{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T05:01:27Z","timestamp":1742965287108,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416781"},{"type":"electronic","value":"9783031416798"}],"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\/978-3-031-41679-8_30","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"508-521","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ICDAR 2023 Competition on\u00a0Born Digital Video Text Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2343-7750","authenticated-orcid":false,"given":"Zhibo","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0215-3684","authenticated-orcid":false,"given":"Xiaoge","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0516-167X","authenticated-orcid":false,"given":"Sibo","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7051-5347","authenticated-orcid":false,"given":"Tong","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6743-4175","authenticated-orcid":false,"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-5053","authenticated-orcid":false,"given":"Fei","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6564-4796","authenticated-orcid":false,"given":"Cong","family":"Yao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"30_CR1","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-031-19815-1_11","volume-title":"ECCV 2022","author":"D Bautista","year":"2022","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 178\u2013196. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_11"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: ICDAR 2019 competition on scene text visual question answering. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1563\u20131570. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00251"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: Scene text visual question answering. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4290\u20134300 (2019)","DOI":"10.1109\/ICCV.2019.00439"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18\u201322 June 2018, pp. 6154\u20136162. Computer Vision Foundation\/IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Lu, J., Niu, Y., Pu, S., Wu, F., Zhou, S.: You only recognize once: towards fast video text spotting. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 855\u2013863 (2019)","DOI":"10.1145\/3343031.3351093"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Chng, C.K., et al.: ICDAR2019 robust reading challenge on arbitrary-shaped text - RRC-art. In: 2019 International Conference on Document Analysis and Recognition, ICDAR 2019, Sydney, Australia, 20\u201325 September 2019, pp. 1571\u20131576. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 2315\u20132324. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"30_CR8","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, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Kuang, Z., et al.: MMOCR: a comprehensive toolbox for text detection, recognition and understanding. In: MM 2021: ACM Multimedia Conference, Virtual Event, China, 20\u201324 October 2021, pp. 3791\u20133794. ACM (2021)","DOI":"10.1145\/3474085.3478328"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition - RRC-MLT-2019. In: 2019 International Conference on Document Analysis and Recognition, ICDAR 2019, Sydney, Australia, 20\u201325 September 2019, pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Reddy, S., Mathew, M., G\u00f3mez, L., Rusi\u00f1ol, M., Karatzas, D., Jawahar, C.V.: Roadtext-1k: text detection & recognition dataset for driving videos. In: 2020 IEEE International Conference on Robotics and Automation, ICRA 2020, Paris, France, 31 May\u201331 August 2020, pp. 11074\u201311080. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196577"},{"key":"30_CR13","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":"30_CR14","unstructured":"Tian, S., Pei, W.Y., Zuo, Z.Y., Yin, X.C.: Scene text detection in video by learning locally and globally. In: International Joint Conference on Artificial Intelligence, IJCAI, pp. 2647\u20132653 (2016)"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 5987\u20135995. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"30_CR16","series-title":"LNCS","first-page":"284","volume-title":"ECCV 2022","author":"C Xue","year":"2022","unstructured":"Xue, C., Zhang, W., Hao, Y., Lu, S., Torr, P.H.S., Bai, S.: Language matters: a weakly supervised vision-language pre-training approach for scene text detection and spotting. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 284\u2013302. Springer, Cham (2022)"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Yang, X.H., He, W., Yin, F., Liu, C.L.: A unified video text detection method with network flow. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 331\u2013336 (2017)","DOI":"10.1109\/ICDAR.2017.62"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41679-8_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:42:14Z","timestamp":1729935734000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_30","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":"19 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","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":"154","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":"49% - 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":"2.89","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":"1.50","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":"Number and type of other papers accepted : IJDAR track papers","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)"}}]}}