{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T22:07:54Z","timestamp":1780956474338,"version":"3.54.1"},"reference-count":54,"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"}],"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.2026.113815","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:58:44Z","timestamp":1776787124000},"page":"113815","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Cross-modal attention fusion of RGB and skeleton for multimodal-driven video anomaly detection"],"prefix":"10.1016","volume":"179","author":[{"given":"Boan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weide","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinmei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoquan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1312-0146","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113815_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110898","article-title":"Semantic-driven dual consistency learning for weakly supervised video anomaly detection","volume":"157","author":"Su","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113815_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111452","article-title":"Knowledge-driven compositional action recognition","volume":"163","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113815_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110877","article-title":"Fast video anomaly detection via context-aware shortcut exploration and abnormal feature distance learning","volume":"157","author":"Park","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113815_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112016","article-title":"A video anomaly detection framework based on semantic consistency and multi-attribute feature complementarity","volume":"170","author":"Wang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113815_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110500","article-title":"Dual GroupGAN: An unsupervised four-competitor (2V2) approach for video anomaly detection","volume":"153","author":"Sun","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113815_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125581","article-title":"Rethinking prediction-based video anomaly detection from local\u2013global normality perspective","volume":"262","author":"Zhao","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113815_b7","series-title":"The evolution of video anomaly detection: A unified framework from DNN to MLLM","author":"Gao","year":"2025"},{"key":"10.1016\/j.patcog.2026.113815_b8","article-title":"Privacy-preserving video anomaly detection: A survey","author":"Liu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"10.1016\/j.patcog.2026.113815_b9","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1109\/TETCI.2024.3358103","article-title":"Skeletal video anomaly detection using deep learning: Survey, challenges, and future directions","volume":"8","author":"Mishra","year":"2024","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.patcog.2026.113815_b10","series-title":"WACV","first-page":"995","article-title":"An exploratory study on human-centric video anomaly detection through variational autoencoders and trajectory prediction","author":"Noghre","year":"2024"},{"key":"10.1016\/j.patcog.2026.113815_b11","series-title":"CVPR","first-page":"6536","article-title":"Future frame prediction for anomaly detection\u2014a new baseline","author":"Liu","year":"2018"},{"key":"10.1016\/j.patcog.2026.113815_b12","first-page":"938","article-title":"Appearance-motion memory consistency network for video anomaly detection","volume":"vol. 35","author":"Cai","year":"2021"},{"key":"10.1016\/j.patcog.2026.113815_b13","series-title":"ICCV","first-page":"1705","article-title":"Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection","author":"Gong","year":"2019"},{"key":"10.1016\/j.patcog.2026.113815_b14","series-title":"CVPR","first-page":"14372","article-title":"Learning memory-guided normality for anomaly detection","author":"Park","year":"2020"},{"key":"10.1016\/j.patcog.2026.113815_b15","doi-asserted-by":"crossref","DOI":"10.1109\/TMM.2025.3535377","article-title":"Audio-visual collaborative learning for weakly supervised video anomaly detection","author":"Meng","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113815_b16","article-title":"Robust low-light image enhancement in the wild via data synthesis and generative diffusion prior","author":"Wang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113815_b17","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2026.3667102","article-title":"Pose-guided multi-cue explicit query construction for disambiguating human-object interactions","author":"Zou","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113815_b18","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2026.3657415","article-title":"DVLTA-VQA: Decoupled vision-language modeling with text-guided adaptation for blind video quality assessment","author":"Yu","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113815_b19","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/TIP.2026.3652021","article-title":"Self-supervised unfolding network with shared reflectance learning for low-light image enhancement","volume":"35","author":"Liu","year":"2026","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113815_b20","series-title":"ACM MM","first-page":"6103","article-title":"Hierarchical scene normality-binding modeling for anomaly detection in surveillance videos","author":"Bao","year":"2022"},{"key":"10.1016\/j.patcog.2026.113815_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129576","article-title":"Spatio-temporal graph-based self-labeling for video anomaly detection","volume":"627","author":"Xing","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113815_b22","series-title":"CVPR","first-page":"733","article-title":"Learning temporal regularity in video sequences","author":"Hasan","year":"2016"},{"key":"10.1016\/j.patcog.2026.113815_b23","series-title":"CVPR","first-page":"15984","article-title":"Self-distilled masked auto-encoders are efficient video anomaly detectors","author":"Ristea","year":"2024"},{"issue":"10","key":"10.1016\/j.patcog.2026.113815_b24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3729222","article-title":"Networking systems for video anomaly detection: A tutorial and survey","volume":"57","author":"Liu","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patcog.2026.113815_b25","series-title":"CVPR","first-page":"11996","article-title":"Learning regularity in skeleton trajectories for anomaly detection in videos","author":"Morais","year":"2019"},{"key":"10.1016\/j.patcog.2026.113815_b26","series-title":"CVPR","first-page":"10539","article-title":"Graph embedded pose clustering for anomaly detection","author":"Markovitz","year":"2020"},{"key":"10.1016\/j.patcog.2026.113815_b27","series-title":"ICCV","first-page":"13545","article-title":"Normalizing flows for human pose anomaly detection","author":"Hirschorn","year":"2023"},{"key":"10.1016\/j.patcog.2026.113815_b28","doi-asserted-by":"crossref","DOI":"10.1109\/TMM.2025.3607708","article-title":"DA-Flow: Dual attention normalizing flow for skeleton-based video anomaly detection","author":"Wu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113815_b29","series-title":"Anomaly detection and generation with diffusion models: A survey","author":"Liu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113815_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111978","article-title":"VPE-WSVAD: Visual prompt exemplars for weakly-supervised video anomaly detection","volume":"299","author":"Su","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.113815_b31","doi-asserted-by":"crossref","first-page":"2213","DOI":"10.1109\/TIP.2024.3374070","article-title":"Toward video anomaly retrieval from video anomaly detection: New benchmarks and model","volume":"33","author":"Wu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113815_b32","series-title":"ICML","first-page":"62429","article-title":"Vision mamba: efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"issue":"1","key":"10.1016\/j.patcog.2026.113815_b33","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.2026.113815_b34","series-title":"ICCV","first-page":"2720","article-title":"Abnormal event detection at 150 FPS in MATLAB","author":"Lu","year":"2013"},{"key":"10.1016\/j.patcog.2026.113815_b35","series-title":"ICCV","first-page":"341","article-title":"A revisit of sparse coding based anomaly detection in stacked RNN framework","author":"Luo","year":"2017"},{"key":"10.1016\/j.patcog.2026.113815_b36","series-title":"CVPR","first-page":"20392","article-title":"A new comprehensive benchmark for semi-supervised video anomaly detection and anticipation","author":"Cao","year":"2023"},{"key":"10.1016\/j.patcog.2026.113815_b37","series-title":"CVPR","first-page":"2921","article-title":"Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates","author":"Kim","year":"2009"},{"key":"10.1016\/j.patcog.2026.113815_b38","series-title":"ICCV","first-page":"2895","article-title":"Unmasking the abnormal events in video","author":"Ionescu","year":"2017"},{"key":"10.1016\/j.patcog.2026.113815_b39","series-title":"ICCV","first-page":"3619","article-title":"Joint detection and recounting of abnormal events by learning deep generic knowledge","author":"Hinami","year":"2017"},{"key":"10.1016\/j.patcog.2026.113815_b40","series-title":"ICIP","first-page":"1577","article-title":"Abnormal event detection in videos using generative adversarial nets","author":"Ravanbakhsh","year":"2017"},{"key":"10.1016\/j.patcog.2026.113815_b41","series-title":"ICCV","first-page":"1273","article-title":"Anomaly detection in video sequence with appearance-motion correspondence","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.patcog.2026.113815_b42","series-title":"ACM MM","first-page":"1805","article-title":"AnoPCN: Video anomaly detection via deep predictive coding network","author":"Ye","year":"2019"},{"key":"10.1016\/j.patcog.2026.113815_b43","doi-asserted-by":"crossref","first-page":"123977","DOI":"10.1109\/ACCESS.2021.3109102","article-title":"Transanomaly: Video anomaly detection using video vision transformer","volume":"9","author":"Yuan","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.113815_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108213","article-title":"Video anomaly detection with spatio-temporal dissociation","volume":"122","author":"Chang","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113815_b45","series-title":"CVPR","first-page":"3054","article-title":"Video prediction recalling long-term motion context via memory alignment learning","author":"Lee","year":"2021"},{"key":"10.1016\/j.patcog.2026.113815_b46","article-title":"NM-GAN: Noise-modulated generative adversarial network for video anomaly detection","volume":"116","author":"Sun","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113815_b47","article-title":"STNMamba: Mamba-based spatial-temporal normality learning for video anomaly detection","author":"Li","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113815_b48","series-title":"ECCV","first-page":"494","article-title":"Video anomaly detection by solving decoupled spatio-temporal jigsaw puzzles","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113815_b49","series-title":"WACV","first-page":"2626","article-title":"Multi-timescale trajectory prediction for abnormal human activity detection","author":"Rodrigues","year":"2020"},{"key":"10.1016\/j.patcog.2026.113815_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110817","article-title":"Contracting skeletal kinematics for human-related video anomaly detection","volume":"156","author":"Flaborea","year":"2024","journal-title":"Pattern Recognit."},{"issue":"6","key":"10.1016\/j.patcog.2026.113815_b51","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."},{"issue":"10","key":"10.1016\/j.patcog.2026.113815_b52","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep high-resolution representation learning for visual recognition","volume":"43","author":"Wang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113815_b53","series-title":"NeurIPS","first-page":"38571","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","volume":"35","author":"Xu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113815_b54","unstructured":"V. Bazarevsky, I. Grishchenko, K. Raveendran, T. Zhu, F. Zhang, M. Grundmann, BlazePose: On-device real-time body pose tracking, in: CVPR Workshops, 2020."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007806?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007806?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:56:38Z","timestamp":1780955798000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326007806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":54,"alternative-id":["S0031320326007806"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113815","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":"Cross-modal attention fusion of RGB and skeleton for multimodal-driven video anomaly detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113815","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113815"}}