{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T03:13:19Z","timestamp":1794971599732,"version":"4.9.1"},"reference-count":91,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"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":["Artif Intell Rev"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s10462-022-10285-3","type":"journal-article","created":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T03:28:59Z","timestamp":1665199739000},"page":"4641-4666","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["An overview of violence detection techniques: current challenges and future directions"],"prefix":"10.1007","volume":"56","author":[{"given":"Nadia","family":"Mumtaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naveed","family":"Ejaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shabana","family":"Habib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Muhammad","family":"Mohsin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prayag","family":"Tiwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shahab S.","family":"Band","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3020-3947","authenticated-orcid":false,"given":"Neeraj","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,8]]},"reference":[{"key":"10285_CR1","doi-asserted-by":"crossref","unstructured":"Abdali A-MR, Al-Tuma RF (2019) Robust real-time violence detection in video using CNN and LSTM. In: 2019 2nd scientific conference of computer sciences (SCCS). IEEE, Piscataway, pp 104\u2013108","DOI":"10.1109\/SCCS.2019.8852616"},{"issue":"4","key":"10285_CR2","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1080\/08839514.2020.1723876","volume":"34","author":"S Accattoli","year":"2020","unstructured":"Accattoli S, Sernani P, Falcionelli N, Mekuria DN, Dragoni AF (2020) Violence detection in videos by combining 3D convolutional neural networks and support vector machines. Appl Artif Intell 34(4):329\u2013344","journal-title":"Appl Artif Intell"},{"key":"10285_CR3","unstructured":"Agarwal R, Machado MC, Castro PS, Bellemare MG (2021) Contrastive behavioral similarity embeddings for generalization in reinforcement learning. arXiv preprint. arXiv:2101.05265"},{"issue":"1","key":"10285_CR4","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1007\/s00521-016-2363-z","volume":"28","author":"M Al-Nawashi","year":"2017","unstructured":"Al-Nawashi M, Al-Hazaimeh OM, Saraee M (2017) A novel framework for intelligent surveillance system based on abnormal human activity detection in academic environments. Neural Comput Appl 28(1):565\u2013572","journal-title":"Neural Comput Appl"},{"key":"10285_CR5","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"Alejandro Barredo Arrieta","year":"2020","unstructured":"Arrieta AB, D\u00edaz-Rodr\u00edguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, Garc\u00eda S, Gil- L\u00f3pez S, Molina D, Benjamins R et al (2020) Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai. Information Fusion 58:82\u2013115","journal-title":"Information Fusion"},{"key":"10285_CR6","unstructured":"Bertasius G, Wang H, Torresani L (2021) Is space-time attention all you need for video understanding? arXiv preprint. arXiv:2102.05095"},{"key":"10285_CR7","doi-asserted-by":"crossref","unstructured":"Bilinski P, Bremond F (2016) Human violence recognition and detection in surveillance videos. In: 2016 13th IEEE International conference on advanced video and signal based surveillance (AVSS). IEEE, Piscataway, pp 30\u201336","DOI":"10.1109\/AVSS.2016.7738019"},{"key":"10285_CR8","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) 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":"10285_CR9","doi-asserted-by":"crossref","unstructured":"Chang C-W, Chang C-Y, Lin Y-Y (2022) A hybrid CNN and LSTM-based deep learning model for abnormal behavior detection. Multimedia Tools Appl 81(2):1\u201319","DOI":"10.1007\/s11042-021-11887-9"},{"key":"10285_CR10","unstructured":"Chen D, Wactlar H, Chen M, Gao C, Bharucha A, Hauptmann A (2008) Recognition of aggressive human behavior using binary local motion descriptors. In: 2008 30th annual international conference of the IEEE engineering in medicine and biology society. IEEE, Piscataway, pp 5238\u20135241"},{"key":"10285_CR11","doi-asserted-by":"crossref","unstructured":"Chen L-H, Hsu H-W, Wang L-Y, Su C-W (2011) Violence detection in movies. In: 2011 Eighth international conference computer graphics, imaging and visualization. IEEE, Piscataway, pp 119\u2013124","DOI":"10.1109\/CGIV.2011.14"},{"key":"10285_CR12","doi-asserted-by":"crossref","unstructured":"Cheng M, Cai K, Li M (2021) Rwf-2000: an open large scale video database for violence detection. In: 2020 25th International conference on pattern recognition (ICPR). IEEE, Piscataway, pp 4183\u20134190","DOI":"10.1109\/ICPR48806.2021.9412502"},{"issue":"3","key":"10285_CR13","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/MCOM.2019.1800644","volume":"57","author":"Qimei Cui","year":"2019","unstructured":"Cui Q, Gong Z, Ni W, Hou Y, Chen X, Tao X, Zhang P (2019) Stochastic online learning for mobile edge computing: learning from changes. IEEE Commun Mag 57(3):63\u201369","journal-title":"IEEE Communications Magazine"},{"key":"10285_CR14","doi-asserted-by":"publisher","first-page":"107561","DOI":"10.1016\/j.patcog.2020.107561","volume":"108","author":"L Minh Dang","year":"2020","unstructured":"Dang LM, Min K, Wang H, Piran MJ, Lee CH, Moon H (2020) Sensor-based and vision-based human activity recognition: a comprehensive survey. Pattern Recogn 108:107561","journal-title":"Pattern Recognition"},{"key":"10285_CR15","doi-asserted-by":"crossref","unstructured":"Datta A, Shah M, Lobo NDV 2002) Person-on-person violence detection in video data. In: Object recognition supported by user interaction for service robots, vol 1. IEEE, Piscataway, pp 433\u2013438","DOI":"10.1109\/ICPR.2002.1044748"},{"key":"10285_CR16","doi-asserted-by":"crossref","unstructured":"De\u00a0Souza FD, Chavez GC, do\u00a0Valle EA Jr, Ara\u00fajo AA (2010) Violence detection in video using spatio-temporal features. In: 2010 23rd SIBGRAPI conference on graphics, patterns and images. IEEE, Piscataway, pp 224\u2013230","DOI":"10.1109\/SIBGRAPI.2010.38"},{"issue":"2","key":"10285_CR17","doi-asserted-by":"publisher","first-page":"e0262538","DOI":"10.1371\/journal.pone.0262538","volume":"17","author":"Nabamallika Dehingia","year":"2022","unstructured":"Dehingia N, Dey AK, McDougal L, McAuley J, Singh A, Raj A (2022) Help seeking behavior by women experiencing intimate partner violence in India: a machine learning approach to identifying risk factors. PLoS ONE 17(2):e0262538","journal-title":"PloS one"},{"key":"10285_CR18","unstructured":"Deniz O, Serrano I, Bueno G, Kim T-K (2014) Fast violence detection in video. In: 2014 international conference on computer vision theory and applications (VISAPP), vol\u00a02. IEEE, Piscataway, pp 478\u2013485"},{"key":"10285_CR19","doi-asserted-by":"crossref","unstructured":"Dhiman C, Vishwakarma DK (2017) High dimensional abnormal human activity recognition using histogram oriented gradients and zernike moments. In: 2017 IEEE International conference on computational intelligence and computing research (ICCIC). IEEE, Piscataway, pp 1\u20134","DOI":"10.1109\/ICCIC.2017.8524372"},{"key":"10285_CR20","doi-asserted-by":"crossref","unstructured":"Ding C, Fan S, Zhu M, Feng W, Jia B (2014) Violence detection in video by using 3d convolutional neural networks. In: International symposium on visual computing. Springer, Cham, pp 551\u2013558","DOI":"10.1007\/978-3-319-14364-4_53"},{"key":"10285_CR21","doi-asserted-by":"crossref","unstructured":"Dogru O, Velswamy K, Huang B (2021) Actor\u2013critic reinforcement learning and application in developing computer-vision-based interface tracking. Engineering 7(9):1248\u20131261","DOI":"10.1016\/j.eng.2021.04.027"},{"key":"10285_CR22","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et\u00a0al (2020) An image is worth 16\u00d716 words: transformers for image recognition at scale. arXiv preprint. arXiv:2010.11929"},{"key":"10285_CR23","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.comnet.2019.01.028","volume":"151","author":"E Fenil","year":"2019","unstructured":"Fenil E, Manogaran Gunasekaran, Vivekananda GN, Thanjaivadivel T, Jeeva S, Ahilan A et al (2019) Real time violence detection framework for football stadium comprising of big data analysis and deep learning through bidirectional LSTM. Comput Netw 151:191\u2013200","journal-title":"Computer Networks"},{"issue":"1","key":"10285_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-021-01264-9","volume":"33","author":"David Freire-Obreg\u00f3n","year":"2022","unstructured":"Freire-Obreg\u00f3n D, Barra P, Castrill\u00f3n-Santana M, De Marsico M (2022) Inflated 3D ConvNet context analysis for violence detection. Mach Vis Appl 33(1):1\u201313","journal-title":"Machine Vision and Applications"},{"key":"10285_CR25","doi-asserted-by":"crossref","unstructured":"Fu EY, Leong HV, Ngai G, Chan SCF (2017) Automatic fight detection in surveillance videos. In: 14th International conference on advances in mobile computing and multimedia (MoMM 2016)\u2014proceedings. Association for Computing Machinery, New York, pp 225\u2013234","DOI":"10.1145\/3007120.3007129"},{"key":"10285_CR27","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.imavis.2016.01.006","volume":"48","author":"Yuan Gao","year":"2016","unstructured":"Gao Y, Liu H, Sun X, Wang C, Liu Y (2016) Violence detection using oriented violent flows. Image Vis Comput 48:37\u201341","journal-title":"Image and vision computing"},{"key":"10285_CR26","doi-asserted-by":"publisher","unstructured":"Gao M, Zheng F, Yu JJ, Shan C, Ding G, Han J (2022) Deep learning for video object segmentation: a review. Artif Intell Rev. https:\/\/doi.org\/10.1007\/s10462-022-10176-7","DOI":"10.1007\/s10462-022-10176-7"},{"key":"10285_CR28","doi-asserted-by":"crossref","unstructured":"Gracia IS, Suarez OD, Garcia GB, Kim TK (2015) Fast fight detection. PLoS ONE 10(4):e0120448","DOI":"10.1371\/journal.pone.0120448"},{"key":"10285_CR29","doi-asserted-by":"publisher","unstructured":"Hafiz AM, Parah SA, Bhat RA (2021) Reinforcement learning applied to machine vision: state of the art. Int J Multimedia Inf Retrieval. https:\/\/doi.org\/10.1007\/s13735-021-00209-2","DOI":"10.1007\/s13735-021-00209-2"},{"key":"10285_CR30","doi-asserted-by":"crossref","unstructured":"Hassner T, Itcher Y, Kliper-Gross O (2012) Violent flows: real-time detection of violent crowd behavior. In: 2012 IEEE computer society conference on computer vision and pattern recognition workshops. IEEE, Piscataway, pp 1\u20136","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"10285_CR31","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint. arXiv:1704.04861"},{"issue":"1","key":"10285_CR33","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TII.2019.2929228","volume":"16","author":"Tanveer Hussain","year":"2019","unstructured":"Hussain T, Muhammad K, Ullah A, Cao Z, Baik SW, de Albuquerque VHC (2019) Cloud-assisted multiview video summarization using cnn and bidirectional LSTM. IEEE Trans Ind Inf 16(1):77\u201386","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10285_CR34","doi-asserted-by":"crossref","unstructured":"Hussain T, Muhammad K, Ullah A, Del\u00a0Ser J, Gandomi AH, Sajjad M, Baik SW, de\u00a0Albuquerque VHC (2020) Multi-view summarization and activity recognition meet edge computing in IoT environments. IEEE Internet Things J 8:9634\u20139644","DOI":"10.1109\/JIOT.2020.3027483"},{"key":"10285_CR32","doi-asserted-by":"publisher","unstructured":"Hussain A, Hussain T, Ullah W, Baik SW (2022) Vision transformer and deep sequence learning for human activity recognition in surveillance videos. Comput Intell Neurosci. https:\/\/doi.org\/10.1155\/2022\/3454167","DOI":"10.1155\/2022\/3454167"},{"key":"10285_CR35","doi-asserted-by":"crossref","unstructured":"Jin Y, Jiao L, Qian Z, Zhang S, Lu S (2021) Learning for learning: predictive online control of federated learning with edge provisioning. In: IEEE INFOCOM 2021\u2014IEEE conference on computer communications. IEEE, Piscataway, pp 1\u201310","DOI":"10.1109\/INFOCOM42981.2021.9488733"},{"key":"10285_CR36","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici C, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"issue":"22","key":"10285_CR37","doi-asserted-by":"publisher","first-page":"4963","DOI":"10.3390\/app9224963","volume":"9","author":"Samee Ullah Khan","year":"2019","unstructured":"Khan SU, Haq IU, Rho S, Baik SW, Lee MY (2019) Cover the violence: a novel deep-learning-based approach towards violence-detection in movies. Appl Sci 9(22):4963","journal-title":"Applied Sciences"},{"key":"10285_CR40","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 586\u2013590","DOI":"10.1145\/2964284.2967289"},{"key":"10285_CR38","doi-asserted-by":"crossref","unstructured":"Li J, Jiang X, Sun T, Xu K (2019) Efficient violence detection using 3d convolutional neural networks. In: 2019 16th IEEE international conference on advanced video and signal based surveillance (AVSS). IEEE, Piscataway, pp 1\u20138","DOI":"10.1109\/AVSS.2019.8909883"},{"key":"10285_CR39","doi-asserted-by":"crossref","unstructured":"Li X, Wang Y, Zhou Z, Qiao Y (2020) SmallBigNet: integrating core and contextual views for video classification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1092\u20131101","DOI":"10.1109\/CVPR42600.2020.00117"},{"issue":"2","key":"10285_CR41","doi-asserted-by":"publisher","first-page":"179","DOI":"10.18280\/ria.340208","volume":"34","author":"BH Lohithashva","year":"2020","unstructured":"Lohithashva BH, Manjunath Aradhya VN, Guru DS (2020) Violent video event detection based on integrated LBP and GLCM texture features. Rev Intell Artif 34(2):179\u2013187","journal-title":"Revue d\u2019Intelligence Artificielle"},{"issue":"16","key":"10285_CR42","doi-asserted-by":"publisher","first-page":"3542","DOI":"10.3390\/s19163542","volume":"19","author":"Eleftherios Lygouras","year":"2019","unstructured":"Lygouras E, Santavas N, Taitzoglou A, Tarchanidis K, Mitropoulos A, Gasteratos A (2019) Unsupervised human detection with an embedded vision system on a fully autonomous UAV for search and rescue operations. Sensors 19(16):3542","journal-title":"Sensors"},{"key":"10285_CR43","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.patrec.2017.04.015","volume":"92","author":"Amira Ben Mabrouk","year":"2017","unstructured":"Mabrouk AB, Zagrouba E (2017) Spatio-temporal feature using optical flow based distribution for violence detection. Pattern Recogn Lett 92:62\u201367","journal-title":"Pattern Recognition Letters"},{"key":"10285_CR44","doi-asserted-by":"crossref","unstructured":"Mahadevan V, Li W, Bhalodia V, Vasconcelos N (2010) Anomaly detection in crowded scenes. In: 2010 IEEE Computer Society conference on computer vision and pattern recognition. IEEE, Piscataway, pp 1975\u20131981","DOI":"10.1109\/CVPR.2010.5539872"},{"key":"10285_CR45","doi-asserted-by":"crossref","unstructured":"Meng Z, Yuan J, Li Z (2017) Trajectory-pooled deep convolutional networks for violence detection in videos. In: International conference on computer vision systems. Springer, Cham, pp 437\u2013447","DOI":"10.1007\/978-3-319-68345-4_39"},{"key":"10285_CR46","doi-asserted-by":"crossref","unstructured":"Mishra AA, Srinivasa G (2018) Automated detection of fighting styles using localized action features. In: 2018 2nd International conference on inventive systems and control (ICISC). IEEE, Piscataway, pp 1385\u20131389","DOI":"10.1109\/ICISC.2018.8399036"},{"key":"10285_CR47","doi-asserted-by":"crossref","unstructured":"Mu G, Cao H, Jin Q (2016) Violent scene detection using convolutional neural networks and deep audio features. In: Chinese conference on pattern recognition. Springer, Singapore, pp 451\u2013463","DOI":"10.1007\/978-981-10-3005-5_37"},{"issue":"3","key":"10285_CR48","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1093\/comjnl\/bxaa061","volume":"65","author":"Aqib Mumtaz","year":"2022","unstructured":"Mumtaz A, Bux\u00a0SA, Habib Z (2022) Fast learning through deep multi-net CNN model for violence recognition in video surveillance. Comput J 65(3):457\u2013472","journal-title":"The Computer Journal"},{"key":"10285_CR49","doi-asserted-by":"publisher","unstructured":"Naik AJ, Gopalakrishna MT (2022) Automated violence detection in video crowd using spider monkey-grasshopper optimization oriented optimal feature selection and deep neural network. J Control Autom Electr Syst. https:\/\/doi.org\/10.1007\/s40313-021-00868-w","DOI":"10.1007\/s40313-021-00868-w"},{"key":"10285_CR50","doi-asserted-by":"crossref","unstructured":"Nguyen NT, Phung DQ, Venkatesh S, Bui H (2005) Learning and detecting activities from movement trajectories using the hierarchical hidden markov model. In: 2005 IEEE Computer Society conference on computer vision and pattern recognition (CVPR\u201905), vol 2. IEEE, Piscataway, pp 955\u2013960","DOI":"10.1109\/CVPR.2005.203"},{"key":"10285_CR51","doi-asserted-by":"crossref","unstructured":"Nievas EB, Suarez OD, Garc\u00eda GB, Sukthankar R (2011) Violence detection in video using computer vision techniques. In: International conference on computer analysis of images and patterns. Springer, Berlin, pp 332\u2013339","DOI":"10.1007\/978-3-642-23678-5_39"},{"issue":"3","key":"10285_CR52","doi-asserted-by":"publisher","first-page":"2259","DOI":"10.1007\/s10462-020-09904-8","volume":"54","author":"Preksha Pareek","year":"2021","unstructured":"Pareek P, Thakkar A (2021) A survey on video-based human action recognition: recent updates, datasets, challenges, and applications. Artif Intell Rev 54(3):2259\u20132322","journal-title":"Artificial Intelligence Review"},{"key":"10285_CR53","doi-asserted-by":"crossref","unstructured":"Pavlidis NG, Tasoulis OK, Plagianakos Vassilis\u00a0P, Nikiforidis G, Vrahatis MN (2005) Spiking neural network training using evolutionary algorithms. In: Proceedings of 2005 IEEE international joint conference on neural networks, vol 4. IEEE, Piscataway, pp 2190\u20132194","DOI":"10.1109\/IJCNN.2005.1556240"},{"key":"10285_CR54","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yao T, Mei T (2017) Learning spatio-temporal representation with pseudo-3D residual networks. In: Proceedings of the IEEE international conference on computer vision, pp 5533\u20135541","DOI":"10.1109\/ICCV.2017.590"},{"key":"10285_CR55","doi-asserted-by":"publisher","unstructured":"Ramanujam E, Perumal T, Padmavathi S (2021) Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review. IEEE Sensors J. https:\/\/doi.org\/10.1109\/JSEN.2021.3069927","DOI":"10.1109\/JSEN.2021.3069927"},{"key":"10285_CR56","unstructured":"Rojat T, Puget R, Filliat D, Del\u00a0Ser J, Gelin R, D\u00edaz-Rodr\u00edguez N (2021) Explainable artificial intelligence (XAI) on timeseries data: a survey. arXiv preprint. arXiv:2104.00950"},{"key":"10285_CR57","doi-asserted-by":"crossref","unstructured":"Roka S, Diwakar M, Karanwal S (2022) A review in anomalies detection using deep learning. In: Proceedings of third international conference on sustainable computing. Springer, Singapore, pp 329\u2013338","DOI":"10.1007\/978-981-16-4538-9_33"},{"key":"10285_CR58","doi-asserted-by":"crossref","unstructured":"Roman DGC, Ch\u00e1vez GC (2020) Violence detection and localization in surveillance video. In: 2020 33rd SIBGRAPI Conference on graphics, patterns and images (SIBGRAPI). IEEE, Piscataway, pp 248\u2013255","DOI":"10.1109\/SIBGRAPI51738.2020.00041"},{"key":"10285_CR59","doi-asserted-by":"crossref","unstructured":"Ryoo MS, Aggarwal JK (2009) Spatio-temporal relationship match: video structure comparison for recognition of complex human activities. In: IEEE International conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"10285_CR60","doi-asserted-by":"publisher","first-page":"107099","DOI":"10.1016\/j.patcog.2019.107099","volume":"99","author":"A Sasithradevi","year":"2020","unstructured":"Sasithradevi A, Mansoor Roomi S Mohamed (2020) Video classification and retrieval through spatio-temporal radon features. Pattern Recogn 99:107099","journal-title":"Pattern Recognition"},{"issue":"10","key":"10285_CR61","doi-asserted-by":"publisher","first-page":"4787","DOI":"10.1109\/TIP.2018.2845742","volume":"27","author":"Ismael Serrano","year":"2018","unstructured":"Serrano I, Deniz O, Espinosa-Aranda JL, Bueno G (2018) Fight recognition in video using hough forests and 2D convolutional neural network. IEEE Trans Image Process 27(10):4787\u20134797","journal-title":"IEEE Transactions on Image Processing"},{"issue":"5","key":"10285_CR62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11704-019-8229-7","volume":"14","author":"Ling Shen","year":"2020","unstructured":"Shen L, Hong R, Hao Y (2020) Advance on large scale near-duplicate video retrieval. Front Comput Sci 14(5):1\u201324","journal-title":"Frontiers of Computer Science"},{"key":"10285_CR63","unstructured":"Sonar A, Pacelli V, Majumdar A (2021) Invariant policy optimization: towards stronger generalization in reinforcement learning. In: Proceedings of the 3rd conference on Learning for dynamics and control. PMLR, pp 21\u201333"},{"key":"10285_CR64","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.ins.2018.02.065","volume":"447","author":"Donghui Song","year":"2018","unstructured":"Song D, Kim C, Park S-K (2018) A multi-temporal framework for high-level activity analysis: violent event detection in visual surveillance. Inf Sci 447:83\u2013103","journal-title":"Information Sciences"},{"key":"10285_CR65","doi-asserted-by":"publisher","first-page":"103557","DOI":"10.1016\/j.engappai.2020.103557","volume":"90","author":"Newton Spola\u00f4r","year":"2020","unstructured":"Spola\u00f4r N, Lee HD, Takaki WSR, Ensina LA, Coy CSR, Wu FC (2020) A systematic review on content-based video retrieval. Eng Appl Artif Intell 90:103557","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10285_CR66","doi-asserted-by":"crossref","unstructured":"Sudhakaran S, Lanz O (2017) 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). IEEE, Piscataway, pp 1\u20136","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"10285_CR67","doi-asserted-by":"crossref","unstructured":"Suleiman A, Chen Y-H, Emer J, Sze V (2017) Towards closing the energy gap between hog and cnn features for embedded vision. In: 2017 IEEE International symposium on circuits and systems (ISCAS). IEEE, Piscataway, pp 1\u20134","DOI":"10.1109\/ISCAS.2017.8050341"},{"key":"10285_CR68","doi-asserted-by":"crossref","unstructured":"Sultani W, Chen C, Shah M (2018) Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6479\u20136488","DOI":"10.1109\/CVPR.2018.00678"},{"issue":"01","key":"10285_CR69","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1142\/S2196888820500013","volume":"7","author":"Shakil Ahmed Sumon","year":"2020","unstructured":"Sumon SA, Goni R, Hashem NB, Rahman RM (2020) Violence detection by pretrained modules with different deep learning approaches. Vietnam J Comput Sci 7(01):19\u201340","journal-title":"Vietnam Journal of Computer Science"},{"key":"10285_CR70","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"10285_CR71","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Feiszli M (2019) Video classification with channel-separated convolutional networks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 5552\u20135561","DOI":"10.1109\/ICCV.2019.00565"},{"key":"10285_CR72","doi-asserted-by":"crossref","unstructured":"Traor\u00e9 A, Akhloufi MA (2020) Violence detection in videos using deep recurrent and convolutional neural networks. In: 2020 IEEE International conference on systems, man, and cybernetics (SMC). IEEE, Piscataway, pp 154\u2013159","DOI":"10.1109\/SMC42975.2020.9282971"},{"issue":"12","key":"10285_CR73","doi-asserted-by":"publisher","first-page":"9692","DOI":"10.1109\/TIE.2018.2881943","volume":"66","author":"Amin Ullah","year":"2018","unstructured":"Ullah A, Muhammad K, Del Ser J, Baik SW, de Albuquerque VHC (2018) Activity recognition using temporal optical flow convolutional features and multilayer LSTM. IEEE Trans Ind Electron 66(12):9692\u20139702","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"11","key":"10285_CR76","doi-asserted-by":"publisher","first-page":"2472","DOI":"10.3390\/s19112472","volume":"19","author":"Fath U Min Ullah","year":"2019","unstructured":"Ullah FUM, Ullah A, Muhammad K, Haq IU, Baik SW (2019) Violence detection using spatiotemporal features with 3d convolutional neural network. Sensors 19(11):2472","journal-title":"Sensors"},{"key":"10285_CR74","doi-asserted-by":"crossref","unstructured":"Ullah A, Muhammad K, Haydarov K, Haq IU, Lee M, Baik SW (2020a) One-shot learning for surveillance anomaly recognition using siamese 3D CNN. In: 2020 International joint conference on neural networks (IJCNN). IEEE, Piscataway, pp 1\u20138","DOI":"10.1109\/IJCNN48605.2020.9207595"},{"issue":"11","key":"10285_CR79","doi-asserted-by":"publisher","first-page":"16979","DOI":"10.1007\/s11042-020-09406-3","volume":"80","author":"Waseem Ullah","year":"2020","unstructured":"Ullah W, Ullah A, Haq IU, Muhammad K, Sajjad M, Baik SW (2020b) CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks. Multimedia Tools Appl 80(11):16979\u201316995","journal-title":"Multimedia Tools and Applications"},{"key":"10285_CR75","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.neucom.2019.12.151","volume":"435","author":"Amin Ullah","year":"2021","unstructured":"Ullah A, Muhammad K, Hussain T, Baik SW (2021a) Conflux LSTMs network: a novel approach for multi-view action recognition. Neurocomputing 435:321\u2013329","journal-title":"Neurocomputing"},{"key":"10285_CR77","doi-asserted-by":"publisher","unstructured":"Ullah FUM, Muhammad K, Haq IU, Khan N, Heidari AAA, Baik SW, Albuquerque V (2021b) AI assisted edge vision for violence detection in IoT based industrial surveillance networks. IEEE Trans Ind Inf. https:\/\/doi.org\/10.1109\/TII.2021.3116377","DOI":"10.1109\/TII.2021.3116377"},{"key":"10285_CR78","doi-asserted-by":"publisher","unstructured":"Ullah FUM, Obaidat MS, Muhammad K, Ullah A, Baik SW, Cuzzolin F, Rodrigues JJP, de\u00a0Albuquerque VHC (2021c) An intelligent system for complex violence pattern analysis and detection. Int J Intell Syst. https:\/\/doi.org\/10.1002\/int.22537","DOI":"10.1002\/int.22537"},{"issue":"11","key":"10285_CR80","doi-asserted-by":"publisher","first-page":"16979","DOI":"10.1007\/s11042-020-09406-3","volume":"80","author":"Waseem Ullah","year":"2021","unstructured":"Ullah W, Ullah A, Haq IU, Muhammad K, Sajjad M, Baik SW (2021d) CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks. Multimedia Tools Appl 80(11):16979\u201316995","journal-title":"Multimedia Tools and Applications"},{"key":"10285_CR82","doi-asserted-by":"crossref","unstructured":"Wang L, Li W, Li W, Van\u00a0Gool L (2018) Appearance-and-relation networks for video classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1430\u20131439","DOI":"10.1109\/CVPR.2018.00155"},{"key":"10285_CR83","doi-asserted-by":"crossref","unstructured":"Wang W, Zhou T, Porikli F, Crandall D, Van\u00a0Gool L (2021) A survey on deep learning technique for video segmentation. arXiv preprint. arXiv:2107.01153","DOI":"10.1109\/TPAMI.2022.3225573"},{"issue":"8","key":"10285_CR81","doi-asserted-by":"publisher","first-page":"2811","DOI":"10.3390\/s21082811","volume":"21","author":"Ullah Waseem","year":"2021","unstructured":"Waseem U, Amin U, Tanveer H, Khan ZA, Baik SW (2021e) An efficient anomaly recognition framework using an attention residual lstm in surveillance videos. Sensors 21(8):2811","journal-title":"Sensors"},{"key":"10285_CR84","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107382","volume":"107","author":"Wu Jiaxin","year":"2020","unstructured":"Wu J, Zhong S, Liu Y (2020) Dynamic graph convolutional network for multi-video summarization. Pattern Recogn 107:107382","journal-title":"Pattern Recognition"},{"key":"10285_CR85","doi-asserted-by":"crossref","unstructured":"Xia Q, Zhang P, Wang JJ, Tian M, Fei C (2018) Real time violence detection based on deep spatio-temporal features. In: Chinese conference on biometric recognition. Springer, Cham, pp 157\u2013165","DOI":"10.1007\/978-3-319-97909-0_17"},{"key":"10285_CR86","doi-asserted-by":"crossref","unstructured":"Xu L, Gong C, Yang J, Wu W, Yao L (2014) Violent video detection based on mosift feature and sparse coding. In: 2014 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, Piscataway, pp 3538\u20133542","DOI":"10.1109\/ICASSP.2014.6854259"},{"key":"10285_CR87","unstructured":"Yue-Hei\u00a0NJ, Hausknecht M, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G (2015) Beyond short snippets: deep networks for video classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4694\u20134702"},{"key":"10285_CR88","doi-asserted-by":"crossref","unstructured":"Yun K, Honorio J, Chattopadhyay D, Berg TL, Samaras D (2012) Two-person interaction detection using body-pose features and multiple instance learning. In: 2012 IEEE Computer Society conference on computer vision and pattern recognition workshops. IEEE, Piscataway, pp 28\u201335","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"10285_CR89","unstructured":"Zaremba W, Sutskever I, Vinyals O (2014) Recurrent neural network regularization. arXiv preprint. arXiv:1409.2329"},{"issue":"12","key":"10285_CR90","doi-asserted-by":"publisher","first-page":"7327","DOI":"10.1007\/s11042-015-2648-8","volume":"75","author":"Tao Zhang","year":"2016","unstructured":"Zhang T, Yang Z, Jia W, Yang B, Yang J, He X (2016) A new method for violence detection in surveillance scenes. Multimedia Tools Appl 75(12):7327\u20137349","journal-title":"Multimedia Tools and Applications"},{"key":"10285_CR91","doi-asserted-by":"crossref","unstructured":"Zhang Z, Lu X, Cao G, Yang Y, Jiao L, Liu F (2021) ViT-YOLO: transformer-based YOLO for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2799\u20132808","DOI":"10.1109\/ICCVW54120.2021.00314"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-022-10285-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-022-10285-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-022-10285-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,5]],"date-time":"2024-10-05T10:58:25Z","timestamp":1728125905000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-022-10285-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,8]]},"references-count":91,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["10285"],"URL":"https:\/\/doi.org\/10.1007\/s10462-022-10285-3","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,8]]},"assertion":[{"value":"8 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}