{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T20:01:25Z","timestamp":1770062485143,"version":"3.49.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:00:00Z","timestamp":1753401600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:00:00Z","timestamp":1753401600000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-04219-3","type":"journal-article","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T11:54:08Z","timestamp":1753444448000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Query-Aware Spatiotemporal Transformer-Based Framework for Enhanced Moment Retrieval in Video Surveillance"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9150-2337","authenticated-orcid":false,"given":"Pratibha","family":"Singh","sequence":"first","affiliation":[]},{"given":"Alok Kumar Singh","family":"Kushwaha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"4219_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103116","volume":"77","author":"O Elharrouss","year":"2021","unstructured":"Elharrouss O, Almaadeed N, Al-Maadeed S. A review of video surveillance systems. J Vis Commun Image Represent. 2021;77: 103116. https:\/\/doi.org\/10.1016\/j.jvcir.2021.103116.","journal-title":"J Vis Commun Image Represent"},{"key":"4219_CR2","first-page":"7","volume":"39","author":"J Wu","year":"2022","unstructured":"Wu J, Gao ZD-S. sound classification based on double two-stream convolution and multi-feature fusion. Appl Res Comput. 2022;39:7.","journal-title":"Appl Res Comput"},{"key":"4219_CR3","doi-asserted-by":"publisher","unstructured":"Lim J. et al. Gun detection in surveillance videos using deep neural networks. In: 2019 Asia-Pacific signal information processing association annual summit and conference APSIPA ASC 2019 1998\u20132002, 2019. https:\/\/doi.org\/10.1109\/APSIPAASC47483.2019.9023182.","DOI":"10.1109\/APSIPAASC47483.2019.9023182"},{"key":"4219_CR4","doi-asserted-by":"crossref","unstructured":"Jiawei L, Shu-Tao X, Qianggang D. Multi-level recognition on falls from activities of daily living. In: Proceedings of the 2020 international conference on multimedia retrieval, 2020, pp. 464\u2013471.","DOI":"10.1145\/3372278.3390702"},{"key":"4219_CR5","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s42154-018-0009-9","volume":"1","author":"J Li","year":"2018","unstructured":"Li J, Cheng H, Guo H, Qiu S. Survey on artificial intelligence for vehicles. Automot Innov. 2018;1:2\u201314.","journal-title":"Automot Innov"},{"key":"4219_CR6","doi-asserted-by":"publisher","first-page":"7911","DOI":"10.1038\/s41598-023-35190-9","volume":"13","author":"M Zahrawi","year":"2023","unstructured":"Zahrawi M, Shaalan K. Improving video surveillance systems in banks using deep learning techniques. Sci Rep. 2023;13:7911. https:\/\/doi.org\/10.1038\/s41598-023-35190-9.","journal-title":"Sci Rep"},{"key":"4219_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-023-01350-3","author":"R Amshavalli","year":"2023","unstructured":"Amshavalli R, Kalaivani J. Real-time institution video data analysis using fog computing and adaptive background subtraction. J Real-Time Image Process. 2023. https:\/\/doi.org\/10.1007\/s11554-023-01350-3.","journal-title":"J Real-Time Image Process"},{"issue":"3","key":"4219_CR8","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1007\/s10772-023-10054-9","volume":"26","author":"M Daouad","year":"2023","unstructured":"Daouad M, Allah FA, Dadi EW. An automatic speech recognition system for isolated Amazigh word using 1D & 2D CNN-LSTM architecture. Int J Speech Technol. 2023;26(3):775\u201387.","journal-title":"Int J Speech Technol"},{"issue":"5","key":"4219_CR9","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.3390\/sym15051045","volume":"15","author":"M Huang","year":"2023","unstructured":"Huang M, Wang M, Liu X, Kan R, Qiu H. Environmental sound classification framework based on l-mhp features and se-resnet50 network model. Symmetry. 2023;15(5):1045.","journal-title":"Symmetry"},{"key":"4219_CR10","doi-asserted-by":"publisher","first-page":"130327","DOI":"10.1109\/ACCESS.2019.2939495","volume":"7","author":"Z Zhang","year":"2019","unstructured":"Zhang Z, Xu S, Zhang S, Qiao T, Cao S. Learning attentive representations for environmental sound classification. IEEE Access. 2019;7:130327\u201339.","journal-title":"IEEE Access"},{"key":"4219_CR11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0223221","volume":"14","author":"M Joshanloo","year":"2019","unstructured":"Joshanloo M, Jovanovi\u0107 V, Taylor T. A multidimensional understanding of prosperity and well-being at country level: data-driven explorations. PLoS ONE. 2019;14: e0223221.","journal-title":"PLoS ONE"},{"key":"4219_CR12","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s40537-019-0212-5","volume":"6","author":"G Sreenu","year":"2019","unstructured":"Sreenu G, Saleem Durai MA. Intelligent video surveillance: a review through deep learning techniques for crowd analysis. J Big Data. 2019;6:48. https:\/\/doi.org\/10.1186\/s40537-019-0212-5.","journal-title":"J Big Data"},{"key":"4219_CR13","doi-asserted-by":"publisher","unstructured":"Singh RP, Srivastava H, Gautam H, Shukla R, Dwivedi RK. An intelligent video surveillance system using edge computing based deep learning model. In: 2023 international conference on intelligent data communication technologies and internet of things (IDCIoT), Bengaluru, India, 2023, pp. 439\u2013444. https:\/\/doi.org\/10.1109\/IDCIoT56793.2023.10053404.","DOI":"10.1109\/IDCIoT56793.2023.10053404"},{"key":"4219_CR14","doi-asserted-by":"publisher","first-page":"3610","DOI":"10.1109\/TIFS.2020.2994740","volume":"15","author":"A Greco","year":"2020","unstructured":"Greco A, Petkov N, Saggese A, Vento M. Aren: a deep learning approach for sound event recognition using a brain inspired representation. IEEE Trans Inf Forensics Secur. 2020;15:3610\u201324.","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"4219_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/9566628","volume":"2021","author":"C-H Tseng","year":"2021","unstructured":"Tseng C-H, Hsieh C-C, Jwo D-J, Wu J-H, Sheu R-K, Chen L-C. Person retrieval in video surveillance using deep learning-based instance segmentation. J Sens. 2021;2021:1\u201312. https:\/\/doi.org\/10.1155\/2021\/9566628.","journal-title":"J Sens"},{"key":"4219_CR16","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1016\/j.procs.2020.03.400","volume":"167","author":"S Masood","year":"2020","unstructured":"Masood S, Ahsan U, Munawwar F, Rizvi DR, Ahmed M. Scene recognition from image using convolutional neural network. Procedia Comput Sci. 2020;167:1005\u201312.","journal-title":"Procedia Comput Sci"},{"key":"4219_CR17","doi-asserted-by":"publisher","unstructured":"Warsi A, Abdullah M, Husen MN, Yahya M. Automatic handgun and knife detection algorithms: a review. In: Proceedings of 14th international conference on ubiquitous information management and communication IMCOM, 2020. https:\/\/doi.org\/10.1109\/IMCOM48794.2020.9001725.","DOI":"10.1109\/IMCOM48794.2020.9001725"},{"issue":"2","key":"4219_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/s21020603","volume":"21","author":"BHD Koh","year":"2021","unstructured":"Koh BHD, Lim CLP, Rahimi H, Woo WL, Gao B. Deep temporal convolution network for time series classification. Sensors. 2021;21(2): 603.","journal-title":"Sensors"},{"key":"4219_CR19","doi-asserted-by":"publisher","first-page":"68482","DOI":"10.1109\/ACCESS.2021.3077499","volume":"9","author":"Z Xu","year":"2021","unstructured":"Xu Z, Li J, Zhang M. A surveillance video real-time analysis system based on edge-cloud and fl-yolo cooperation in coal mine. IEEE Access. 2021;9:68482\u201397.","journal-title":"IEEE Access"},{"issue":"no. 21","key":"4219_CR20","doi-asserted-by":"publisher","first-page":"15847","DOI":"10.1109\/JIOT.2021.3051080","volume":"8","author":"MA Rahman","year":"2021","unstructured":"Rahman MA, Hossain MS. An internet-of-medical-things-enabled edge computing framework for tackling COVID-19. IEEE Internet Things J. 2021;8(21):15847\u201354.","journal-title":"IEEE Internet Things J"},{"key":"4219_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2021.106019","volume":"154","author":"A Pramanik","year":"2021","unstructured":"Pramanik A, Sarkar S, Maiti J. A real-time video surveillance system for traffic pre-events detection. Accid Anal Prev. 2021;154: 106019.","journal-title":"Accid Anal Prev"},{"key":"4219_CR22","doi-asserted-by":"crossref","unstructured":"Xu J, Yang H. Identification of pedestrian attributes based on video sequence. In: IEEE international conference on advanced manufacturing (ICAM), Yunlin, Taiwan, 2018, pp. 467\u2013470.","DOI":"10.1109\/AMCON.2018.8614752"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04219-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04219-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04219-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T23:47:35Z","timestamp":1757288855000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04219-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,25]]},"references-count":22,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["4219"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04219-3","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,25]]},"assertion":[{"value":"3 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2025","order":3,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Not applicable. This study did not involve human participants or animals.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research Involving Human and\/or Animals"}},{"value":"As this study did not involve human participants, informed consent was not required.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}}],"article-number":"685"}}