{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:56:31Z","timestamp":1752674191591,"version":"3.41.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705519"},{"type":"electronic","value":"9783031705526"}],"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\/978-3-031-70552-6_17","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"281-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring the\u00a0Capabilities of\u00a0Large Multimodal Models on\u00a0Dense Text"],"prefix":"10.1007","author":[{"given":"Shuo","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"17_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR2","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":"17_CR3","unstructured":"Bai, J., et al.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"17_CR4","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":"17_CR5","unstructured":"Chen, W., et al.: TabFact: a large-scale dataset for table-based fact verification. arXiv preprint arXiv:1909.02164 (2019)"},{"key":"17_CR6","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10032-019-00334-z","volume":"23","author":"CK Ch\u2019ng","year":"2020","unstructured":"Ch\u2019ng, C.K., Chan, C.S., Liu, C.: Total-text: towards orientation robustness in scene text detection. Int. J. Doc. Anal. Recogn. (IJDAR) 23, 31\u201352 (2020). https:\/\/doi.org\/10.1007\/s10032-019-00334-z","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"17_CR7","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"17_CR9","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Hu, W., Xu, Y., Li, Y., Li, W., Chen, Z., Tu, Z.: Bliva: a simple multimodal llm for better handling of text-rich visual questions. arXiv preprint arXiv:2308.09936 (2023)","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et\u00a0al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"17_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/978-3-030-86159-9_28","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021 Workshops","author":"M Kerroumi","year":"2021","unstructured":"Kerroumi, M., Sayem, O., Shabou, A.: VisualWordGrid: information extraction from scanned documents using a multimodal approach. In: Barney Smith, E.H., Pal, U. (eds.) ICDAR 2021. LNCS, vol. 12917, pp. 389\u2013402. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86159-9_28"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Kuang, J., et al.: Visual information extraction in the wild: practical dataset and end-to-end solution. In: The 17th International Conference on Document Analysis and Recognition (2023)","DOI":"10.1007\/978-3-031-41731-3_3"},{"issue":"7","key":"17_CR14","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vision 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"17_CR15","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, ICML 2023, 23\u201329 July 2023, Honolulu, Hawaii, USA. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 19730\u201319742. PMLR (2023)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Monkey: image resolution and text label are important things for large multi-modal models. arXiv preprint arXiv:2311.06607 (2023)","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"17_CR18","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"17_CR19","unstructured":"Liu, Y., et\u00a0al.: On the hidden mystery of OCR in large multimodal models. arXiv preprint arXiv:2305.07895 (2023)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Panteleev, D., Bissacco, A., Fujii, Y., Raptis, M.: Towards end-to-end unified scene text detection and layout analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"17_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2017)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: Chartqa: a benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"17_CR24","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":"17_CR25","doi-asserted-by":"crossref","unstructured":"Nayef, N., et\u00a0al.: 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), pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"17_CR26","unstructured":"OpenAI: Gpt-4 technical report (2023)"},{"key":"17_CR27","unstructured":"OpenAI: Gpt-4v(ision) system card (2023)"},{"key":"17_CR28","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: ICDAR2017 competition on reading chinese text in the wild (RCTW-17). In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 1429\u20131434. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"17_CR30","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, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"17_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-030-86549-8_36","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"T Stanis\u0142awek","year":"2021","unstructured":"Stanis\u0142awek, T., et al.: Kleister: key information extraction datasets involving long documents with complex layouts. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 564\u2013579. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_36"},{"key":"17_CR32","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.\u00a035, pp. 13878\u201313888 (2021)","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"17_CR33","doi-asserted-by":"publisher","first-page":"106954","DOI":"10.1016\/j.patcog.2019.06.020","volume":"96","author":"J Tang","year":"2019","unstructured":"Tang, J., Yang, Z., Wang, Y., Zheng, Q., Xu, Y., Bai, X.: Seglink++: detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern Recogn. 96, 106954 (2019)","journal-title":"Pattern Recogn."},{"key":"17_CR34","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"17_CR35","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"17_CR36","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 preprint arXiv:1601.07140 (2016)"},{"key":"17_CR37","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, pp. 10126\u201310135 (2020)","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Wu, P., Xie, S.: V*: guided visual search as a core mechanism in multimodal llms. arXiv preprint arXiv:2312.14135 (2023)","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"17_CR39","unstructured":"Ye, Q., et\u00a0al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: mPLUG-Owl2: revolutionizing multi-modal large language model with modality collaboration. arXiv preprint arXiv:2311.04257 (2023)","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"17_CR41","unstructured":"Yuliang, L., Lianwen, J., Shuaitao, Z., Sheng, Z.: Detecting curve text in the wild: new dataset and new solution. arXiv preprint arXiv:1712.02170 (2017)"},{"key":"17_CR42","unstructured":"Zhang, Y., et al.: Llavar: enhanced visual instruction tuning for text-rich image understanding. arXiv preprint arXiv:2306.17107 (2023)"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00166"}],"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\/978-3-031-70552-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:46Z","timestamp":1749996466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_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":"11 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"}}]}}