{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T20:50:48Z","timestamp":1782939048003,"version":"3.54.5"},"reference-count":57,"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":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":["Computers and Electrical Engineering"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.compeleceng.2026.111256","type":"journal-article","created":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T06:45:12Z","timestamp":1779605112000},"page":"111256","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Context-Aware Multi-Scale Transformers with dual-stage multiple instance learning for violence detection"],"prefix":"10.1016","volume":"137","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4818-3017","authenticated-orcid":false,"given":"Shobha","family":"Kumari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3460-6989","authenticated-orcid":false,"given":"Vijay","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compeleceng.2026.111256_b1","series-title":"2024 IEEE international conference on multimedia and expo","first-page":"1","article-title":"Multi-scale bottleneck transformer for weakly supervised multimodal violence detection","author":"Sun","year":"2024"},{"key":"10.1016\/j.compeleceng.2026.111256_b2","doi-asserted-by":"crossref","unstructured":"Bharti Rahul, Kumari Shobha, Kumar Vijay. Video-Based Violence and Anomaly Detection Techniques in Surveillance Systems. In: 2025 IEEE 4th world conference on applied intelligence and computing. 2025, p. 1059\u201364.","DOI":"10.1109\/AIC66080.2025.11212179"},{"key":"10.1016\/j.compeleceng.2026.111256_b3","article-title":"Multimodal attention-enhanced feature fusion-based weakly supervised anomaly violence detection","author":"Shin","year":"2024","journal-title":"IEEE Open J Comput Soc"},{"key":"10.1016\/j.compeleceng.2026.111256_b4","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3574835","article-title":"An integrated CNN-BiLSTM-transformer framework for improved anomaly detection using surveillance videos","author":"Natha","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.compeleceng.2026.111256_b5","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s11760-025-05090-8","article-title":"A hybrid context-aware video violence detection framework using hierarchical spatiotemporal and semantic modeling: S. Kumari, V. Kumar","volume":"20","author":"Kumari","year":"2026","journal-title":"Signal, Image Video Process"},{"key":"10.1016\/j.compeleceng.2026.111256_b6","doi-asserted-by":"crossref","first-page":"2198","DOI":"10.1109\/ACCESS.2023.3339379","article-title":"KianNet: A violence detection model using an attention-based CNN-LSTM structure","volume":"12","author":"Vosta","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.compeleceng.2026.111256_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2023.108614","article-title":"Combined CNN\/RNN video privacy protection evaluation method for monitoring home scene violence","volume":"106","author":"Liu","year":"2023","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.compeleceng.2026.111256_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2022.108319","article-title":"A real time crime scene intelligent video surveillance systems in violence detection framework using deep learning techniques","volume":"103","author":"Sahay","year":"2022","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.compeleceng.2026.111256_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2025.110651","article-title":"Crime prediction against women in surveillance videos using deep learning models: A review","volume":"128","author":"Dhuri","year":"2025","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.compeleceng.2026.111256_b10","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.neunet.2023.01.048","article-title":"Crimenet: Neural structured learning using vision transformer for violence detection","volume":"161","author":"Rend\u00f3n-Segador","year":"2023","journal-title":"Neural Netw"},{"key":"10.1016\/j.compeleceng.2026.111256_b11","series-title":"Video vision transformers for violence detection","author":"Singh","year":"2022"},{"key":"10.1016\/j.compeleceng.2026.111256_b12","doi-asserted-by":"crossref","first-page":"43796","DOI":"10.1109\/ACCESS.2024.3380192","article-title":"VD-net: An edge vision-based surveillance system for violence detection","volume":"12","author":"Khan","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.compeleceng.2026.111256_b13","series-title":"2021 IEEE international conference on communication, networks and satellite","first-page":"195","article-title":"Data efficient video transformer for violence detection","author":"Abdali","year":"2021"},{"key":"10.1016\/j.compeleceng.2026.111256_b14","series-title":"2022 5th international conference on pattern recognition and artificial intelligence","first-page":"880","article-title":"End-to-end video violence detection with transformer","author":"Zhou","year":"2022"},{"key":"10.1016\/j.compeleceng.2026.111256_b15","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3564435","article-title":"Advanced detection of violence from video: Performance evaluation of transformer and state of the art of convolution of neural network transformer","author":"Alshalawi","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.compeleceng.2026.111256_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.113595","article-title":"From human and object interaction to threat detection: An interpretable threat detection method for human violence scenarios","volume":"166","author":"Wang","year":"2026","journal-title":"Eng Appl Artif Intell"},{"key":"10.1016\/j.compeleceng.2026.111256_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111987","article-title":"Skeleton-based multi-person action recognition towards real-world violence detection","volume":"161","author":"Truong","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"10.1016\/j.compeleceng.2026.111256_b18","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.compeleceng.2026.111256_b19","series-title":"Computer analysis of images and patterns: 14th international conference, CAIP 2011, seville, Spain, August 29-31, 2011, proceedings, part II 14","first-page":"332","article-title":"Violence detection in video using computer vision techniques","author":"Bermejo Nievas","year":"2011"},{"key":"10.1016\/j.compeleceng.2026.111256_b20","series-title":"2019 ninth international conference on intelligent computing and information systems","first-page":"80","article-title":"Violence recognition from videos using deep learning techniques","author":"Soliman","year":"2019"},{"key":"10.1016\/j.compeleceng.2026.111256_b21","series-title":"2020 25th international conference on pattern recognition","first-page":"4183","article-title":"RWF-2000: an open large scale video database for violence detection","author":"Cheng","year":"2021"},{"key":"10.1016\/j.compeleceng.2026.111256_b22","doi-asserted-by":"crossref","first-page":"160580","DOI":"10.1109\/ACCESS.2021.3131315","article-title":"Deep learning for automatic violence detection: Tests on the airtlab dataset","volume":"9","author":"Sernani","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.compeleceng.2026.111256_b23","series-title":"2017 14th IEEE international conference on 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.compeleceng.2026.111256_b24","doi-asserted-by":"crossref","unstructured":"Tran Du, Bourdev Lubomir, Fergus Rob, Torresani Lorenzo, Paluri Manohar. Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision. 2015, p. 4489\u201397.","DOI":"10.1109\/ICCV.2015.510"},{"key":"10.1016\/j.compeleceng.2026.111256_b25","first-page":"4000","article-title":"A combination of light pre-trained convolutional neural networks and long short-term memory for real-time violence detection in videos","volume":"400","author":"Abdullah","year":"2023","journal-title":"Methods"},{"issue":"8","key":"10.1016\/j.compeleceng.2026.111256_b26","doi-asserted-by":"crossref","first-page":"380","DOI":"10.3390\/info11080380","article-title":"Spatiotemporal convolutional neural network with convolutional block attention module for micro-expression recognition","volume":"11","author":"Chen","year":"2020","journal-title":"Information"},{"key":"10.1016\/j.compeleceng.2026.111256_b27","series-title":"2019 ninth international conference on intelligent computing and information systems","first-page":"80","article-title":"Violence recognition from videos using deep learning techniques","author":"Soliman","year":"2019"},{"key":"10.1016\/j.compeleceng.2026.111256_b28","series-title":"European conference on computer vision","first-page":"74","article-title":"Human interaction learning on 3d skeleton point clouds for video violence recognition","author":"Su","year":"2020"},{"key":"10.1016\/j.compeleceng.2026.111256_b29","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":"22","key":"10.1016\/j.compeleceng.2026.111256_b30","doi-asserted-by":"crossref","first-page":"61995","DOI":"10.1007\/s11042-023-15599-0","article-title":"Violence recognition on videos using two-stream 3d cnn with custom spatiotemporal crop","volume":"83","author":"Pratama","year":"2024","journal-title":"Multimedia Tools Appl"},{"issue":"67","key":"10.1016\/j.compeleceng.2026.111256_b31","doi-asserted-by":"crossref","first-page":"40","DOI":"10.4114\/intartif.vol24iss67pp40-50","article-title":"A temporal fusion approach for video classification with convolutional and LSTM neural networks applied to violence detection","volume":"24","author":"de Oliveira Lima","year":"2021","journal-title":"Intel Artif"},{"key":"10.1016\/j.compeleceng.2026.111256_b32","doi-asserted-by":"crossref","first-page":"76270","DOI":"10.1109\/ACCESS.2021.3083273","article-title":"Efficient spatio-temporal modeling methods for real-time violence recognition","volume":"9","author":"Kang","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.compeleceng.2026.111256_b33","series-title":"2021 IEEE international conference on image processing","first-page":"2593","article-title":"Violence detection from video under 2D spatio-temporal representations","author":"Chelali","year":"2021"},{"issue":"3","key":"10.1016\/j.compeleceng.2026.111256_b34","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1049\/cvi2.12162","article-title":"Violence 4D: Violence detection in surveillance using 4D convolutional neural networks","volume":"17","author":"Magdy","year":"2023","journal-title":"IET Comput Vis"},{"key":"10.1016\/j.compeleceng.2026.111256_b35","series-title":"Enhancing human action recognition and violence detection through deep learning audiovisual fusion","author":"Janani","year":"2024"},{"key":"10.1016\/j.compeleceng.2026.111256_b36","article-title":"Multimodal deep learning for violence detection: Vggish and MobileViT integration with knowledge distillation on jetson nano","author":"Swapnil","year":"2024","journal-title":"IEEE Open J Commun Soc"},{"key":"10.1016\/j.compeleceng.2026.111256_b37","series-title":"2019 ninth international conference on image processing theory, tools and applications","first-page":"1","article-title":"Vision-based fight detection from surveillance cameras","author":"Akt\u0131","year":"2019"},{"key":"10.1016\/j.compeleceng.2026.111256_b38","series-title":"2022 international conference on emerging techniques in computational intelligence","first-page":"121","article-title":"Violence detection using deep learning techniques","author":"Gupta","year":"2022"},{"key":"10.1016\/j.compeleceng.2026.111256_b39","series-title":"2022 IEEE world AI ioT congress (aIIoT)","first-page":"544","article-title":"Violence detection using computer vision approaches","author":"Talha","year":"2022"},{"key":"10.1016\/j.compeleceng.2026.111256_b40","article-title":"A shallow 3D convolutional neural network for violence detection in videos","volume":"26","author":"D\u00fcndar","year":"2024","journal-title":"Egypt Inform. J"},{"issue":"3","key":"10.1016\/j.compeleceng.2026.111256_b41","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1007\/s40313-021-00868-w","article-title":"Automated violence detection in video crowd using spider monkey-grasshopper optimization oriented optimal feature selection and deep neural network","volume":"33","author":"Naik","year":"2022","journal-title":"J Control Autom Electr Syst"},{"issue":"12","key":"10.1016\/j.compeleceng.2026.111256_b42","doi-asserted-by":"crossref","first-page":"4502","DOI":"10.3390\/s22124502","article-title":"Weakly supervised violence detection in surveillance video","volume":"22","author":"Choqueluque-Roman","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.compeleceng.2026.111256_b43","doi-asserted-by":"crossref","first-page":"15363","DOI":"10.1109\/ACCESS.2025.3531213","article-title":"Violence detection from industrial surveillance videos using deep learning","volume":"13","author":"Khan","year":"2025","journal-title":"IEEE Access"},{"issue":"3","key":"10.1016\/j.compeleceng.2026.111256_b44","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1007\/s10489-026-07122-3","article-title":"Video violence detection using pre-trained VGG19 combined with manual logic, LSTM layers and Bi-LSTM layers","volume":"56","author":"Negre","year":"2026","journal-title":"Appl Intell"},{"issue":"23","key":"10.1016\/j.compeleceng.2026.111256_b45","doi-asserted-by":"crossref","first-page":"9383","DOI":"10.3390\/s22239383","article-title":"Deep multi-scale features fusion for effective violence detection and control charts visualization","volume":"22","author":"Mumtaz","year":"2022","journal-title":"Sensors"},{"issue":"4","key":"10.1016\/j.compeleceng.2026.111256_b46","article-title":"A fully integrated violence detection system using CNN and LSTM.","volume":"11","author":"Sharma","year":"2021","journal-title":"Int J Electr Comput Eng (2088-8708)"},{"key":"10.1016\/j.compeleceng.2026.111256_b47","series-title":"2021 IEEE international conference on artificial intelligence in engineering and technology","first-page":"1","article-title":"Convolutional neural network-long short term memory based IOT node for violence detection","author":"AlDahoul","year":"2021"},{"key":"10.1016\/j.compeleceng.2026.111256_b48","first-page":"05013","article-title":"Long-term recurrent convolutional network violent behaviour recognition with attention mechanism","volume":"vol. 336","author":"Liang","year":"2021"},{"issue":"1","key":"10.1016\/j.compeleceng.2026.111256_b49","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.13474","article-title":"Fight detection with spatial and channel wise attention-based ConvLSTM model","volume":"41","author":"Chaturvedi","year":"2024","journal-title":"Expert Syst"},{"issue":"10","key":"10.1016\/j.compeleceng.2026.111256_b50","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0276939","article-title":"Lightweight mobile network for real-time violence recognition","volume":"17","author":"Zhang","year":"2022","journal-title":"PLoS One"},{"key":"10.1016\/j.compeleceng.2026.111256_b51","doi-asserted-by":"crossref","first-page":"18772","DOI":"10.1109\/ACCESS.2023.3245521","article-title":"Toward fast and accurate violence detection for automated video surveillance applications","volume":"11","author":"Huszar","year":"2023","journal-title":"IEEE Access"},{"issue":"6","key":"10.1016\/j.compeleceng.2026.111256_b52","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.3390\/s22062216","article-title":"Efficient violence detection in surveillance","volume":"22","author":"Vijeikis","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.compeleceng.2026.111256_b53","series-title":"EPIA conference on artificial intelligence","first-page":"290","article-title":"Comparison of transfer learning behaviour in violence detection with different public datasets","author":"Dur\u00e3es","year":"2021"},{"key":"10.1016\/j.compeleceng.2026.111256_b54","series-title":"2021 6th international conference on image, vision and computing","first-page":"55","article-title":"A frame-based feature model for violence detection from surveillance cameras using convlstm network","author":"Mugunga","year":"2021"},{"issue":"12","key":"10.1016\/j.compeleceng.2026.111256_b55","doi-asserted-by":"crossref","first-page":"11001","DOI":"10.1007\/s11042-024-19388-1","article-title":"An ensemble based approach for violence detection in videos using deep transfer learning","volume":"84","author":"Kaur","year":"2025","journal-title":"Multimedia Tools Appl"},{"key":"10.1016\/j.compeleceng.2026.111256_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127337","article-title":"SUSAN: A deep learning-based architecture for violence detection against women in surveillance videos","volume":"280","author":"Andrade","year":"2025","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.compeleceng.2026.111256_b57","series-title":"2022 IEEE 5th international conference on image processing applications and systems","first-page":"1","article-title":"Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep CNNs, RNNs and attention-based mechanisms","author":"Siddique","year":"2022"}],"container-title":["Computers and Electrical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0045790626003289?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0045790626003289?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T12:24:45Z","timestamp":1780835085000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0045790626003289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":57,"alternative-id":["S0045790626003289"],"URL":"https:\/\/doi.org\/10.1016\/j.compeleceng.2026.111256","relation":{},"ISSN":["0045-7906"],"issn-type":[{"value":"0045-7906","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Context-Aware Multi-Scale Transformers with dual-stage multiple instance learning for violence detection","name":"articletitle","label":"Article Title"},{"value":"Computers and Electrical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compeleceng.2026.111256","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":"111256"}}