{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T09:11:30Z","timestamp":1780909890065,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819214679","type":"print"},{"value":"9789819214686","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-92-1468-6_24","type":"book-chapter","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T08:43:51Z","timestamp":1780908231000},"page":"362-373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unified Multimodal Retrieval Framework for\u00a0Multimodal RAG"],"prefix":"10.1007","author":[{"given":"Haitao","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengxue","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"24_CR1","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":"24_CR2","unstructured":"Faysse, M., et al.: ColPali: efficient document retrieval with vision language models. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"G\u00fcnther, M., et al.: jina-embeddings-v4: universal embeddings for multimodal multilingual retrieval. arXiv preprint arXiv:2506.18902 (2025)","DOI":"10.18653\/v1\/2025.mrl-main.36"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Izacard, G., Grave, E.: Leveraging passage retrieval with generative models for open domain question answering. arXiv preprint arXiv:2007.01282 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"24_CR5","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"24_CR6","unstructured":"Jiang, T., et al.: E5-v: universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580 (2024)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: EMNLP (1), pp. 6769\u20136781 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"24_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":"24_CR9","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":"24_CR10","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.: 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_CR11","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":"24_CR12","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":"24_CR13","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":"24_CR14","doi-asserted-by":"publisher","first-page":"109834","DOI":"10.1016\/j.patcog.2023.109834","volume":"144","author":"R Tito","year":"2023","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Hierarchical multimodal transformers for multipage DocVQA. Pattern Recogn. 144, 109834 (2023)","journal-title":"Pattern Recogn."},{"key":"24_CR15","unstructured":"Wang, P., et al.: One-peace: exploring one general representation model toward unlimited modalities. arXiv preprint arXiv:2305.11172 (2023)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Yan, S.Q., Gu, J.C., Zhu, Y., Ling, Z.H.: Corrective retrieval augmented generation (2024)","DOI":"10.2139\/ssrn.5267341"},{"key":"24_CR18","unstructured":"Yao, Y., et\u00a0al.: MiniCPM-v: a GPT-4v level MLLM on your phone. arXiv preprint arXiv:2408.01800 (2024)"},{"key":"24_CR19","unstructured":"Yu, S., et\u00a0al.: VisRAG: vision-based retrieval-augmented generation on multi-modality documents. arXiv preprint arXiv:2410.10594 (2024)"},{"key":"24_CR20","unstructured":"Zhang, X., et al.: GME: improving universal multimodal retrieval by multimodal LLMs. arXiv preprint arXiv:2412.16855 (2024)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, J., Liu, Z., Xiao, S., Zhao, B., Xiong, Y.: VISTA: visualized text embedding for universal multi-modal retrieval. arXiv preprint arXiv:2406.04292 (2024)","DOI":"10.18653\/v1\/2024.acl-long.175"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1468-6_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T08:44:25Z","timestamp":1780908265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1468-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819214679","9789819214686"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1468-6_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}