{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T12:24:15Z","timestamp":1763641455757,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2011,4,18]],"date-time":"2011-04-18T00:00:00Z","timestamp":1303084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2011,4,18]]},"DOI":"10.1145\/1991996.1992019","type":"proceedings-article","created":{"date-parts":[[2011,6,6]],"date-time":"2011-06-06T11:53:52Z","timestamp":1307361232000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["A comprehensive neural-based approach for text recognition in videos using natural language processing"],"prefix":"10.1145","author":[{"given":"Khaoula","family":"Elagouni","sequence":"first","affiliation":[{"name":"Orange Labs R&D, rue du Clos Courtel, Cesson-S\u00e9vign\u00e9 Cedex, France"}]},{"given":"Christophe","family":"Garcia","sequence":"additional","affiliation":[{"name":"LIRIS, Insa de Lyon, B\u00e2t. Jules Verne, Villeurbanne Cedex, France"}]},{"given":"Pascale","family":"S\u00e9billot","sequence":"additional","affiliation":[{"name":"IRISA, Insa de Rennes, Campus de Beaulieu, Rennes Cedex, France"}]}],"member":"320","published-online":{"date-parts":[[2011,4,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/29.32278"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.506792"},{"key":"e_1_3_2_1_3_1","volume-title":"LIBSVM: a library for support vector machines","author":"Chang C.","year":"2001","unstructured":"C. Chang and C. Lin . LIBSVM: a library for support vector machines . 2001 . C. Chang and C. Lin. LIBSVM: a library for support vector machines. 2001."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/76.809161"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/846220.1515084"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2003.06.001"},{"key":"e_1_3_2_1_7_1","first-page":"319","volume-title":"IEEE Region 10 Conference, TENCON'04","volume":"1","author":"Chen T.","year":"2005","unstructured":"T. Chen , D. Ghosh , and S. Ranganath . Video-text extraction and recognition . In IEEE Region 10 Conference, TENCON'04 , volume 1 , pages 319 -- 322 , 2005 . T. Chen, D. Ghosh, and S. Ranganath. Video-text extraction and recognition. In IEEE Region 10 Conference, TENCON'04, volume 1, pages 319--322, 2005."},{"key":"e_1_3_2_1_8_1","first-page":"290","volume-title":"International Conference on Computer Vision Theory and Applications","volume":"2","author":"Delakis M.","year":"2008","unstructured":"M. Delakis and C. Garcia . Text detection with convolutional neural networks . In International Conference on Computer Vision Theory and Applications , volume 2 , pages 290 -- 294 , 2008 . M. Delakis and C. Garcia. Text detection with convolutional neural networks. In International Conference on Computer Vision Theory and Applications, volume 2, pages 290--294, 2008."},{"key":"e_1_3_2_1_9_1","first-page":"601","volume-title":"IEEE International Conference on Multimedia and Expo","author":"Dorai C.","year":"2001","unstructured":"C. Dorai , H. Aradhye , and J.-C. Shim . End-to-end video text recognition for multimedia content analysis . In IEEE International Conference on Multimedia and Expo , pages 601 -- 604 . IEEE Computer Society , 2001 . C. Dorai, H. Aradhye, and J.-C. Shim. End-to-end video text recognition for multimedia content analysis. In IEEE International Conference on Multimedia and Expo, pages 601--604. IEEE Computer Society, 2001."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.97"},{"key":"e_1_3_2_1_11_1","first-page":"397","volume-title":"International Conference on Image Processing","volume":"2","author":"Hua X.","year":"2002","unstructured":"X. Hua , P. Yin , and H. Zhang . Efficient video text recognition using multiple frame integration . In International Conference on Image Processing , volume 2 , pages 397 -- 400 , 2002 . X. Hua, P. Yin, and H. Zhang. Efficient video text recognition using multiple frame integration. In International Conference on Image Processing, volume 2, pages 397--400, 2002."},{"key":"e_1_3_2_1_12_1","volume-title":"Universitat Mannheim\/Institut fur Informatik","author":"Kopf S.","year":"2005","unstructured":"S. Kopf , T. Haenselmann , and W. Effelsberg . Robust character recognition in low-resolution images and videos . Universitat Mannheim\/Institut fur Informatik , 2005 . S. Kopf, T. Haenselmann, and W. Effelsberg. Robust character recognition in low-resolution images and videos. Universitat Mannheim\/Institut fur Informatik, 2005."},{"key":"e_1_3_2_1_13_1","first-page":"255","volume-title":"Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks","author":"LeCun Y.","year":"1995","unstructured":"Y. LeCun and Y. Bengio . Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks , pages 255 -- 258 , 1995 . Y. LeCun and Y. Bengio. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, pages 255--258, 1995."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.541415"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.234741"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/231930"},{"key":"e_1_3_2_1_17_1","first-page":"100","volume-title":"International Workshop on Camera-Based Document Analysis and Recognition","author":"Sa\u00efdane Z.","year":"2007","unstructured":"Z. Sa\u00efdane and C. Garcia . Automatic scene text recognition using a convolutional neural network . In International Workshop on Camera-Based Document Analysis and Recognition , pages 100 -- 106 , 2007 . Z. Sa\u00efdane and C. Garcia. Automatic scene text recognition using a convolutional neural network. In International Workshop on Camera-Based Document Analysis and Recognition, pages 100--106, 2007."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/938980.939477"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.850966"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCIS.2009.5291877"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-303"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0165-0114(91)90046-S"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.58"},{"key":"e_1_3_2_1_24_1","first-page":"528","volume-title":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2","author":"Zhang D.","year":"2003","unstructured":"D. Zhang and S. Chang . A Bayesian framework for fusing multiple word knowledge models in videotext recognition . In IEEE Computer Society Conference on Computer Vision and Pattern Recognition , volume 2 , pages 528 -- 533 , 2003 . D. Zhang and S. Chang. A Bayesian framework for fusing multiple word knowledge models in videotext recognition. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume 2, pages 528--533, 2003."}],"event":{"name":"ICMR'11: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Trento Italy","acronym":"ICMR'11"},"container-title":["Proceedings of the 1st ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1991996.1992019","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1991996.1992019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T11:05:54Z","timestamp":1750244754000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1991996.1992019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4,18]]},"references-count":24,"alternative-id":["10.1145\/1991996.1992019","10.1145\/1991996"],"URL":"https:\/\/doi.org\/10.1145\/1991996.1992019","relation":{},"subject":[],"published":{"date-parts":[[2011,4,18]]},"assertion":[{"value":"2011-04-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}