{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:51:06Z","timestamp":1742914266399,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031189067"},{"type":"electronic","value":"9783031189074"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-18907-4_40","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"510-523","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Disentangled OCR: A More Granular Information for\u00a0\u201cText\u201d-to-Image Retrieval"],"prefix":"10.1007","author":[{"given":"Xinyu","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Shilin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Huen","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Anna","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"40_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1007\/978-3-030-58536-5_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"O Sidorov","year":"2020","unstructured":"Sidorov, O., Hu, R., Rohrbach, M., Singh, A.: TextCaps: a dataset for image captioning with reading comprehension. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 742\u2013758. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_44"},{"key":"40_CR2","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"40_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K-H Lee","year":"2018","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"40_CR4","unstructured":"Zeng, Y., Zhang, X., Li, H.: Multi-grained vision language pre-training: aligning texts with visual concepts. arXiv preprint arXiv:2111.08276 (2021)"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Nguyen, M.-D., Nguyen, B.T., Gurrin, C.: A deep local and global scene-graph matching for image-text retrieval. arXiv preprint arXiv:2106.02400 (2021)","DOI":"10.3233\/FAIA210049"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Diao, H., et al.: Similarity reasoning and filtration for image-text matching. arXiv preprint arXiv:2101.01368 (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"40_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1007\/978-3-030-58545-7_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Kant","year":"2020","unstructured":"Kant, Y., et al.: Spatially aware multimodal transformers for TextVQA. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 715\u2013732. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_41"},{"key":"40_CR8","unstructured":"He, P., et al.: DeBERTa: decoding-enhanced BERT with disentangled attention. arXiv preprint arXiv:2006.03654 (2020)"},{"key":"40_CR9","unstructured":"Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Ule, J., et al.: CLIP identifies Nova-regulated RNA networks in the brain. Science 302(5648), 1212\u20131215 (2003)","DOI":"10.1126\/science.1090095"},{"key":"40_CR12","unstructured":"Li, J., et al.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. arXiv preprint arXiv:2201.12086 (2022)"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Lu, X., Zhao, T., Lee, K.: VisualSparta: an embarrassingly simple approach to large-scale text-to-image search with weighted bag-of-words. arXiv preprint arXiv:2101.00265 (2021)","DOI":"10.18653\/v1\/2021.acl-long.389"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Messina, N., et al.: Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 17(4), 1\u201323 (2021)","DOI":"10.1145\/3451390"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Mafla, A., et al.: StacMR: scene-text aware cross-modal retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2021)","DOI":"10.1109\/WACV48630.2021.00227"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Cheng, M., et al.: ViSTA: vision and scene text aggregation for cross-modal retrieval. arXiv preprint arXiv:2203.16778 (2022)","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"40_CR17","first-page":"67","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. ACL 2, 67\u201378 (2014)","journal-title":"ACL"},{"key":"40_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"40_CR19","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)"},{"key":"40_CR20","unstructured":"Wang, P., et al.: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. arXiv preprint arXiv:2202.03052 (2022)"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: Is an image worth five sentences? A new look into semantics for image-text matching. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2022)","DOI":"10.1109\/WACV51458.2022.00254"},{"key":"40_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1007\/978-3-030-58621-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Liao","year":"2020","unstructured":"Liao, M., Pang, G., Huang, J., Hassner, T., Bai, X.: Mask TextSpotter v3: segmentation proposal network for robust scene text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 706\u2013722. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_41"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Scene text retrieval via joint text detection and similarity learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00453"},{"key":"40_CR24","unstructured":"Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems 28 (2015)"},{"key":"40_CR25","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems 28 (2015)"},{"key":"40_CR26","unstructured":"Zhu, Q., et al.: Simple is not easy: a simple strong baseline for TextVQA and TextCaps. arXiv preprint arXiv:2012.05153 2 (2020)"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"40_CR28","unstructured":"Huang, Z., et al.: Pixel-BERT: aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 (2020)"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Miech, A., et al.: Thinking fast and slow: efficient text-to-visual retrieval with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00970"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18907-4_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:11:11Z","timestamp":1666825871000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","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":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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)"}}]}}