{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T20:57:44Z","timestamp":1774990664828,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100017407","name":"Universidad Internacional de La Rioja","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100017407","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Video violence detection using artificial intelligence plays a key role in public safety applications. Although convolutional and recurrent neural networks are widely adopted for this task, the actual contribution of temporal modeling over strong frame-level representations remains insufficiently analyzed. This work provides a systematic study of video violence detection models under a unified experimental framework. We investigate whether violence can be reliably detected from individual frames without explicit temporal modeling, evaluate the effectiveness of combining CNNs with LSTM and Bi-LSTM layers, and analyze the impact of architectural and hyperparameter choices, including neuron configuration and backbone selection (VGG-16 vs. VGG-19). Experiments are conducted on three widely used benchmark datasets. Our results show that frame-level analysis using a pre-trained VGG-19 network, combined with a simple aggregation strategy, achieves competitive performance, reaching 95% accuracy on Hockey Fights and 96% on Violent Flow. While Bi-LSTM layers can provide moderate improvements of up to 4% over standard LSTM models in certain datasets, these gains are not consistent across all scenarios. Furthermore, variations in hyperparameter configurations do not systematically lead to improved performance. Overall, this study highlights that increased architectural complexity does not always translate into better results and that, in several cases, simple frame-based approaches can rival more complex temporal models. These findings provide practical insights into the cost\u2013benefit trade-off of temporal modeling for video-based violence detection.<\/jats:p>","DOI":"10.1007\/s10489-026-07122-3","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T12:48:55Z","timestamp":1770122935000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Video violence detection using pre-trained VGG19 combined with manual logic, LSTM layers and Bi-LSTM layers"],"prefix":"10.1007","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8372-7572","authenticated-orcid":false,"given":"Pablo","family":"Negre","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6599-0186","authenticated-orcid":false,"given":"Ricardo S.","family":"Alonso","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8175-2201","authenticated-orcid":false,"given":"Javier","family":"Prieto","sequence":"additional","affiliation":[]},{"given":"Oscar","family":"Garc\u00eda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"7122_CR1","doi-asserted-by":"crossref","unstructured":"Muarifah A, Mashar R, Hashim IHM, Rofiah NH, Oktaviani F (2022) Aggression in adolescents: the role of mother-child attachment and self-esteem. Behav Sci 12(5)","DOI":"10.3390\/bs12050147"},{"key":"7122_CR2","doi-asserted-by":"publisher","first-page":"103223","DOI":"10.1016\/j.cities.2021.103223","volume":"115","author":"D Long","year":"2021","unstructured":"Long D, Liu L, Xu M, Feng J, Chen J, He L (2021) Ambient population and surveillance cameras: the guardianship role in street robbers\u2019 crime location choice. Cities 115:103223","journal-title":"Cities"},{"issue":"5","key":"7122_CR3","first-page":"1319","volume":"3","author":"SZ Nurisma","year":"2023","unstructured":"Nurisma SZ, Astuti B (2023) Peace sociodrama: a strategy to reduce junior high school aggression. Int J Soc Serv Res 3(5):1319\u20131324","journal-title":"Int J Soc Serv Res"},{"issue":"1","key":"7122_CR4","first-page":"117","volume":"10","author":"A Enaifoghe","year":"2021","unstructured":"Enaifoghe A, Dlelana M, Durokifa AA, Dlamini NP (2021) The prevalence of gender-based violence against women in South Africa: a call for action. Afr J Gend Soc Dev 10(1):117","journal-title":"Afr J Gend Soc Dev"},{"issue":"12","key":"7122_CR5","doi-asserted-by":"publisher","first-page":"4016","DOI":"10.3390\/s24124016","volume":"24","author":"P Negre","year":"2024","unstructured":"Negre P, Alonso RS, Gonz\u00e1lez-Briones A, Prieto J, Rodr\u00edguez-Gonz\u00e1lez S (2024) Literature review of deep-learning-based detection of violence in video. Sensors 24(12):4016","journal-title":"Sensors"},{"key":"7122_CR6","doi-asserted-by":"publisher","first-page":"920","DOI":"10.7717\/peerj-cs.920","volume":"8","author":"B Omarov","year":"2022","unstructured":"Omarov B, Narynov S, Zhumanov Z, Gumar A, Khassanova M (2022) State-of-the-art violence detection techniques in video surveillance security systems: a systematic review. PeerJ Comput Sci 8:920","journal-title":"PeerJ Comput Sci"},{"key":"7122_CR7","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.dss.2018.07.003","volume":"113","author":"L Vomfell","year":"2018","unstructured":"Vomfell L, H\u00e4rdle WK, Lessmann S (2018) Improving crime count forecasts using Twitter and taxi data. Decis Support Syst 113:73\u201385","journal-title":"Decis Support Syst"},{"issue":"9","key":"7122_CR8","doi-asserted-by":"publisher","first-page":"1494","DOI":"10.1109\/JPROC.2021.3059994","volume":"109","author":"D Ding","year":"2021","unstructured":"Ding D, Ma Z, Chen D, Chen Q, Liu Z, Zhu F (2021) Advances in video compression system using deep neural network: a review and case studies. Proc IEEE 109(9):1494\u20131520","journal-title":"Proc IEEE"},{"key":"7122_CR9","doi-asserted-by":"crossref","unstructured":"Vosta S, Yow K-C (2022) A CNN-RNN combined structure for real-world violence detection in surveillance cameras. Appl Sci 12(3)","DOI":"10.3390\/app12031021"},{"issue":"14","key":"7122_CR10","doi-asserted-by":"publisher","first-page":"5706","DOI":"10.3390\/su12145706","volume":"12","author":"RS Alonso","year":"2020","unstructured":"Alonso RS, Sitt\u00f3n-Candanedo I, Casado-Vara R, Prieto J, Corchado JM (2020) Deep reinforcement learning for the management of software-defined networks and network function virtualization in an edge-IoT architecture. Sustainability 12(14):5706","journal-title":"Sustainability"},{"key":"7122_CR11","doi-asserted-by":"publisher","first-page":"107968","DOI":"10.1016\/j.engappai.2024.107968","volume":"132","author":"Y Dong","year":"2024","unstructured":"Dong Y, Jiang H, Liu Y, Yi Z (2024) Global wavelet-integrated residual frequency attention regularized network for hypersonic flight vehicle fault diagnosis with imbalanced data. Eng Appl Artif Intell 132:107968","journal-title":"Eng Appl Artif Intell"},{"key":"7122_CR12","doi-asserted-by":"crossref","unstructured":"Dong Y, Jiang H, Wang X, Li Z (2025) Entropy-oriented semi-supervised dynamic prototype contrastive learning for rotating machinery fault diagnosis. IEEE\/ASME Trans Mechatron","DOI":"10.1109\/TMECH.2025.3570186"},{"key":"7122_CR13","doi-asserted-by":"crossref","unstructured":"Wang X, Jiang H, Zeng T, Dong Y (2025) An adaptive fused domain-cycling variational generative adversarial network for machine fault diagnosis under data scarcity. Inf Fusion, 103616","DOI":"10.1016\/j.inffus.2025.103616"},{"issue":"10","key":"7122_CR14","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1080\/08839514.2021.1922841","volume":"35","author":"I Iqbal","year":"2021","unstructured":"Iqbal I, Odesanmi GA, Wang J, Liu L (2021) Comparative investigation of learning algorithms for image classification with small dataset. Appl Artif Intell 35(10):697\u2013716","journal-title":"Appl Artif Intell"},{"issue":"10","key":"7122_CR15","doi-asserted-by":"publisher","first-page":"1990","DOI":"10.1049\/iet-ipr.2019.1646","volume":"14","author":"I Iqbal","year":"2020","unstructured":"Iqbal I, Shahzad G, Rafiq N, Mustafa G, Ma J (2020) Deep learning-based automated detection of human knee joint\u2019s synovial fluid from magnetic resonance images with transfer learning. IET Image Proc 14(10):1990\u20131998","journal-title":"IET Image Proc"},{"key":"7122_CR16","doi-asserted-by":"crossref","unstructured":"Bermejo\u00a0Nievas E, Deniz\u00a0Suarez O, Bueno\u00a0Garc\u00eda G, Sukthankar R (2011) Violence detection in video using computer vision techniques. In: Computer analysis of images and patterns: 14th international conference, CAIP 2011, Seville, Spain, August 29-31, 2011, Proceedings, Part II 14. Springer, pp 332\u2013339","DOI":"10.1007\/978-3-642-23678-5_39"},{"key":"7122_CR17","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, pp 1\u20136","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"7122_CR18","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). pp 4183\u20134190","DOI":"10.1109\/ICPR48806.2021.9412502"},{"key":"7122_CR19","doi-asserted-by":"crossref","unstructured":"Soliman MM, Kamal MH, El-Massih\u00a0Nashed MA, Mostafa YM, Chawky BS, Khattab D (2019) Violence recognition from videos using deep learning techniques. In: 2019 Ninth International Conference on Intelligent Computing and Information Systems (ICICIS). pp 80\u201385","DOI":"10.1109\/ICICIS46948.2019.9014714"},{"issue":"12","key":"7122_CR20","doi-asserted-by":"publisher","first-page":"10400","DOI":"10.1002\/int.22537","volume":"37","author":"FUM Ullah","year":"2022","unstructured":"Ullah FUM, Obaidat MS, Muhammad K, Ullah A, Baik SW, Cuzzolin F, Rodrigues JJ, Albuquerque VHC (2022) An intelligent system for complex violence pattern analysis and detection. Int J Intell Syst 37(12):10400\u201310422","journal-title":"Int J Intell Syst"},{"issue":"8","key":"7122_CR21","doi-asserted-by":"publisher","first-page":"5359","DOI":"10.1109\/TII.2021.3116377","volume":"18","author":"FUM Ullah","year":"2021","unstructured":"Ullah FUM, Muhammad K, Haq IU, Khan N, Heidari AA, Baik SW, Albuquerque VHC (2021) AI-assisted edge vision for violence detection in IoT-based industrial surveillance networks. IEEE Trans Industr Inf 18(8):5359\u20135370","journal-title":"IEEE Trans Industr Inf"},{"key":"7122_CR22","doi-asserted-by":"crossref","unstructured":"Mugunga I, Dong J, Rigall E, Guo S, Madessa AH, Nawaz HS (2021) A frame-based feature model for violence detection from surveillance cameras using ConvLSTM network. In: 2021 6th International Conference on Image, Vision and Computing (ICIVC). IEEE, pp 55\u201360","DOI":"10.1109\/ICIVC52351.2021.9526948"},{"key":"7122_CR23","doi-asserted-by":"crossref","unstructured":"Qasim\u00a0Gandapur M, Verd\u00fa E (2023) ConvGRU-CNN: spatiotemporal deep learning for real-world anomaly detection in video surveillance system","DOI":"10.9781\/ijimai.2023.05.006"},{"key":"7122_CR24","doi-asserted-by":"crossref","unstructured":"Tumer C, Isgor B, Koklu M (2025) Violence detection in video using hybrid models based on MobileNetV2","DOI":"10.62411\/faith.3048-3719-284"},{"issue":"12","key":"7122_CR25","doi-asserted-by":"publisher","first-page":"7924","DOI":"10.1007\/s00034-024-02824-w","volume":"43","author":"V Akula","year":"2024","unstructured":"Akula V, Kavati I (2024) Human violence detection in videos using key frame identification and 3D CNN with convolutional block attention module. Circ Syst Signal Process 43(12):7924\u20137950","journal-title":"Circ Syst Signal Process"},{"key":"7122_CR26","doi-asserted-by":"crossref","unstructured":"Jaiswal SG, Mohod SW (2021) Classification of violent videos using ensemble boosting machine learning approach with low level features","DOI":"10.21817\/indjcse\/2021\/v12i6\/211206165"},{"key":"7122_CR27","doi-asserted-by":"publisher","first-page":"111987","DOI":"10.1016\/j.engappai.2025.111987","volume":"161","author":"M-T Truong","year":"2025","unstructured":"Truong M-T, Hoang V-D (2025) Skeleton-based multi-person action recognition towards real-world violence detection. Eng Appl Artif Intell 161:111987","journal-title":"Eng Appl Artif Intell"},{"issue":"6","key":"7122_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-025-04118-7","volume":"6","author":"N Tran","year":"2025","unstructured":"Tran N, Nguyen H, Ly D, Ngo K, Nguyen HD (2025) Advancing violence detection with graph-based skeleton motion analysis. SN Comput Sci 6(6):1\u201318","journal-title":"SN Comput Sci"},{"key":"7122_CR29","doi-asserted-by":"crossref","unstructured":"Alshalawi A, Abdul W, Muhammad G (2025) Advanced detection of violence from video: performance evaluation of transformer and state of the art of convolution of neural network transformer. IEEE Access","DOI":"10.1109\/ACCESS.2025.3564435"},{"key":"7122_CR30","doi-asserted-by":"crossref","unstructured":"Meng J, Tian H, Lin G, Hu J-F, Zheng W-S (2025) Audio-visual collaborative learning for weakly supervised video anomaly detection. IEEE Trans Multimed","DOI":"10.1109\/TMM.2025.3535377"},{"key":"7122_CR31","doi-asserted-by":"crossref","unstructured":"Negre P, Alonso RS, Prieto J, Dang CN, Corchado JM (2024) Systematic mapping study on violence detection in video by means of trustworthy artificial intelligence. Available at SSRN 4757631","DOI":"10.2139\/ssrn.4757631"},{"issue":"23","key":"7122_CR32","doi-asserted-by":"publisher","first-page":"9383","DOI":"10.3390\/s22239383","volume":"22","author":"N Mumtaz","year":"2022","unstructured":"Mumtaz N, Ejaz N, Aladhadh S, Habib S, Lee MY (2022) Deep multi-scale features fusion for effective violence detection and control charts visualization. Sensors 22(23):9383","journal-title":"Sensors"},{"issue":"6","key":"7122_CR33","doi-asserted-by":"publisher","first-page":"2216","DOI":"10.3390\/s22062216","volume":"22","author":"R Vijeikis","year":"2022","unstructured":"Vijeikis R, Raudonis V, Dervinis G (2022) Efficient violence detection in surveillance. Sensors 22(6):2216","journal-title":"Sensors"},{"key":"7122_CR34","doi-asserted-by":"crossref","unstructured":"Sharma S, Sudharsan B, Naraharisetti S, Trehan V, Jayavel K (2021) A fully integrated violence detection system using CNN and LSTM. Int J Electr Comput Eng (2088-8708) 11(4)","DOI":"10.11591\/ijece.v11i4.pp3374-3380"},{"key":"7122_CR35","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1007\/s00371-020-01878-6","volume":"37","author":"M Asad","year":"2021","unstructured":"Asad M, Yang J, He J, Shamsolmoali P, He X (2021) Multi-frame feature-fusion-based model for violence detection. Vis Comput 37:1415\u20131431","journal-title":"Vis Comput"},{"issue":"4","key":"7122_CR36","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s42979-020-00207-x","volume":"1","author":"R Halder","year":"2020","unstructured":"Halder R, Chatterjee R (2020) CNN-BiLSTM model for violence detection in smart surveillance. SN Comput Sci 1(4):201","journal-title":"SN Comput Sci"},{"issue":"9","key":"7122_CR37","doi-asserted-by":"publisher","first-page":"8549","DOI":"10.1007\/s13369-021-05589-5","volume":"46","author":"HMB Jahlan","year":"2021","unstructured":"Jahlan HMB, Elrefaei LA (2021) Mobile neural architecture search network and convolutional long short-term memory-based deep features toward detecting violence from video. Arab J Sci Eng 46(9):8549\u20138563","journal-title":"Arab J Sci Eng"},{"key":"7122_CR38","unstructured":"Contardo P, Tomassini S, Falcionelli N, Dragoni AF, Sernani P (2023) Combining a mobile deep neural network and a recurrent layer for violence detection in videos"},{"key":"7122_CR39","doi-asserted-by":"crossref","unstructured":"Gupta H, Ali ST (2022) Violence detection using deep learning techniques. In: 2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI). IEEE, pp 121\u2013124","DOI":"10.1109\/ICETCI55171.2022.9921388"},{"key":"7122_CR40","doi-asserted-by":"crossref","unstructured":"Aarthy K, Nithya AA (2022) Crowd violence detection in videos using deep learning architecture. In: 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon). IEEE, pp 1\u20136","DOI":"10.1109\/MysuruCon55714.2022.9972624"},{"key":"7122_CR41","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, pp 154\u2013159","DOI":"10.1109\/SMC42975.2020.9282971"},{"key":"7122_CR42","doi-asserted-by":"crossref","unstructured":"Traor\u00e9 A, Akhloufi MA (2020) 2D bidirectional gated recurrent unit convolutional neural networks for end-to-end violence detection in videos. In: International conference on image analysis and recognition. Springer, pp 152\u2013160","DOI":"10.1007\/978-3-030-50347-5_14"},{"key":"7122_CR43","doi-asserted-by":"crossref","unstructured":"Islam MS, Hasan MM, Abdullah S, Akbar JUM, Arafat N, Murad SA (2021) A deep spatio-temporal network for vision-based sexual harassment detection. In: 2021 Emerging Technology in Computing, Communication and Electronics (ETCCE). IEEE, pp 1\u20136","DOI":"10.1109\/ETCCE54784.2021.9689891"},{"key":"7122_CR44","doi-asserted-by":"crossref","unstructured":"Talha KR, Bandapadya K, Khan MM (2022) Violence detection using computer vision approaches. In: 2022 IEEE World AI IoT Congress (AIIoT). IEEE, pp 544\u2013550","DOI":"10.1109\/AIIoT54504.2022.9817374"},{"issue":"1","key":"7122_CR45","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1007\/s10515-022-00323-3","volume":"29","author":"A Srivastava","year":"2022","unstructured":"Srivastava A, Badal T, Saxena P, Vidyarthi A, Singh R (2022) UAV surveillance for violence detection and individual identification. Autom Softw Eng 29(1):28","journal-title":"Autom Softw Eng"},{"key":"7122_CR46","doi-asserted-by":"crossref","unstructured":"Negre P, Alonso RS, Prieto J, Novais P, Corchado JM (2024) Violence detection in video models implementation using pre-trained VGG19 combined with manual logic, LSTM layers and Bi-LSTM layers. In: DCAI 2024. In Press","DOI":"10.2139\/ssrn.4832475"},{"key":"7122_CR47","unstructured":"European Commission, High-Level Expert Group on AI (2019) Ethics guidelines for trustworthy AI. https:\/\/ec.europa.eu\/digital-strategy\/news-redirect\/65479. Accessed 30 Oct 2024"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07122-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-026-07122-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07122-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:00:45Z","timestamp":1774933245000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-026-07122-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["7122"],"URL":"https:\/\/doi.org\/10.1007\/s10489-026-07122-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"14 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"72"}}