{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:32:15Z","timestamp":1743096735544,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031263156"},{"type":"electronic","value":"9783031263163"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26316-3_39","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"658-674","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Two-Stage Multimodality Fusion for\u00a0High-Performance Text-Based Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Bingjia","family":"Li","sequence":"first","affiliation":[]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Minyi","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Shuigeng","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"issue":"12","key":"39_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":"39_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":"39_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Biten, A.F., Litman, R., Xie, Y., Appalaraju, S., Manmatha, R.: LATR: layout-aware transformer for scene-text VQA. arXiv preprint arXiv:2112.12494 (2021)","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"39_CR5","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":"39_CR6","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":"39_CR7","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":"39_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"12","key":"39_CR9","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":"39_CR10","doi-asserted-by":"crossref","unstructured":"Gao, D., Li, K., Wang, R., Shan, S., Chen, X.: Multi-modal graph neural network for joint reasoning on vision and scene text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12746\u201312756 (2020)","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Han, W., Huang, H., Han, T.: Finding the evidence: localization-aware answer prediction for text visual question answering. arXiv preprint arXiv:2010.02582 (2020)","DOI":"10.18653\/v1\/2020.coling-main.278"},{"key":"39_CR12","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":"39_CR13","unstructured":"Jiang, Y., Natarajan, V., Chen, X., Rohrbach, M., Batra, D., Parikh, D.: Pythia v0. 1: the winning entry to the VQA challenge 2018. arXiv preprint arXiv:1807.09956 (2018)"},{"key":"39_CR14","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":"39_CR15","unstructured":"Kim, W., Son, B., Kim, I.: VILT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"39_CR16","unstructured":"Krasin, I., et al.: Openimages: a public dataset for large-scale multi-label and multi-class image classification, vol. 2, no. 3, p. 18 (2017). Dataset. https:\/\/github.com\/openimages"},{"key":"39_CR17","unstructured":"Lamb, A.M., Alias Parth Goyal, A.G., Zhang, Y., Zhang, S., Courville, A.C., Bengio, Y.: Professor forcing: a new algorithm for training recurrent networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Lewis, D., Agam, G., Argamon, S., Frieder, O., Grossman, D., Heard, J.: Building a test collection for complex document information processing. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 665\u2013666 (2006)","DOI":"10.1145\/1148170.1148307"},{"key":"39_CR19","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":"39_CR20","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Lu, X., Fan, Z., Wang, Y., Oh, J., Ros\u00e9, C.P.: Localize, group, and select: boosting text-VQA by scene text modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2631\u20132639 (2021)","DOI":"10.1109\/ICCVW54120.2021.00297"},{"key":"39_CR22","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Mishra, A., Shekhar, S., Singh, A.K., Chakraborty, A.: OCR-VQA: visual question answering by reading text in images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 947\u2013952. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"39_CR25","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)"},{"key":"39_CR26","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":"39_CR27","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":"39_CR28","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":"39_CR29","doi-asserted-by":"crossref","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: TextOCR: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8802\u20138812 (2021)","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"39_CR30","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. In: International Conference on Learning Representations (2019)"},{"key":"39_CR31","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":"39_CR32","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":"39_CR33","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"39_CR35","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"39_CR36","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":"39_CR37","doi-asserted-by":"crossref","unstructured":"Zeng, G., Zhang, Y., Zhou, Y., Yang, X.: Beyond OCR+ VQA: involving OCR into the flow for robust and accurate TextVQA. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 376\u2013385 (2021)","DOI":"10.1145\/3474085.3475606"},{"key":"39_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, X., Yang, Q.: Position-augmented transformers with entity-aligned mesh for TextVQA. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2519\u20132528 (2021)","DOI":"10.1145\/3474085.3475425"},{"key":"39_CR39","unstructured":"Zhao, M., et al.: Towards video text visual question answering: benchmark and baseline. In: Thirty-Sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2022)"},{"key":"39_CR40","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","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26316-3_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:37:25Z","timestamp":1677659845000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26316-3_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263156","9783031263163"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26316-3_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","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":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","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":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}