{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T04:48:38Z","timestamp":1746766118108,"version":"3.37.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030289560"},{"type":"electronic","value":"9783030289577"}],"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\/978-3-030-28957-7_1","type":"book-chapter","created":{"date-parts":[[2019,9,11]],"date-time":"2019-09-11T23:06:24Z","timestamp":1568243184000},"page":"3-11","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Evaluating Performance and Accuracy Improvements for Attention-OCR"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1005-4315","authenticated-orcid":false,"given":"Adam","family":"Brzeski","sequence":"first","affiliation":[]},{"given":"Kamil","family":"Grinholc","sequence":"additional","affiliation":[]},{"given":"Kamil","family":"Nowodworski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8231-709X","authenticated-orcid":false,"given":"Adam","family":"Przyby\u0142ek","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,11]]},"reference":[{"key":"1_CR1","unstructured":"Badue, C., et al.: Self-driving cars: A survey. arXiv preprint arXiv:1901.04407 (2019)"},{"key":"1_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. CoRR, abs\/1409.0473 (2014)"},{"key":"1_CR3","unstructured":"Bartz, C., Yang, H., Meinel, C.: STN-OCR: A single neural network for text detection and text recognition. CoRR, abs\/1707.08831 (2017)"},{"key":"1_CR4","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. CoRR, abs\/1506.03099 (2015)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Brzeski, A., Grinholc, K., Nowodworski, K., Przyby\u0142ek, A.: Residual mobilenets. In: Workshop on Modern Approaches in Data Engineering and Information System Design at ADBIS 2019 (2019)","DOI":"10.1007\/978-3-030-30278-8_33"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Goyal, K., Dyer, C., Berg-Kirkpatrick, T.: Differentiable scheduled sampling for credit assignment. CoRR, abs\/1704.06970 (2017)","DOI":"10.18653\/v1\/P17-2058"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. CoRR, abs\/1604.06646 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR, abs\/1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR9","unstructured":"Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"1_CR10","unstructured":"Husz\u00e1r, F.: How (not) to train your generative model: Scheduled sampling, likelihood, adversary? arXiv e-prints, November 2015"},{"key":"1_CR11","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R., (eds) Advances in Neural Information Processing Systems, vol. 28, pp. 2017\u20132025. Curran Associates Inc (2015)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C.: Towards end-to-end text spotting with convolutional recurrent neural networks. CoRR, abs\/1707.03985 (2017)","DOI":"10.1109\/ICCV.2017.560"},{"issue":"9\u201312","key":"1_CR13","doi-asserted-by":"publisher","first-page":"2509","DOI":"10.1007\/s00170-016-8628-y","volume":"87","author":"M Liukkonen","year":"2016","unstructured":"Liukkonen, M., Tsai, T.-N.: Toward decentralized intelligence in manufacturing: recent trends in automatic identification of things. Int. J. Adv. Manufact. Technol. 87(9\u201312), 2509\u20132531 (2016)","journal-title":"Int. J. Adv. Manufact. Technol."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Luong, M.-T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. CoRR, abs\/1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Mathews, A.P., Xie, L., He, X.: Semstyle: Learning to generate stylised image captions using unaligned text. CoRR, abs\/1805.07030 (2018)","DOI":"10.1109\/CVPR.2018.00896"},{"key":"1_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-540-88688-4_14","volume-title":"Computer Vision \u2013 ECCV 2008","author":"D Nist\u00e9r","year":"2008","unstructured":"Nist\u00e9r, D., Stew\u00e9nius, H.: Linear time maximally stable extremal regions. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5303, pp. 183\u2013196. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88688-4_14"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Przyby\u0142ek, K., Shkroba, I.: Crowd counting \u00e1 la bourdieu. In: Workshop on Modern Approaches in Data Engineering and Information System Design at ADBIS 2019 (2019)","DOI":"10.1007\/978-3-030-30278-8_31"},{"key":"1_CR18","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR, abs\/1506.01497 (2015)"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lv, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. CoRR, abs\/1603.03915 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"1_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"1_CR21","unstructured":"Smith, R., et al.: End-to-end interpretation of the French street name signs dataset. CoRR, abs\/1702.03970 (2017)"},{"key":"1_CR22","unstructured":"S\u00f8nderby, S.K., S\u00f8nderby, C.K., Maal\u00f8e, L., Winther, O.: Recurrent spatial transformer networks. CoRR, abs\/1509.05329 (2015)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243 (2019)","DOI":"10.18653\/v1\/P19-1355"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1007\/978-3-319-50835-1_66","volume-title":"Advances in Visual Computing","author":"AP Tafti","year":"2016","unstructured":"Tafti, A.P., Baghaie, A., Assefi, M., Arabnia, H.R., Yu, Z., Peissig, P.: OCR as a service: an experimental evaluation of Google Docs OCR, Tesseract, ABBYY FineReader, and Transym. In: Bebis, G., et al. (eds.) ISVC 2016. LNCS, vol. 10072, pp. 735\u2013746. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-50835-1_66"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Le, Q.V.: MnasNet: Platform-aware neural architecture search for mobile. arXiv preprint arXiv:1807.11626 (2018)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., Takaki, S., Yamagishi, J.: An RNN-based quantized f0 model with multi-tier feedback links for text-to-speech synthesis. In: INTERSPEECH (2017)","DOI":"10.21437\/Interspeech.2017-246"},{"key":"1_CR28","unstructured":"Wang, Y., Gao, Z., Long, M., Wang, J., Yu, P.S.: PredRNN++: Towards A resolution of the deep-in-time dilemma in spatiotemporal predictive learning. CoRR, abs\/1804.06300 (2018)"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Wojna, Z., et al.: Attention-based extraction of structured information from street view imagery. CoRR, abs\/1704.03549 (2017)","DOI":"10.1109\/ICDAR.2017.143"},{"key":"1_CR30","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/978-3-319-24702-1_9","volume-title":"Mobile Cloud Visual Media Computing","author":"C Yi","year":"2015","unstructured":"Yi, C., Tian, Y.: Assistive text reading from natural scene for blind persons. In: Hua, G., Hua, X.-S. (eds.) Mobile Cloud Visual Media Computing, pp. 219\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24702-1_9"}],"container-title":["Lecture Notes in Computer Science","Computer Information Systems and Industrial Management"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-28957-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T09:20:24Z","timestamp":1664356824000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-28957-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030289560","9783030289577"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-28957-7_1","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":"11 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CISIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Computer Information Systems and Industrial Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cisim2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/cisim2019.wi.pb.edu.pl\/","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 (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"61% - 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 (provided by the conference organizers)"}},{"value":"2-3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}