{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T15:03:10Z","timestamp":1763910190717,"version":"3.37.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030006914"},{"type":"electronic","value":"9783030006921"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-00692-1_25","type":"book-chapter","created":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T08:59:31Z","timestamp":1536829171000},"page":"287-299","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Extracting Textual Overlays from Social Media Videos Using Neural Networks"],"prefix":"10.1007","author":[{"given":"Adam","family":"S\u0142ucki","sequence":"first","affiliation":[]},{"given":"Tomasz","family":"Trzci\u0144ski","sequence":"additional","affiliation":[]},{"given":"Adam","family":"Bielski","sequence":"additional","affiliation":[]},{"given":"Pawe\u0142","family":"Cyrta","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,14]]},"reference":[{"key":"25_CR1","unstructured":"Davies, M.: The Corpus of Contemporary American English (COCA): 560 million words, 1990-present (2008)"},{"key":"25_CR2","unstructured":"Donoser, M., Bischof, H.: Efficient Maximally Stable Extremal Region (MSER) tracking. In: CVPR (2006)"},{"key":"25_CR3","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, ICML 2006, pp. 369\u2013376. ACM, New York (2006). http:\/\/doi.acm.org\/10.1145\/1143844.1143891"},{"key":"25_CR4","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"25_CR5","unstructured":"Kannao, R., Guha, P.: Overlay text extraction from TV news broadcast. CoRR abs\/1604.00470 (2016). http:\/\/arxiv.org\/abs\/1604.00470"},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Karatzas, D., Mestre, S.R., Mas, J., Nourbakhsh, F., Roy, P.P.: ICDAR 2011 robust reading competition - challenge 1: reading text in born-digital images (web and email). In: 2011 International Conference on Document Analysis and Recognition, pp. 1485\u20131490, September 2011. https:\/\/doi.org\/10.1109\/ICDAR.2011.295","DOI":"10.1109\/ICDAR.2011.295"},{"key":"25_CR7","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions and reversals. Sov. Phys. Dokl. 10, 707 (1966)","journal-title":"Sov. Phys. Dokl."},{"key":"25_CR8","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: TextBoxes: a fast text detector with a single deep neural network. CoRR abs\/1611.06779 (2016). http:\/\/googlebooks.byu.edu\/"},{"key":"25_CR9","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. CoRR abs\/1512.02325 (2015). http:\/\/arxiv.org\/abs\/1512.02325"},{"key":"25_CR10","unstructured":"Lundqvist, F., Wallberg, O.: Natural image distortions and optical character recognition accuracy. Ph.D. thesis, KTH, School of Computer Science and Communication (2016)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Sato, T., Kanade, T., Hughes, E., Smith, M., Satoh, S.: Video OCR: indexing digital news libraries by recognition of superimposed caption. In: ACM Multimedia Systems Special Issue on Video Libraries, February 1998","DOI":"10.1007\/s005300050140"},{"key":"25_CR12","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. CoRR abs\/1507.05717 (2015). http:\/\/arxiv.org\/abs\/1507.05717"},{"key":"25_CR13","unstructured":"Smith, R.: An overview of the Tesseract OCR engine. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 02, ICDAR 2007, pp. 629\u2013633. IEEE Computer Society, Washington, DC (2007). http:\/\/dl.acm.org\/citation.cfm?id=1304596.1304846"},{"key":"25_CR14","unstructured":"Tian, S., Pan, Y., Huang, C., Lu, S., Yu, K., Tan, C.L.: Text flow: a unified text detection system in natural scene images. CoRR abs\/1604.06877 (2016). http:\/\/arxiv.org\/abs\/1604.06877"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Yang, H., Wang, C., Bartz, C., Meinel, C.: SceneTextReg: a real-time video OCR system. In: Proceedings of the 2016 ACM on Multimedia Conference, MM 2016, pp. 698\u2013700. ACM, New York (2016). http:\/\/doi.acm.org\/10.1145\/2964284.2973811","DOI":"10.1145\/2964284.2973811"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Yang, H., Wang, B., Lin, S., Wipf, D.P., Guo, M., Guo, B.: Unsupervised extraction of video highlights via robust recurrent auto-encoders. CoRR abs\/1510.01442 (2015)","DOI":"10.1109\/ICCV.2015.526"},{"key":"25_CR17","unstructured":"Yao, C., et al.: Incidental scene text understanding: recent progresses on ICDAR 2015 robust reading competition challenge 4. CoRR abs\/1511.09207 (2015). http:\/\/arxiv.org\/abs\/1511.09207"}],"container-title":["Lecture Notes in Computer Science","Computer Vision and Graphics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00692-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,24]],"date-time":"2019-10-24T01:11:53Z","timestamp":1571879513000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-00692-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030006914","9783030006921"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00692-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"ICCVG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Warsaw","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccvg2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccvg.wzim.sggw.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}