{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:07:54Z","timestamp":1742969274027,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705489"},{"type":"electronic","value":"9783031705496"}],"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\/978-3-031-70549-6_17","type":"book-chapter","created":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T09:02:15Z","timestamp":1725786135000},"page":"279-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dataset and\u00a0Benchmark for\u00a0Urdu Natural Scenes Text Detection, Recognition and\u00a0Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Hiba","family":"Maryam","sequence":"first","affiliation":[]},{"given":"Ling","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Jiajun","family":"Song","sequence":"additional","affiliation":[]},{"given":"Tajrian ABM","family":"Shafayet","sequence":"additional","affiliation":[]},{"given":"Qidi","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"17_CR1","unstructured":"Jain, R., Vijayan, R.J., Namboodiri, A.M., Jawahar, C.V.: Text detection and recognition in natural scenes. In: Proceedings of the 22nd ACM International Conference on Multimedia (MM 2014) (2014)"},{"key":"17_CR2","series-title":"LNCS","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0","volume-title":"ECCV 2016","author":"R Panda","year":"2016","unstructured":"Panda, R., Mishra, A., Jawahar, C.V.: Towards End-to-End Text Spotting in Natural Scenes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: 2012 IEEE Conference Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"17_CR4","unstructured":"Wang, T., Neumann, L., Matas, J.: Scene text localization with edges. In: Proceedings of the International Conference on Document Analysis and Recognition (ICDAR) (2011)"},{"key":"17_CR5","unstructured":"Chen, X., Yuille, A.: Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS 2014) (2014)"},{"key":"17_CR6","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 39, 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (PAMI)"},{"key":"17_CR7","first-page":"2752","volume":"25","author":"X Xu","year":"2019","unstructured":"Xu, X., Yang, W., Zhou, L., Luo, L., Gao, Z.: Text detection and recognition in scene images: a survey. IEEE Trans. Image Process. 25, 2752\u20132773 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR8","unstructured":"Anwar, M.A., Siddiqui, A.M.: Cursive-Text: A Comprehensive Dataset for End-to-End Urdu Text Recognition in Natural Scene Images (2020)"},{"key":"17_CR9","unstructured":"Kafle, K., Kanan, C., Kembhavi, A.: Analysis of CNN-based methods for question-image matching. arXiv preprint arXiv:1705.10385 (2017)"},{"key":"17_CR10","unstructured":"Kahou, S. E., Michalski, V., Konda, K., Memisevic, R., Pal, C.: Navigational CNNs: uncertainty-guided camera control for autonomous navigation. arXiv preprint arXiv:1805.07129 (2018)"},{"key":"17_CR11","unstructured":"Kise, K., Jin, Z., Kawano, Y., Nagahara, H., Taniguchi, R.: ICDAR 2019 competition on recognition of handwritten mathematical expressions and typeset formula detection"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Salvatore, C., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: CVPR (2017)","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"17_CR13","unstructured":"Liao, M.: Real-time scene text detection with differentiable binarization, 20 November 2019. arXiv.org. arXiv:1911.08947"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Wang, W.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network, 16 August 2019. arXiv.org. arXiv:1908.05900","DOI":"10.1109\/ICCV.2019.00853"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Zhu, Y.: Fourier contour embedding for arbitrary-shaped text detection, 21 April 2021. arXiv.org. arXiv:2104.10442","DOI":"10.1109\/CVPR46437.2021.00314"},{"issue":"9","key":"17_CR16","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2019","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035\u20132048 (2019). https:\/\/doi.org\/10.1109\/TPAMI.2018.2848939","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Lee, J.: On recognizing texts of arbitrary shapes with 2D self-attention, 10 October 2019. arXiv.org. arXiv:1910.04396","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Fang, S.: Read Like Humans: autonomous, bidirectional and iterative language modeling for scene text recognition, 11 March 2021. arXiv.org. arXiv:2103.06495","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"17_CR19","unstructured":"Team, G.: Gemini: a family of highly capable multimodal models, 19 December 2023. arXiv.org. arXiv:2312.11805"},{"key":"17_CR20","unstructured":"Deepopinion: GitHub - deepopinion\/anls-star-metric: Official implementation of the ANLS metric. GitHub (n.d.). https:\/\/github.com\/deepopinion\/anls-star-metric"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2015). https:\/\/doi.org\/10.1109\/tpami.2014.2366765","DOI":"10.1109\/TPAMI.2014.2366765"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70549-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T09:08:05Z","timestamp":1725786485000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70549-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705489","9783031705496"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70549-6_17","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":"9 September 2024","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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}