{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:25:39Z","timestamp":1783113939576,"version":"3.54.6"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006013","name":"United Arab Emirates University","doi-asserted-by":"publisher","award":["12T101"],"award-info":[{"award-number":["12T101"]}],"id":[{"id":"10.13039\/501100006013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.iswa.2026.200676","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:06:01Z","timestamp":1779174361000},"page":"200676","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ST-GCVA: Hierarchical graph-based spatio-temporal reasoning for robust violence detection"],"prefix":"10.1016","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8020-3590","authenticated-orcid":false,"given":"Mustaqeem","family":"Khan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamil","family":"Alkilani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wasim","family":"Abusafia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamil","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farman","family":"Ullah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naqqash","family":"Dilshad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.iswa.2026.200676_b1","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017a). Quo Vadis, action recognition? A new model and the kinetics dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6299\u20136308).","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.iswa.2026.200676_b2","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017b). Quo vadis, action recognition? A new model and the kinetics dataset. In Proc. IEEE conf. computer vision and pattern recognition (pp. 6299\u20136308).","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.iswa.2026.200676_b3","series-title":"2020 25th international conference on pattern recognition","first-page":"4183","article-title":"January. rwf-2000: an open, large-scale video database for violence detection","author":"Cheng","year":"2021"},{"key":"10.1016\/j.iswa.2026.200676_b4","first-page":"150","article-title":"DOVE: Detection of movie violence using motion intensity analysis on skin and blood","volume":"6","author":"Clarin","year":"2005","journal-title":"PCSC"},{"issue":"3","key":"10.1016\/j.iswa.2026.200676_b5","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Machine Learning"},{"key":"10.1016\/j.iswa.2026.200676_b6","series-title":"MediaEval","article-title":"Fudan-huawei at MediaEval 2015: Detecting violent scenes and affective impact in movies with deep learning","author":"Dai","year":"2015"},{"key":"10.1016\/j.iswa.2026.200676_b7","series-title":"Histograms of oriented gradients for human detection","author":"Dalal","year":"2005"},{"key":"10.1016\/j.iswa.2026.200676_b8","first-page":"478","article-title":"Fast violence detection in video","volume":"vol. 2","author":"Deniz","year":"2014"},{"key":"10.1016\/j.iswa.2026.200676_b9","doi-asserted-by":"crossref","first-page":"100379","DOI":"10.1016\/j.cosrev.2021.100379","article-title":"A survey on deep learning and its applications","volume":"40","author":"Dong","year":"2021","journal-title":"Computer Science Review"},{"key":"10.1016\/j.iswa.2026.200676_b10","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.imavis.2016.01.006","article-title":"Violence detection using oriented violent flows","volume":"48","author":"Gao","year":"2016","journal-title":"Image and Vision Computing"},{"key":"10.1016\/j.iswa.2026.200676_b11","first-page":"1","article-title":"SurveillanceNet: Spatio-temporal anomaly identification in surveillance videos using two-stream CNN and LSTM","author":"Ghauri","year":"2025","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.iswa.2026.200676_b12","series-title":"Two-stream multi-dimensional convolutional network for real-time violence detection","author":"Ghosh","year":"2022"},{"key":"10.1016\/j.iswa.2026.200676_b13","series-title":"Two-stream multidimensional convolutional network for real-time violence detection","author":"Ghosh","year":"2022"},{"key":"10.1016\/j.iswa.2026.200676_b14","series-title":"2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","first-page":"1","article-title":"Violent flows: Real-time detection of violent crowd behavior","author":"Hassner","year":"2012"},{"issue":"8","key":"10.1016\/j.iswa.2026.200676_b15","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.1016\/j.iswa.2026.200676_b16","first-page":"1","article-title":"Deep learning techniques for video-based violence detection: a comprehensive review","author":"Houssein","year":"2026","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"key":"10.1016\/j.iswa.2026.200676_b17","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1007\/978-3-319-25087-8_29","article-title":"Subspace nearest neighbor search-problem statement approach and discussion","author":"Hund","year":"2015","journal-title":"International Conference on Similarity Search and Applications"},{"key":"10.1016\/j.iswa.2026.200676_b18","series-title":"2021 international joint conference on neural networks","first-page":"1","article-title":"Efficient two-stream network for violence detection using separable convolutional lstm","author":"Islam","year":"2021"},{"issue":"15","key":"10.1016\/j.iswa.2026.200676_b19","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1049\/el.2017.0970","article-title":"Violent activity detection with transfer learning method","volume":"53","author":"Keceli","year":"2017","journal-title":"Electronics Letters"},{"key":"10.1016\/j.iswa.2026.200676_b20","doi-asserted-by":"crossref","unstructured":"Li, X., Huo, Y., Jin, Q., & Xu, J. (2016). Detecting Violence in Video using Subclasses. In Proceedings of the 24th ACM international conference on multimedia (pp. 86\u2013590).","DOI":"10.1145\/2964284.2967289"},{"issue":"7","key":"10.1016\/j.iswa.2026.200676_b21","doi-asserted-by":"crossref","first-page":"1058","DOI":"10.1109\/TMM.2015.2436057","article-title":"Tag features for geo-aware image classification","volume":"17","author":"Liao","year":"2015","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.iswa.2026.200676_b22","article-title":"Privacy-preserving video anomaly detection: A survey","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.iswa.2026.200676_b23","article-title":"CRCL: Causal representation consistency learning for anomaly detection in surveillance videos","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"issue":"7","key":"10.1016\/j.iswa.2026.200676_b24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3645101","article-title":"Generalized video anomaly event detection: Systematic taxonomy and comparison of deep models","volume":"56","author":"Liu","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.iswa.2026.200676_b25","series-title":"Generalized image matching by the method of differences","author":"Lucas","year":"1986"},{"key":"10.1016\/j.iswa.2026.200676_b26","series-title":"An iterative image registration technique with an application to stereo vision","author":"Lucas","year":"1981"},{"issue":"2","key":"10.1016\/j.iswa.2026.200676_b27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10044-024-01265-0","article-title":"A spatio-temporal model for violence detection based on spatial and temporal attention modules and 2D CNNs","volume":"27","author":"Mahmoodi","year":"2024","journal-title":"Pattern Analysis and Applications"},{"issue":"8","key":"10.1016\/j.iswa.2026.200676_b28","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.3390\/math13081226","article-title":"Two-stage video violence detection framework using gmflow and CBAM-enhanced ResNet3D","volume":"13","author":"Mahmoud","year":"2025","journal-title":"Mathematics"},{"key":"10.1016\/j.iswa.2026.200676_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118791","article-title":"Video violence recognition and localization using a semi-supervised complex attention model","volume":"212","author":"Mohammadi","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.iswa.2026.200676_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118791","article-title":"Video violence recognition and localization using a semi-supervised complex attention model","volume":"212","author":"Mohammadi","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.iswa.2026.200676_b31","series-title":"Computer Analysis of Images and Patterns","first-page":"332","article-title":"Movies fight detection dataset","year":"2011"},{"key":"10.1016\/j.iswa.2026.200676_b32","doi-asserted-by":"crossref","unstructured":"Nievas, E. B., Suarez, O. D., Garc, G. B., & Sukthankar, R. (2011a). Violence detection in video using computer vision techniques. In International Conference on Computer analysis of images and patterns (pp. 332\u2013339).","DOI":"10.1007\/978-3-642-23678-5_39"},{"key":"10.1016\/j.iswa.2026.200676_b33","series-title":"Computer Analysis of Images and Patterns","first-page":"332","article-title":"Hockey fight detection dataset","author":"Nievas","year":"2011"},{"key":"10.1016\/j.iswa.2026.200676_b34","unstructured":"Nievas, E. B., Suarez, O. D., Garcia, G. B., & Sukthankar, R. (2011c). Violence detection in video using computer vision techniques. In International Conference on Computer Analysis of Images and Patterns."},{"key":"10.1016\/j.iswa.2026.200676_b35","series-title":"MediaEval","article-title":"Umons at MediaEval 2015 affective impact of movies task including violent scenes detection","author":"Seddati","year":"2015"},{"issue":"10","key":"10.1016\/j.iswa.2026.200676_b36","doi-asserted-by":"crossref","first-page":"4787","DOI":"10.1109\/TIP.2018.2845742","article-title":"Fight recognition in video using hough forests and 2D convolutional neural network","volume":"27","author":"Serrano","year":"2018","journal-title":"IEEE Transactions on Image Processing"},{"issue":"10","key":"10.1016\/j.iswa.2026.200676_b37","doi-asserted-by":"crossref","first-page":"4787","DOI":"10.1109\/TIP.2018.2845742","article-title":"Fight recognition in video using hough forests and 2D convolutional neural network","volume":"27","author":"Serrano","year":"2018","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.iswa.2026.200676_b38","series-title":"NIPS","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"Shi","year":"2015"},{"key":"10.1016\/j.iswa.2026.200676_b39","doi-asserted-by":"crossref","first-page":"39172","DOI":"10.1109\/ACCESS.2019.2906275","article-title":"A novel violent video detection scheme based on modified 3D convolutional neural networks","volume":"7","author":"Song","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.iswa.2026.200676_b40","series-title":"2017 the 14th IEEE International Conference on Advanced Video and Signal-Based Surveillance","first-page":"1","article-title":"Learning to detect violent videos using a convolutional long short-term memory","author":"Sudhakaran","year":"2017"},{"key":"10.1016\/j.iswa.2026.200676_b41","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., & Lanz, O. (2017b). Learning to detect violent videos using convolutional long short-term memory. In 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (pp. 1\u20136).","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"10.1016\/j.iswa.2026.200676_b42","doi-asserted-by":"crossref","unstructured":"Sudhakaran, Swathikiran, & Lanz, Oswald (2017c). Learning to detect violent videos using convolutional long short-term memory. In 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (pp. 1\u20136).","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"10.1016\/j.iswa.2026.200676_b43","series-title":"Proc. 14th IEEE int. conf. advanced video and signal based surveillance","first-page":"1","article-title":"Learning to detect violent videos using convolutional long short-term memory","author":"Sudhakaran","year":"2017"},{"key":"10.1016\/j.iswa.2026.200676_b44","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1\u20139).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10.1016\/j.iswa.2026.200676_b45","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3D convolutional networks. In Proc. ICCV.","DOI":"10.1109\/ICCV.2015.510"},{"issue":"10","key":"10.1016\/j.iswa.2026.200676_b46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3561971","article-title":"A comprehensive review of vision-based violence detection in surveillance videos","volume":"55","author":"Ullah","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.iswa.2026.200676_b47","doi-asserted-by":"crossref","unstructured":"Xu, L., Gong, C., Yang, J., Wu, Q., & Yao, L. (2014). Violent video detection based on MoSIFT feature and sparse coding. In 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2014 (pp. 3538\u20133542).","DOI":"10.1109\/ICASSP.2014.6854259"},{"key":"10.1016\/j.iswa.2026.200676_b48","doi-asserted-by":"crossref","DOI":"10.1145\/3797034","article-title":"A new semi-supervised video anomaly detection baseline in lack of anomalous samples","author":"Zhao","year":"2026","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"issue":"1","key":"10.1016\/j.iswa.2026.200676_b49","first-page":"12044","article-title":"Violent interaction detection in video based on deep learning","volume":"844","author":"Zhou","year":"2017","journal-title":"Journal of Physics: Conference Series"}],"container-title":["Intelligent Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2667305326000517?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2667305326000517?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:07:30Z","timestamp":1783112850000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2667305326000517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":49,"alternative-id":["S2667305326000517"],"URL":"https:\/\/doi.org\/10.1016\/j.iswa.2026.200676","relation":{},"ISSN":["2667-3053"],"issn-type":[{"value":"2667-3053","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ST-GCVA: Hierarchical graph-based spatio-temporal reasoning for robust violence detection","name":"articletitle","label":"Article Title"},{"value":"Intelligent Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.iswa.2026.200676","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"200676"}}