{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:35:31Z","timestamp":1742999731578,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030313319"},{"type":"electronic","value":"9783030313326"}],"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\/978-3-030-31332-6_29","type":"book-chapter","created":{"date-parts":[[2019,9,21]],"date-time":"2019-09-21T15:02:34Z","timestamp":1569078154000},"page":"329-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning of Visual and Textual Data for Region Detection Applied to Item Coding"],"prefix":"10.1007","author":[{"given":"Roberto","family":"Arroyo","sequence":"first","affiliation":[]},{"given":"Javier","family":"Tovar","sequence":"additional","affiliation":[]},{"given":"Francisco J.","family":"Delgado","sequence":"additional","affiliation":[]},{"given":"Emilio J.","family":"Almaz\u00e1n","sequence":"additional","affiliation":[]},{"given":"Diego G.","family":"Serrador","sequence":"additional","affiliation":[]},{"given":"Antonio","family":"Hurtado","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,22]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Arroyo, R., Alcantarilla, P.F., Bergasa, L.M., Romera, E.: Fusion and binarization of CNN features for robust topological localization across seasons. In: International Conference on Intelligent Robots and Systems (IROS), pp. 4656\u20134663 (2016)","DOI":"10.1109\/IROS.2016.7759685"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Arroyo, R., Alcantarilla, P.F., Bergasa, L.M., Yebes, J.J., Bronte, S.: Fast and effective visual place recognition using binary codes and disparity information. In: International Conference on Intelligent Robots and Systems (IROS), pp. 3089\u20133094 (2014)","DOI":"10.1109\/IROS.2014.6942989"},{"key":"29_CR3","doi-asserted-by":"publisher","first-page":"66322","DOI":"10.1109\/ACCESS.2018.2878899","volume":"6","author":"X Bai","year":"2018","unstructured":"Bai, X., Yang, M., Lyu, P., Xu, Y., Luo, J.: Integrating scene text and visual appearance for fine-grained image classification. IEEE Access 6, 66322\u201366335 (2018)","journal-title":"IEEE Access"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Eitel, A., Springenberg, J.T., Spinello, L., Riedmiller, M.A., Burgard, W.: Multimodal deep learning for robust RGB-D object recognition. In: International Conference on Intelligent Robots and Systems (IROS), pp. 681\u2013687 (2015)","DOI":"10.1109\/IROS.2015.7353446"},{"key":"29_CR6","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-030-01249-6_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Patrick Follmann","year":"2018","unstructured":"Follmann, P., Bottger, T., Hartinger, P., Konig, R., Ulrich, M.: MVTec D2S: densely segmented supermarket dataset. In: European Conference on Computer Vision (ECCV), pp. 581\u2013597 (2018)"},{"key":"29_CR7","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1007\/978-3-030-01246-5_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Peng Gao","year":"2018","unstructured":"Gao, P., et al.: Question-guided hybrid convolution for visual question answering. In: European Conference on Computer Vision (ECCV), pp. 485\u2013501 (2018)"},{"key":"29_CR8","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 249\u2013256 (2010)"},{"key":"29_CR9","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-030-01264-9_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Llu\u00eds G\u00f3mez","year":"2018","unstructured":"Gomez, L., Mafla, A., Rusinol, M., Karatzas, D.: Single shot scene text retrieval. In: European Conference on Computer Vision (ECCV), pp. 728\u2013744 (2018)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference for Learning Representations (ICLR), pp. 1\u201315 (2015)"},{"key":"29_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems (NIPS), pp. 1106\u20131114 (2012)"},{"key":"29_CR13","unstructured":"Kulyukin, V., Kutiyanawala, A., Zama1, T., Clyde, S.: Vision-based localization and text chunking of nutrition fact tables on android smartphones. In: International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV), pp. 314\u2013320 (2013)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Lee, C., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"issue":"8","key":"29_CR15","first-page":"707","volume":"10","author":"V Levenshtein","year":"1966","unstructured":"Levenshtein, V.: Binary codes capable of correcting deletions, insertions, and reversals. J. Sov. Phys. Dokl. 10(8), 707\u2013710 (1966)","journal-title":"J. Sov. Phys. Dokl."},{"key":"29_CR16","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":"29_CR17","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-030-01228-1_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Yang Liu","year":"2018","unstructured":"Liu, Y., Wang, Z., Jin, H., Wassell, I.: Synthetically supervised feature learning for scene text recognition. In: European Conference on Computer Vision (ECCV), pp. 449\u2013465 (2018)"},{"key":"29_CR18","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-01264-9_5","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Pengyuan Lyu","year":"2018","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., Bai, X.: Mask TextSpotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: European Conference on Computer Vision (ECCV), pp. 71\u201397 (2018)"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Meyers, A., et al.: Im2Calories: towards an automated mobile vision food diary. In: International Conference on Computer Vision (ICCV), pp. 1233\u20131241 (2015)","DOI":"10.1109\/ICCV.2015.146"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1717\u20131724 (2014)","DOI":"10.1109\/CVPR.2014.222"},{"key":"29_CR21","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1007\/978-3-030-01270-0_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Shitala Prasad","year":"2018","unstructured":"Prasad, S., Kong, A.: Using object information for spotting text. In: European Conference on Computer Vision (ECCV), pp. 559\u2013576 (2018)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Qiao, S., Shen, W., Qiu, W., Liu, C., Yuille, A.: ScaleNet: guiding object proposal generation in supermarkets and beyond. In: International Conference on Computer Vision (ICCV), pp. 1791\u20131800 (2017)","DOI":"10.1109\/ICCV.2017.199"},{"key":"29_CR23","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1007\/978-3-030-01249-6_36","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Archan Ray","year":"2018","unstructured":"Ray, A., Kumar, N., Shaw, A., Mukherjee, D.P.: U-PC: unsupervised planogram compliance. In: European Conference on Computer Vision (ECCV), pp. 598\u2013613 (2018)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"29_CR25","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: International Conference on Neural Information Processing Systems (NIPS), pp. 91\u201399 (2015)"},{"key":"29_CR26","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-01216-8_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Fatemeh Sadat Saleh","year":"2018","unstructured":"Saleh, F.S., Aliakbarian, M.S., Salzmann, M., Petersson, L., Alvarez, J.M.: Effective use of synthetic data for urban scene semantic segmentation. In: European Conference on Computer Vision (ECCV), pp. 86\u2013103 (2018)"},{"key":"29_CR27","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1007\/978-3-030-01231-1_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Martin Sundermeyer","year":"2018","unstructured":"Sundermeyer, M., Marton, Z., Durner, M., Brucker, M., Triebel, R.: Implicit 3D orientation learning for 6D object detection from RGB images. In: European Conference on Computer Vision (ECCV), pp. 712\u2013729 (2018)"},{"key":"29_CR28","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/978-981-13-1580-0_20","volume-title":"First International Conference on Artificial Intelligence and Cognitive Computing","author":"V Gundimeda","year":"2019","unstructured":"Gundimeda, V., Murali, R.S., Joseph, R., Naresh Babu, N.T.: An automated computer vision system for extraction of retail food product metadata. In: Bapi, R.S., Rao, K.S., Prasad, M.V.N.K. (eds.) First International Conference on Artificial Intelligence and Cognitive Computing. AISC, vol. 815, pp. 199\u2013216. Springer, Singapore (2019). https:\/\/doi.org\/10.1007\/978-981-13-1580-0_20"},{"key":"29_CR29","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1007\/978-3-030-01231-1_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Curtis Wigington","year":"2018","unstructured":"Wigington, C., Tensmeyer, C., Davis, B., Barrett, W., Price, B., Cohen, S.: Start, follow, read: end-to-end full-page handwriting recognition. In: European Conference on Computer Vision (ECCV), pp. 372\u2013388 (2018)"},{"key":"29_CR30","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: International Conference on Neural Information Processing Systems (NIPS), pp. 3320\u20133328 (2014)"},{"key":"29_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"issue":"3","key":"29_CR32","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1177\/1932296815582222","volume":"9","author":"W Zhang","year":"2015","unstructured":"Zhang, W., Yu, Q., Siddiquie, B., Divakaran, A., Sawhney, H.S.: Snap-n-Eat: food recognition and nutrition estimation on a smartphone. J. Diab. Sci. Technol. 9(3), 525\u2013533 (2015)","journal-title":"J. Diab. Sci. Technol."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31332-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T00:09:59Z","timestamp":1695254999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-31332-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030313319","9783030313326"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31332-6_29","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":"22 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IbPRIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iberian Conference on Pattern Recognition and Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"1 July 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ibpria2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ibpria.org\/2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"137","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":"99","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":"72% - 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":"3.1","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}