{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:32:20Z","timestamp":1757313140107,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533105"},{"type":"electronic","value":"9783031533112"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53311-2_10","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"127-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Two-Stage Reasoning Network with\u00a0Modality Decomposition for\u00a0Text VQA"],"prefix":"10.1007","author":[{"given":"Shengrong","family":"Ling","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sisi","family":"You","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"issue":"12","key":"10_CR1","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TPAMI.2014.2339814","volume":"36","author":"J Almaz\u00e1n","year":"2014","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., Valveny, E.: Word spotting and recognition with embedded attributes. IEEE Trans. Pattern Anal. Mach. Intell. 36(12), 2552\u20132566 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR2","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, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10_CR3","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: Scene text visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4291\u20134301 (2019)","DOI":"10.1109\/ICCV.2019.00439"},{"key":"10_CR5","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Borisyuk, F., Gordo, A., Sivakumar, V.: Rosetta: large scale system for text detection and recognition in images. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 71\u201379 (2018)","DOI":"10.1145\/3219819.3219861"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Fang, C., et a.: Towards escaping from language bias and OCR error: semantics-centered text visual question answering. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 01\u201306. IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859603"},{"issue":"12","key":"10_CR8","doi-asserted-by":"publisher","first-page":"9603","DOI":"10.1109\/TPAMI.2021.3132034","volume":"44","author":"C Gao","year":"2021","unstructured":"Gao, C., et al.: Structured multimodal attentions for textVQA. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9603\u20139614 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A., Darrell, T., Rohrbach, M.: Iterative answer prediction with pointer-augmented multimodal transformers for textVQA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9992\u201310002 (2020)","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"10_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMM.2021.3120194","volume":"25","author":"ZX Jin","year":"2023","unstructured":"Jin, Z.X., et al.: Ruart: a novel text-centered solution for text-based visual question answering. IEEE Trans. Multimedia 25, 1\u201312 (2023). https:\/\/doi.org\/10.1109\/TMM.2021.3120194","journal-title":"IEEE Trans. Multimedia"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 (2016)","DOI":"10.18653\/v1\/E17-2068"},{"key":"10_CR12","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":"10_CR13","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"10_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"7","key":"10_CR15","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vision 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"10_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/978-3-030-86365-4_25","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2021","author":"C Li","year":"2021","unstructured":"Li, C., Du, Q., Wang, Q., Jin, Y.: Learning hierarchical reasoning for text-based visual question answering. In: Farka\u0161, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12893, pp. 305\u2013316. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86365-4_25"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Liu, F., Xu, G., Wu, Q., Du, Q., Jia, W., Tan, M.: Cascade reasoning network for text-based visual question answering. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4060\u20134069 (2020)","DOI":"10.1145\/3394171.3413924"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, S., Jin, L., Xie, L., Wu, Y., Wang, Z.: Omnidirectional scene text detection with sequential-free box discretization. arXiv preprint arXiv:1906.02371 (2019)","DOI":"10.24963\/ijcai.2019\/423"},{"key":"10_CR19","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"10_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"10_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"10_CR23","unstructured":"Wang, P., Yang, L., Li, H., Deng, Y., Shen, C., Zhang, Y.: A simple and robust convolutional-attention network for irregular text recognition. arXiv preprint arXiv:1904.01375 6(2), 1 (2019)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xiao, L., Lu, Y., Jin, Y., He, H.: Towards reasoning ability in scene text visual question answering. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2281\u20132289 (2021)","DOI":"10.1145\/3474085.3475390"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: On the general value of evidence, and bilingual scene-text visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10126\u201310135 (2020)","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"10_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108214","volume":"122","author":"J Wu","year":"2022","unstructured":"Wu, J., et al.: A multimodal attention fusion network with a dynamic vocabulary for TextVQA. Pattern Recogn. 122, 108214 (2022)","journal-title":"Pattern Recogn."},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Tap: text-aware pre-training for text-VQA and text-caption. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8751\u20138761 (2021)","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Gao, C., Wang, P., Wu, Q.: Simple is not easy: a simple strong baseline for TextVQA and TextCAPS. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 3608\u20133615 (2021)","DOI":"10.1609\/aaai.v35i4.16476"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53311-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:23:58Z","timestamp":1710257038000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53311-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533105","9783031533112"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53311-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","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":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","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":"112","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":"38% - 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":"3.2","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":"3.2","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)"}}]}}