{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:53:28Z","timestamp":1781571208861,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819540877","type":"print"},{"value":"9789819540884","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4088-4_5","type":"book-chapter","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T14:14:29Z","timestamp":1762611269000},"page":"63-77","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CoFi-VisRAG: Coarse-to-Fine Visual Retrieval-Augmented Generation for\u00a0Multimodal Documents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6029-5532","authenticated-orcid":false,"given":"Chunming","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zibo","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongtong","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guotong","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhunchen","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"5_CR1","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Chang, Y., Narang, M., Suzuki, H., Cao, G., Gao, J., Bisk, Y.: WebQA: multihop and multimodal QA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16495\u201316504 (2022)","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: BGE M3-embedding: multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"5_CR4","unstructured":"Chen, Z., et al.: MindSearch: mimicking human minds elicits deep AI searcher. arXiv preprint arXiv:2407.20183 (2024)"},{"key":"5_CR5","unstructured":"Faysse, M., et al.: ColPali: efficient document retrieval with vision language models. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"5_CR6","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: International Conference on Machine Learning, pp. 3929\u20133938. PMLR (2020)"},{"key":"5_CR7","unstructured":"Lee, C., et al.: NV-Embed: improved techniques for training LLMs as generalist embedding models. arXiv preprint arXiv:2405.17428 (2024)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Multimodal arXiv: a dataset for improving scientific comprehension of large vision-language models. arXiv preprint arXiv:2403.00231 (2024)","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Luo, M., Fang, Z., Gokhale, T., Yang, Y., Baral, C.: End-to-end knowledge retrieval with multi-modal queries. arXiv preprint arXiv:2306.00424 (2023)","DOI":"10.18653\/v1\/2023.acl-long.478"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Ma, X., Lin, S.C., Li, M., Chen, W., Lin, J.: Unifying multimodal retrieval via document screenshot embedding. arXiv preprint arXiv:2406.11251 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.373"},{"key":"5_CR11","unstructured":"Ma, Y., et\u00a0al.: MMLongBench-Doc: benchmarking long-context document understanding with visualizations. arXiv preprint arXiv:2407.01523 (2024)"},{"key":"5_CR12","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":"5_CR13","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":"5_CR14","doi-asserted-by":"crossref","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: PlotQA: reasoning over scientific plots. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1527\u20131536 (2020)","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Sharifymoghaddam, S., Upadhyay, S., Chen, W., Lin, J.: UniRAG: universal retrieval augmentation for multi-modal large language models. arXiv preprint arXiv:2405.10311 (2024)","DOI":"10.18653\/v1\/2025.findings-naacl.108"},{"key":"5_CR16","unstructured":"Tan, C., et al.: Retrieval meets reasoning: even high-school textbook knowledge benefits multimodal reasoning. arXiv preprint arXiv:2405.20834 (2024)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Nishida, K., Hasegawa, T., Saito, I., Saito, K.: SlideVQA: a dataset for document visual question answering on multiple images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 13636\u201313645 (2023)","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Wei, C., et al.: UniIR: training and benchmarking universal multimodal information retrievers. In: European Conference on Computer Vision, pp. 387\u2013404. Springer (2024)","DOI":"10.1007\/978-3-031-73021-4_23"},{"key":"5_CR19","unstructured":"Yu, S., et\u00a0al.: VisRAG: vision-based retrieval-augmented generation on multi-modality documents. arXiv preprint arXiv:2410.10594 (2024)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Yu, Z., Xiong, C., Yu, S., Liu, Z.: Augmentation-adapted retriever improves generalization of language models as generic plug-in. arXiv preprint arXiv:2305.17331 (2023)","DOI":"10.18653\/v1\/2023.acl-long.136"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"5_CR22","unstructured":"Zheng, X., et al.: Retrieval augmented generation and understanding in vision: a survey and new outlook. arXiv preprint arXiv:2503.18016 (2025)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Zou, A., et al.: DOCBENCH: a benchmark for evaluating LLM-based document reading systems. arXiv preprint arXiv:2407.10701 (2024)","DOI":"10.18653\/v1\/2025.knowledgenlp-1.29"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4088-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:04:05Z","timestamp":1781568245000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4088-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819540877","9789819540884"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4088-4_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}