{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:17:48Z","timestamp":1771949868521,"version":"3.50.1"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585440","type":"print"},{"value":"9783030585457","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58545-7_41","type":"book-chapter","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T10:04:51Z","timestamp":1604484291000},"page":"715-732","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["Spatially Aware Multimodal Transformers for TextVQA"],"prefix":"10.1007","author":[{"given":"Yash","family":"Kant","sequence":"first","affiliation":[]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Anderson","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Schwing","sequence":"additional","affiliation":[]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[]},{"given":"Jiasen","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Harsh","family":"Agrawal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,5]]},"reference":[{"key":"41_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, 2552\u20132566 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_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":"41_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":"41_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Bigham, J.P., et al.: VizWiz: nearly real-time answers to visual questions. In: W4A (2010)","DOI":"10.1145\/1805986.1806020"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: ICDAR 2019 competition on scene text visual question answering. arXiv preprint arXiv:1907.00490 (2019)","DOI":"10.1109\/ICCV.2019.00439"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: Scene text visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4291\u20134301 (2019)","DOI":"10.1109\/ICCV.2019.00439"},{"key":"41_CR8","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":"41_CR9","doi-asserted-by":"crossref","unstructured":"Borisyuk, F., Gordo, A., Sivakumar, V.: Rosetta. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2018)","DOI":"10.1145\/3219819.3219861"},{"key":"41_CR10","unstructured":"Chen, Y.-C., et al.: UNITER: learning universal image-text representations. arXiv preprint arXiv:1909.11740 (2019)"},{"key":"41_CR11","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, Bert (2019)"},{"key":"41_CR12","unstructured":"Dong, L., et al.: Unified language model pre-training for natural language understanding and generation. In: NeurIPS (2019)"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A., Darrell, T., Rohrbach, M.: Iterative answer prediction with pointer-augmented multimodal transformers for TextVQA. arXiv preprint arXiv:1911.06258 (2019)","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"41_CR15","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":"41_CR16","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"D. Karatzas, F., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"41_CR18","unstructured":"Kipf, T., Welling, M.: Semi-supervised classification with graph convolutional networks. ArXiv, abs\/1609.02907 (2016)"},{"key":"41_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2016","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123, 32\u201373 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"41_CR20","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. arXiv:1811.00982 (2018)"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Jiang, D., Zhou, M.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training. arXiv preprint arXiv:1908.06066 (2019)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Li, L., Gan, Z., Cheng, Y., Liu, J.: Relation-aware graph attention network for visual question answering. ArXiv, abs\/1903.12314 (2019)","DOI":"10.1109\/ICCV.2019.01041"},{"key":"41_CR23","unstructured":"Li, M.H., Yatskar, L., Yin, D., Hsieh, C.-J., Chang, K.-W.: VisualBert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"41_CR24","unstructured":"Lin, Y., Zhao, H., Li, Y., Wang, D.: Dcd$$\\_$$zju, TextVQA challenge 2019 winner (2014). https:\/\/visualqa.org\/workshop.html"},{"key":"41_CR25","unstructured":"Peter, J., et al.: Generating wikipedia by summarizing long sequences. In: ICLR (2018)"},{"key":"41_CR26","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. ArXiv, abs\/1908.02265 (2019)"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. arXiv preprint arXiv:1912.02315 (2019)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"41_CR28","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances in Neural Information Processing Systems, pp. 289\u2013297 (2016)"},{"key":"41_CR29","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one? ArXiv, abs\/1905.10650 (2019)"},{"key":"41_CR30","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.V.: Image retrieval using textual cues. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.378"},{"key":"41_CR31","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: Proceedings of the International Conference on Document Analysis and Recognition (2019)","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Murahari, V., Batra, D., Parikh, D., Das, A.: Large-scale pretraining for visual dialog: a simple state-of-the-art baseline. arXiv preprint arXiv:1912.02379 (2019)","DOI":"10.1007\/978-3-030-58523-5_20"},{"key":"41_CR33","unstructured":"Qi, D., Su, L., Song, J., Cui, E.D.B., Bharti, T., Sacheti, A.: ImageBert: cross-modal pre-training with large-scale weak-supervised image-text data. ArXiv, abs\/2001.07966 (2020)"},{"key":"41_CR34","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In:NuerIPS, pp. 91\u201399 (2015)"},{"key":"41_CR35","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. ArXiv, abs\/1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"41_CR36","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8309\u20138318 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"41_CR37","unstructured":"Su, W., ZhuX., Cao, Y., Li, B., Lu, L., Wei, F., Dai, J.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"41_CR38","unstructured":"Anonymous submission. Msft$$\\_$$vti, textvqa challenge 2019 top entry (post-challenge) (2014). https:\/\/evalai.cloudcv.org\/web\/challenges\/challenge-page\/244\/"},{"key":"41_CR39","doi-asserted-by":"crossref","unstructured":"Sukhbaatar, S., Grave, E., Bojanowski, P., Joulin, A.: Adaptive attention span in transformers. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1032"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: Videobert: a joint model for video and language representation learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7464\u20137473 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"41_CR41","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"41_CR42","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"41_CR43","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018)"},{"key":"41_CR44","doi-asserted-by":"crossref","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1580"},{"key":"41_CR45","doi-asserted-by":"crossref","unstructured":"Wang, X., Tu, Z., Wang, L., Shi, S.: Self-attention with structural position representations. In: EMNLP\/IJCNLP (2019)","DOI":"10.18653\/v1\/D19-1145"},{"key":"41_CR46","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"41_CR47","doi-asserted-by":"crossref","unstructured":"Yang, B., Tu, Z., Wong, D.F., Meng, F., Chao, L.S., Zhang, T.: Modeling localness for self-attention networks. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1475"},{"key":"41_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/978-3-030-01264-9_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Yao","year":"2018","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 711\u2013727. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_42"},{"key":"41_CR49","unstructured":"Zhao, G., Lin, J., Zhang, Z., Ren, X., Su, Q., Sun, X.: Explicit sparse transformer: concentrated attention through explicit selection. ArXiv, abs\/1912.11637 (2019)"},{"key":"41_CR50","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J.J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. ArXiv, abs\/1909.11059 (2019)"},{"key":"41_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Aligning books and movies: towards story-like visual explanations by watching movies and reading books. In: IEEE International Conference on Computer Vision (ICCV), pp. 19\u201327 (2015)","DOI":"10.1109\/ICCV.2015.11"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58545-7_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T01:17:33Z","timestamp":1730683053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58545-7_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585440","9783030585457"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58545-7_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"5 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","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":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 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)"}}]}}