{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T05:30:00Z","timestamp":1746077400655,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T00:00:00Z","timestamp":1655337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T00:00:00Z","timestamp":1655337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,16]]},"DOI":"10.1109\/comm54429.2022.9817200","type":"proceedings-article","created":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T15:41:28Z","timestamp":1657726888000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Two-Stage Spatio- Temporal Vision Transformer for the Detection of Violent Scenes"],"prefix":"10.1109","author":[{"given":"Mihai Gabriel","family":"Constantin","sequence":"first","affiliation":[{"name":"University Politehnica of Bucharest,Bucharest,Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Ionescu","sequence":"additional","affiliation":[{"name":"University Politehnica of Bucharest,Bucharest,Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68345-4_39"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14364-4_53"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s19112472"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3005-5_37"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749406"},{"key":"ref15","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.comnet.2019.01.028","article-title":"Real time violence detection framework for football stadium comprising of big data analysis and deep learning through bidirectional lstm","volume":"151","author":"fenil","year":"2019","journal-title":"Computer Networks"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00207-x"},{"key":"ref19","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref4","first-page":"2","article-title":"The mediaeval 2013 affect task: violent scenes detection","author":"demarty","year":"2013","journal-title":"MediaEval 2013 Working Notes"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref3","article-title":"Affect in multimedia: Benchmarking violent scenes detection","author":"constantin","year":"2020","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2725820"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.12.045"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.12.065"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932114"},{"key":"ref20","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Transformers in vision: A survey","author":"khan","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref24","article-title":"Beit: Bert pre-training of image transformers","author":"bao","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Support vector method for novelty detection","author":"scholkopf","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 14th International Conference on Communications (COMM)","start":{"date-parts":[[2022,6,16]]},"location":"Bucharest, Romania","end":{"date-parts":[[2022,6,18]]}},"container-title":["2022 14th International Conference on Communications (COMM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9817096\/9817149\/09817200.pdf?arnumber=9817200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T20:42:29Z","timestamp":1659645749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9817200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/comm54429.2022.9817200","relation":{},"subject":[],"published":{"date-parts":[[2022,6,16]]}}}