{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:28:24Z","timestamp":1793132904519,"version":"4.5.0"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>The growing demand of smart surveillance systems necessitates the accurate and real-time detection of weapons and face recognition with robustness against occlusion, illumination changes, and complex backgrounds. Existing techniques based on standalone CNN or transformer architectures are less effective in capturing local fine-grained features as well as long-range dependencies. This paper presents ConViDeTR, a hybrid deep learning framework that integrates CNN, Vision Transformer (ViT), and Detection Transformer (DETR) architectures into a unified framework. The key contribution of the proposed framework is the deep feature fusion layer, which integrates local spatial features, global context features, and object query features in one shared feature space. This enables the synchronous execution of weapon detection and face recognition using one efficient framework. The experiments using existing benchmark datasets validate the performance, achieving 98.9% accuracy in weapon detection and 97.34% accuracy in face recognition and outperforming the existing techniques in both tasks. The framework also demonstrates real-time performance with 25\u201330 FPS and low latency. The performance of the proposed framework sustains its effectiveness, robustness, and scalability in the development of next-generation intelligent surveillance systems.<\/jats:p>","DOI":"10.3389\/frai.2026.1841848","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T05:39:30Z","timestamp":1781069970000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["An efficient hybrid CNN\u2013transformer framework for real-time weapon detection and face recognition"],"prefix":"10.3389","volume":"9","author":[{"given":"P.","family":"Shanthi","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V.","family":"Manjula","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"ref1","first-page":"1","author":"Ahire","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"20551","DOI":"10.1007\/s00521-024-10582-8","article-title":"MFI3D: masked face identification with 3D face reconstruction and deep learning","volume":"37","author":"Alzu\u2019bi","year":"2025","journal-title":"Neural Comput. & Applic."},{"key":"ref3","first-page":"1","volume-title":"In 2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE)","author":"Arockia Abins","year":"2024"},{"key":"ref4","first-page":"213","author":"Carion","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.neucom.2018.10.076","article-title":"Brightness guided preprocessing for automatic cold steel weapon detection in surveillance videos with deep learning","volume":"330","author":"Castillo","year":"2019","journal-title":"Neurocomputing"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.clsr.2009.02.003","article-title":"Towards a new generation of CCTV networks: erosion of data protection safeguards?","volume":"25","author":"Coudert","year":"2009","journal-title":"Comput. Law Secur. Rev."},{"key":"ref7","first-page":"549","author":"Dave","year":"2022"},{"key":"ref8","first-page":"4690","author":"Deng","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2010.11929","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"01071","DOI":"10.1051\/e3sconf\/202339101071","article-title":"Weapon detection in surveillance videos using Yolov8 and Pelsf-DCNN","volume":"391","author":"Dugyala","year":"2023","journal-title":"E3S Web Conf."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/j.ijcce.2024.07.003","article-title":"Advanced deep learning for masked individual surveillance","volume":"5","author":"Elhoseny","year":"2024","journal-title":"Int. J. Cogn. Comput. Eng."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1109\/76.728411","article-title":"A real-time system for video surveillance of unattended outdoor environments","volume":"8","author":"Foresti","year":"1998","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref13","first-page":"770","author":"He","year":"2016"},{"key":"ref14","first-page":"193","author":"Jain","year":"2020"},{"key":"ref15","year":"2023"},{"key":"ref16","year":"2007"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2406","DOI":"10.1016\/j.matpr.2021.06.373","article-title":"Criminal face identification system using deep learning algorithm multi-task cascade neural network (MTCNN)","volume":"80","author":"Kumar","year":"2023","journal-title":"Mater. Today Proc."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1109\/ICSCSS60660.2024.10624946","article-title":"Real-time criminal identification system based on face recognition","volume":"26","author":"Kumar","year":"2020","journal-title":"Adv. Sci. Lett."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"55981","DOI":"10.1007\/s11042-023-17748-x","article-title":"Real-time detection of abnormal human activity using deep learning and temporal attention mechanism in video surveillance","volume":"83","author":"Kumar","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref20","author":"Nagnath","year":"2021"},{"key":"ref21","volume-title":"2022 International Conference on Electronic Systems and Intelligent Computing (ICESIC)","author":"Nikkath","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"38","DOI":"10.5772\/intechopen.76444","article-title":"Advance intelligent video surveillance system (AIVSS): a future aspect","volume":"37","author":"Rai","year":"2019","journal-title":"Intell. Video Surveill."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"26766","DOI":"10.1038\/s41598-025-07782-0","article-title":"Weapon detection with FMR-CNN and YOLOv8 for enhanced crime prevention and security","volume":"15","author":"Shanthi","year":"","journal-title":"Sci. Rep."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/s10791-025-09715-x","article-title":"A systematic review on CNN-YOLO techniques for face and weapon detection in crime prevention","volume":"28","author":"Shanthi","year":"","journal-title":"Disc. Comput."},{"key":"ref25","first-page":"1067","volume-title":"In 2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N)","author":"Tabassum","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1016\/j.compeleceng.2017.11.011","article-title":"Video surveillance systems-current status and future trends","volume":"70","author":"Tsakanikas","year":"2018","journal-title":"Comput. Electr. Eng."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1777","DOI":"10.1007\/s41870-023-01184-z","article-title":"A novel facial emotion recognition model using segmentation VGG-19 architecture","volume":"15","author":"Vignesh","year":"2023","journal-title":"Int. J. Inf. Technol."},{"key":"ref28","first-page":"239","author":"Wang","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1007\/s10043-024-00915-2","article-title":"Mask-based lensless face recognition system with dual-prior face restoration","volume":"31","author":"Wang","year":"2024","journal-title":"Opt. Rev."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"104342","DOI":"10.1016\/j.dsp.2023.104342","article-title":"Robust weapon detection in dark environments using Yolov7-DarkVision","volume":"145","author":"Yadav","year":"2024","journal-title":"Digit. Signal Process."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1007\/s41870-024-02375-y","article-title":"WeaponVision AI: a software for strengthening surveillance through deep learning in real-time automated weapon detection","volume":"17","author":"Yadav","year":"2025","journal-title":"Int. J. Inf. Technol."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s11334-024-00580-3","article-title":"SIRD-YOLO: an enhanced deep learning model for weapon detection using spatial interactions and diverse receptive fields","volume":"21","author":"Yadav","year":"2025","journal-title":"Innov. Syst. Softw. Eng."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1841848\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T05:39:32Z","timestamp":1781069972000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1841848\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":32,"alternative-id":["10.3389\/frai.2026.1841848"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1841848","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]},"article-number":"1841848"}}