{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:25:54Z","timestamp":1743081954538,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030121761"},{"type":"electronic","value":"9783030121778"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-12177-8_3","type":"book-chapter","created":{"date-parts":[[2019,1,18]],"date-time":"2019-01-18T12:13:44Z","timestamp":1547813624000},"page":"25-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Scene Text Detection with a SSD and Encoder-Decoder Network Based Method"],"prefix":"10.1007","author":[{"given":"Cong","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,19]]},"reference":[{"key":"3_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: ICDAR2017 competition on reading Chinese text in the wild (RCTW-17) (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.1109\/TPAMI.2003.1251157","volume":"25","author":"KI Kim","year":"2003","unstructured":"Kim, K.I., Jung, K., Kim, J.H.: Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm. IEEE Trans. Pattern Anal. Mach. Intell. 25, 1631\u20131639 (2003)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tan, C.L.: A Laplacian method for video text detection. In: 10th International Conference on Document Analysis and Recognition, ICDAR 2009, pp. 66\u201370 (2009)","DOI":"10.1109\/ICDAR.2009.153"},{"key":"3_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/978-3-642-15549-9_43","volume-title":"Computer Vision \u2013 ECCV 2010","author":"K Wang","year":"2010","unstructured":"Wang, K., Belongie, S.: Word spotting in the wild. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 591\u2013604. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_43"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: Computer Vision and Pattern Recognition, CVPR, pp. 2963\u20132970 (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"3_CR7","unstructured":"Chowdhury, A.R., Bhattacharya, U., Parui, S.K.: Scene text detection using sparse stroke information and MLP. In: 21st International Conference on Pattern Recognition, ICPR, pp. 294\u2013297 (2012)"},{"key":"3_CR8","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 1083\u20131090 (2012)"},{"key":"3_CR9","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1016\/j.imavis.2004.02.006","volume":"22","author":"J Matas","year":"2004","unstructured":"Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. Image Vis. Comput. 22, 761\u2013767 (2004)","journal-title":"Image Vis. Comput."},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Shahab, A., Shafait, F., Dengel, A.: Robust reading competition challenge 2: reading text in scene images. In: IEEE International Conference on Document Analysis and Recognition, pp. 1491\u20131496 (2011)","DOI":"10.1109\/ICDAR.2011.296"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: IEEE International Conference on Document Analysis and Recognition, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Sun, L., Huo, Q., Jia, W., Chen, K.: Robust text detection in natural scene images by generalized color-enhanced contrasting extremal region and neural networks. In: IEEE 22nd International Conference on Pattern Recognition, ICPR, pp. 2715\u20132720 (2014)","DOI":"10.1109\/ICPR.2014.469"},{"key":"3_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/978-3-319-10593-2_33","volume-title":"Computer Vision \u2013 ECCV 2014","author":"W Huang","year":"2014","unstructured":"Huang, W., Qiao, Y., Tang, X.: Robust scene text detection with convolution neural network induced MSER trees. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 497\u2013511. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_33"},{"key":"3_CR14","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR15","unstructured":"Zhong, Z., Jin, L., Zhang, S., Feng, Z.: DeepText: a unified framework for text proposal generation and text detection in natural images, pp. 1\u201318. arXiv preprint arXiv:1605.07314 (2015)"},{"key":"3_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-319-46484-8_4","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Tian","year":"2016","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 56\u201372. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_4"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks. In: Computer Vision and Pattern Recognition, pp. 4159\u20134167 (2016)","DOI":"10.1109\/CVPR.2016.451"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: EAST: an efficient and accurate scene text detector, pp. 2642\u20132651 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"3_CR21","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)"},{"key":"3_CR22","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","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. IEEE Trans. Pattern Anal. Mach. Intell. 39, 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. Computer Science (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"3_CR24","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. Computer Science (2014)"}],"container-title":["Lecture Notes in Computer Science","Video Analytics. Face and Facial Expression Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-12177-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,10]],"date-time":"2022-09-10T16:51:43Z","timestamp":1662828703000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-12177-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030121761","9783030121778"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-12177-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"19 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FFER","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Face and Facial Expression Recognition from Real World Videos","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"20 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ffer2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ffer.aau.dk\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"9","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"7","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"78% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"1","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"The peer review information is combined from the workshops FFER 2018 and DLPR 2018.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}