hu, Channel-wise topology refinement graph convolution for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13359\u201313368.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"10.1016\/j.patcog.2026.113898_b48","doi-asserted-by":"crossref","unstructured":"X. Yao, R. Li, J. Zhang, J. Sun, C. Zhang, Explicit boundary guided semi-push-pull contrastive learning for supervised anomaly detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 24490\u201324499.","DOI":"10.1109\/CVPR52729.2023.02346"},{"key":"10.1016\/j.patcog.2026.113898_b49","series-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113898_b50","series-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"10.1016\/j.patcog.2026.113898_b51","series-title":"TSPO: Temporal sampling policy optimization for long-form video language understanding","author":"Tang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113898_b52","doi-asserted-by":"crossref","unstructured":"J. Xu, S.-Y. Lo, B. Safaei, V.M. Patel, I. Dwivedi, Towards zero-shot anomaly detection and reasoning with multimodal large language models, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 20370\u201320382.","DOI":"10.1109\/CVPR52734.2025.01897"},{"key":"10.1016\/j.patcog.2026.113898_b53","doi-asserted-by":"crossref","unstructured":"Y. Li, A. Goodge, F. Liu, C.-S. Foo, Promptad: Zero-shot anomaly detection using text prompts, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 1093\u20131102.","DOI":"10.1109\/WACV57701.2024.00113"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008630?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008630?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:49:56Z","timestamp":1783054196000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326008630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":53,"alternative-id":["S0031320326008630"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113898","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Action hints: Semantic typicality and context uniqueness for generalizable skeleton-based video anomaly detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113898","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113898"}}