{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T20:20:27Z","timestamp":1785702027926,"version":"3.56.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705328","type":"print"},{"value":"9783031705335","type":"electronic"}],"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\/978-3-031-70533-5_24","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"406-437","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["WikiDT: Visual-Based Table Recognition and\u00a0Question Answering Dataset"],"prefix":"10.1007","author":[{"given":"Hui","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusheng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luis","family":"Goncalves","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jishen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"24_CR1","unstructured":"Intelligent document processing market size and forecast. https:\/\/www.verifiedmarketresearch.com\/product\/intelligent-document-processing-market\/. Accessed 30 Oct 2022"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Biten, A.F., Litman, R., Xie, Y., Appalaraju, S., Manmatha, R.: LaTr: layout-aware transformer for scene-text VQA. In: CVPR 2022 (2022)","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"24_CR3","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":"24_CR4","unstructured":"Borchmann, \u0141., et al.: Due: end-to-end document understanding benchmark. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"24_CR5","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"24_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"24_CR7","unstructured":"Chen, W., et al.: Tabfact: a large-scale dataset for table-based fact verification. arXiv preprint arXiv:1909.02164 (2019)"},{"key":"24_CR8","unstructured":"Chi, Z., Huang, H., Xu, H.-D., Yu, H., Yin, W., Mao, X.-L.: Complicated table structure recognition. arXiv preprint arXiv:1908.04729 (2019)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Gao, L., et al.: ICDAR 2019 competition on table detection and recognition (CTDAR). In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1510\u20131515. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1449\u20131453. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.292"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Herzig, J., Nowak, P.K., M\u00fcller, T., Piccinno, F., Eisenschlos, J.M.: Tapas: weakly supervised table parsing via pre-training. arXiv preprint arXiv:2004.02349 (2020)","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"24_CR16","unstructured":"Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., Darrell, T., Keutzer, K.: Densenet: implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869 (2014)"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Kafle, K., Price, B., Cohen, S., Kanan, C.: DVQA: understanding data visualizations via question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5648\u20135656 (2018)","DOI":"10.1109\/CVPR.2018.00592"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Seo, M., Schwenk, D., Choi, J., Farhadi, A., Hajishirzi, H.: Are you smarter than a sixth grader? Textbook question answering for multimodal machine comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4999\u20135007 (2017)","DOI":"10.1109\/CVPR.2017.571"},{"key":"24_CR20","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: Tablebank: a benchmark dataset for table detection and recognition. arXiv preprint arXiv:1903.01949 (2019)"},{"key":"24_CR21","unstructured":"Lin, C.-Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"24_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"8","key":"24_CR23","doi-asserted-by":"publisher","first-page":"5705","DOI":"10.1007\/s10462-020-09832-7","volume":"53","author":"S Manmadhan","year":"2020","unstructured":"Manmadhan, S., Kovoor, B.C.: Visual question answering: a state-of-the-art review. Artif. Intell. Rev. 53(8), 5705\u20135745 (2020)","journal-title":"Artif. Intell. Rev."},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.V.: Infographicvqa. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"24_CR25","unstructured":"Mathew, M., Tito, R., Karatzas, D., Manmatha, R., Jawahar, C.V.: Document visual question answering challenge 2020 (2020)"},{"key":"24_CR26","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":"24_CR27","unstructured":"Monroe, W., Wang, Y.: Dependency parsing features for semantic parsing (2014)"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Paliwal, S.S., Vishwanath, D., Rahul, R., Sharma, M., Vig, L.: Tablenet: deep learning model for end-to-end table detection and tabular data extraction from scanned document images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 128\u2013133. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Pan, F., Canim, M., Glass, M., Gliozzo, A., Fox, P.: CLTR: an end-to-end, transformer-based system for cell level table retrieval and table question answering. arXiv preprint arXiv:2106.04441 (2021)","DOI":"10.18653\/v1\/2021.acl-demo.24"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Pasupat, P., Liang, P.: Compositional semantic parsing on semi-structured tables. arXiv preprint arXiv:1508.00305 (2015)","DOI":"10.3115\/v1\/P15-1142"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Prasad, D., Gadpal, A., Kapadni, K., Visave, M., Sultanpure, K.: Cascadetabnet: an approach for end to end table detection and structure recognition from image-based documents (2020)","DOI":"10.1109\/CVPRW50498.2020.00294"},{"issue":"140","key":"24_CR33","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Robertson, S., Walker, S., Jones, S., Hancock-Beaulieu, M.M., Gatford, M.: Okapi at TREC-3. In: Overview of the Third Text REtrieval Conference (TREC-3), pp. 109\u2013126. NIST, Gaithersburg, MD (1995)","DOI":"10.6028\/NIST.SP.500-225.routing-city"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Shi, H., Gao, S., Tian, Y., Chen, X., Zhao, J.: Learning bounded context-free-grammar via LSTM and the transformer: difference and the explanations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 8267\u20138276 (2022)","DOI":"10.1609\/aaai.v36i8.20801"},{"key":"24_CR36","unstructured":"Shi, H., Gu, Y., Zhou, Y., Zhao, B., Gao, S., Zhao, J.: Every preference changes differently: neural multi-interest preference model with temporal dynamics for recommendation. arXiv preprint arXiv:2207.06652 (2022)"},{"key":"24_CR37","unstructured":"Shi, H., Zhang, Y.: Deep symbolic superoptimization without human knowledge. In: ICLR 2020 (2020)"},{"key":"24_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"24_CR39","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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Smock, B., Pesala, R., Abraham, R.: PubTables-1M: towards comprehensive table extraction from unstructured documents. arXiv preprint arXiv:2110.00061 (2021)","DOI":"10.1109\/CVPR52688.2022.00459"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Yoshida, S.: Visualmrc: machine reading comprehension on document images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 13878\u201313888 (2021)","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"10","key":"24_CR43","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":"24_CR44","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 (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"24_CR45","unstructured":"Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903 (2022)"},{"key":"24_CR46","unstructured":"Zhong, V., Xiong, C., Socher, R.: Seq2sql: generating structured queries from natural language using reinforcement learning. arXiv preprint arXiv:1709.00103 (2017)"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani, E., Jimeno Yepes, A.: Image-based table recognition: data, model, and evaluation. arXiv preprint arXiv:1911.10683 (2019)","DOI":"10.1007\/978-3-030-58589-1_34"}],"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\/978-3-031-70533-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:09:05Z","timestamp":1725685745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 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"}}]}}