{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:10:39Z","timestamp":1726060239733},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030341190"},{"type":"electronic","value":"9783030341206"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-34120-6_33","type":"book-chapter","created":{"date-parts":[[2019,11,27]],"date-time":"2019-11-27T17:03:47Z","timestamp":1574874227000},"page":"406-417","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Weakly Supervised Text Detection Based on Attention Mechanism"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-0267-9905","authenticated-orcid":false,"given":"Lanfang","family":"Dong","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-1742-5262","authenticated-orcid":false,"given":"Diancheng","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7470-9077","authenticated-orcid":false,"given":"Hanchao","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,28]]},"reference":[{"key":"33_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"33_CR2","unstructured":"Xu, K., Ba, J., Kiros, R., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Ye, Y., Zhao, Z., Li, Y., et al.: Video question answering via attribute-augmented attention network learning. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 829\u2013832 (2017)","DOI":"10.1145\/3077136.3080655"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Q., Hu, Q., Huang, J.X., et al.: Enhancing recurrent neural networks with positional attention for question answerin. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 993\u2013996 (2017)","DOI":"10.1145\/3077136.3080699"},{"key":"33_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1007\/978-3-319-10593-2_34","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Jaderberg","year":"2014","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 512\u2013528. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_34"},{"key":"33_CR7","unstructured":"Wang, T., Wu, D.J., Coates A., et al.: End-to-end text recognition with convolutional neural networks. In: Proceedings of the 21st International Conference on Pattern Recognition, pp. 3304\u20133308 (2012)"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, C., Shen, W., et al.: Multi-oriented text detection with fully convolutional network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4159\u20134167 (2016)","DOI":"10.1109\/CVPR.2016.451"},{"key":"33_CR9","unstructured":"He, T., Huang, W., Qiao, Y., et al.: Accurate text localization in natural image with cascaded convolutional text network. arXiv preprint arXiv:1603.09423 (2016)"},{"key":"33_CR10","unstructured":"Yao, C., Bai, X., Sang, N., et al.: Scene text detection via holistic, multi-channel prediction. arXiv preprint arXiv:1606.09002 (2016)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"33_CR12","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":"33_CR13","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., He, T., et al.: Single shot text detector with regional attention. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3047\u20133055 (2017)","DOI":"10.1109\/ICCV.2017.331"},{"key":"33_CR15","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":"33_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yao, C., Wen, H., et al.: EAST: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, X.Y., Yin, F., et al.: Deep direct regression for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 745\u2013753 (2017)","DOI":"10.1109\/ICCV.2017.87"},{"key":"33_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"11","key":"33_CR19","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(11), 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR20","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3538\u20133545 (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"33_CR22","unstructured":"Yao, C., Bai, X., Liu, W., et al.: Detecting texts of arbitrary orientations in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1083\u20131090 (2012)"},{"key":"33_CR23","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., et al.: ICDAR 2013 competition on robust reading. In: 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493 (2013)"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., et al.: ICDAR 2015 competition on robust reading. In: 13th International Conference on Document Analysis and Recognition, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., et al.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"9","key":"33_CR26","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1109\/TPAMI.2014.2388210","volume":"37","author":"XC Yin","year":"2015","unstructured":"Yin, X.C., Pei, W.Y., Zhang, J., et al.: Multi-orientation scene text detection with adaptive clustering. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1930\u20131937 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"33_CR27","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","volume":"36","author":"XC Yin","year":"2014","unstructured":"Yin, X.C., Yin, X., Huang, K., et al.: Robust text detection in natural scene images. IEEE Trans. Pattern Anal. Mach. Intell. 36(5), 970\u2013983 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Kang, L., Li, Y., Doermann, D.: Orientation robust text line detection in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4034\u20134041 (2014)","DOI":"10.1109\/CVPR.2014.514"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Busta, M., Neumann, L., Matas, J.: Fastext: Efficient unconstrained scene text detector. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1206\u20131214 (2015)","DOI":"10.1109\/ICCV.2015.143"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., et al.: Textboxes: a fast text detector with a single deep neural network. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11196"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-34120-6_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:20:31Z","timestamp":1693527631000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-34120-6_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030341190","9783030341206"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-34120-6_33","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":"28 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.csig.org.cn\/detail\/2669","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}  <script>parent.window.postMessage('ixistenz.url:https://api.crossref.org/works/10.1007%2F978-3-030-34120-6_33', '*'); </script> <div id='browserdiffcontainer' style='position: fixed; right: 10px; top: 10vh; min-width: 60px;  border: 1px solid white; background: rgb(251, 189, 0);; opacity: 0.9; font-family: helvetica, arial, sans serif;  font-size: 12px; z-index: 20001; padding-bottom: 20px;'><div onclick="toggle('browserdiffcontainerlist'); return false;" style='background: rgb(151, 89, 0);; color: white; '><strong>&nbsp; <span class='glyphicon glyphicon-minus'></span> NODES</strong></div><div id='browserdiffcontainerlist' style='padding-left: 10px; padding-right: 5px; max-height: 50vh; overflow: auto; '><div><a href='#diffid123' style='color: white;' onClick="parent.window.postMessage('ixistenz.opendiff:123', '*');; return false;" style='text-decoration: none; '>INTERN </a> <a style='color: white;' href='#diffid123'><sup>11</sup></a></div><div><a href='#diffid878' style='color: white;' onClick="parent.window.postMessage('ixistenz.opendiff:878', '*');; return false;" style='text-decoration: none; '>Note </a> <a style='color: white;' href='#diffid878'><sup>4</sup></a></div></div></div>
<script>
function toggle( divname ) {
  var x = document.getElementById( divname );
  if (x.style.display === 'none') {
    x.style.display = 'block';
  } else {
    x.style.display = 'none';
  }
} </script>