{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T10:40:09Z","timestamp":1768473609169,"version":"3.49.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416781","type":"print"},{"value":"9783031416798","type":"electronic"}],"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_23","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"405-419","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["ICDAR 2023 Competition on\u00a0Video Text Reading for\u00a0Dense and\u00a0Small Text"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6011-5174","authenticated-orcid":false,"given":"Weijia","family":"Wu","sequence":"first","affiliation":[]},{"given":"Yuzhong","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Zhuang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jiahong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Mike Zheng","family":"Shou","sequence":"additional","affiliation":[]},{"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[]},{"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"issue":"6","key":"23_CR1","doi-asserted-by":"publisher","first-page":"2752","DOI":"10.1109\/TIP.2016.2554321","volume":"25","author":"X-C Yin","year":"2016","unstructured":"Yin, X.-C., Zuo, Z.-Y., Tian, S., Liu, C.-L.: Text detection, tracking and recognition in video: a comprehensive survey. IEEE Trans. Image Process. 25(6), 2752\u20132773 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR2","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using lstms. In: International Conference on Machine Learning, pp. 843\u2013852 (2015)"},{"issue":"8","key":"23_CR3","first-page":"4065","volume":"44","author":"J Dong","year":"2021","unstructured":"Dong, J., et al.: Dual encoding for video retrieval by text. IEEE Trans. Pattern Anal. Mach. Intell. 44(8), 4065\u20134080 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"23_CR4","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TITS.2008.922938","volume":"9","author":"C-NE Anagnostopoulos","year":"2008","unstructured":"Anagnostopoulos, C.-N.E., Anagnostopoulos, I.E., Psoroulas, I.D., Loumos, V., Kayafas, E.: License plate recognition from still images and video sequences: a survey. IEEE Trans. Intell. Transp. Syst. 9(3), 377\u2013391 (2008)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"23_CR5","first-page":"1156","volume":"2015","author":"D Karatzas","year":"2015","unstructured":"Karatzas, D., et al.: Competition on robust reading. IEEE Int. Conf. Doc. Anal. Recogn. 2015, 1156\u20131160 (2015)","journal-title":"IEEE Int. Conf. Doc. Anal. Recogn."},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Nguyen, P.X., Wang, K., Belongie, S.: Video text detection and recognition: dataset and benchmark. In: IEEE Winter Conference on Applications of Computer Vision, pp. 776\u2013783 (2014)","DOI":"10.1109\/WACV.2014.6836024"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Reddy, S., Mathew, M., Gomez, L., Rusinol, M., Karatzas, D., Jawahar, C.: Roadtext-1k: text detection & recognition dataset for driving videos. In: IEEE International Conference on Robotics and Automation, pp. 11 074\u201311 080 (2020)","DOI":"10.1109\/ICRA40945.2020.9196577"},{"key":"23_CR8","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: ACM International Conference on Multimedia, pp. 855\u2013863 (2019)","DOI":"10.1145\/3343031.3351093"},{"key":"23_CR9","unstructured":"Wu, W., et al.: A bilingual, Openworld video text dataset and end-to-end video text spotter with transformer. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"23_CR10","unstructured":"Zhou, X., Zhou, S., Yao, C., Cao, Z., Yin, Q.: Icdar 2015 text reading in the wild competition, arXiv preprintarXiv:1506.03184 (2015)"},{"key":"23_CR11","unstructured":"Dendorfer, P., et al.: Cvpr19 tracking and detection challenge: how crowded can it get? arXiv preprintarXiv:1906.04567 (2019)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: Icdar,: robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, vol. 2013, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., Nevatia, R.: Learning to associate: Hybridboosted multi-target tracker for crowded scene. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2009, pp. 2953\u20132960. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206735"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Workshops of European Conference on Computer Vision, pp. 17\u201335 (2016)","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"23_CR15","unstructured":"Wu, W., et al.: End-to-end video text spotting with transformer, arXiv preprintarXiv:2203.10539, (2022)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"issue":"10","key":"23_CR17","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Internimage: exploring large-scale vision foundation models with deformable convolutions, arXiv preprintarXiv:2211.05778 (2022)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"23_CR19","doi-asserted-by":"publisher","unstructured":"Zhang, Y., et al.: Bytetrack: multi-object tracking by associating every detection box. In: Computer Vision-ECCV,: 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXII. Springer vol. 2022, pp. 1\u201321 (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_1","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"23_CR22","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, no. 07, pp. 11 474\u201311 481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"23_CR23","doi-asserted-by":"publisher","first-page":"9321","DOI":"10.1109\/TIP.2021.3124313","volume":"30","author":"Y Gao","year":"2021","unstructured":"Gao, Y., et al.: Video text tracking with a spatio-temporal complementary model. IEEE Trans. Image Process. 30, 9321\u20139331 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR24","unstructured":"Aharon, N., Orfaig, R., Bobrovsky, B.-Z.: Bot-sort: robust associations multi-pedestrian tracking, arXiv preprintarXiv:2206.14651 (2022)"},{"key":"23_CR25","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 preprintarXiv:1601.07140 (2016)"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: Icdar2017 competition on reading Chinese text in the wild (rctw-17). In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1429\u20131434. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"23_CR27","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), pp. 1571\u20131576. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, J., Liu, W., Han, J., Ding, E., Liu, J.: Chinese street view text: large-scale Chinese text reading with partially supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9086\u20139095 (2019)","DOI":"10.1109\/ICCV.2019.00918"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"autista, 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.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13688, pp. 178\u2013196. Springer, Cham (2022).","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"23_CR31","unstructured":"Wu, W., et al.: Real-time end-to-end video text spotter with contrastive representation learning, arXiv preprintarXiv:2207.08417 (2022)"}],"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_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:42:25Z","timestamp":1729935745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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)"}}]}}