{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:10:19Z","timestamp":1783930219512,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234318","type":"print"},{"value":"9789819234325","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3432-5_25","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:40:11Z","timestamp":1783928411000},"page":"307-318","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Entity-Aligned Cross-Modal Knowledge Graphs for Evidence Completion in Complex Document Question Answering"],"prefix":"10.1007","author":[{"given":"YanFei","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"De Gui","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengzheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenkui","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"25_CR1","unstructured":"Lewis, P., et al.: Retrieval-Augmented generation for knowledge-intensive NLP tasks. Adv. Neural Inform. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: Proceedings of ACL-IJCNLP 2021, pp. 2579\u20132591 (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking. In: Proceedings of ACM MM 2022, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: European Conference on Computer Vision (ECCV), pp. 498\u2013517 (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Ma, X., Lin, S.-C., Li, M., Chen, W., Lin, J.: Unifying multimodal retrieval via document screenshot embedding. In: Proceedings of EMNLP 2024, pp. 6492\u20136505 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.373"},{"key":"25_CR6","unstructured":"Faysse, M., et al.: ColPali: efficient document retrieval with vision language models. In: International Conference on Learning Representations (ICLR) (2025)"},{"key":"25_CR7","unstructured":"Yu, S., et al.: VisRAG: vision-based retrieval-augmented generation on multi-modality documents. In: International Conference on Learning Representations (ICLR) (2025)"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Iki, T., Hasegawa, T., Nishida, K., Saito, K., Suzuki, J.: VDocRAG: retrieval-augmented generation over visually-rich documents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.02312"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Cho, J., Mahata, D., Irsoy, O., He, Y., Bansal, M.: M3DocRAG: multi-modal retrieval is what you need for multi-page multi-document understanding. arXiv preprint arXiv:2411.04952 (2024)","DOI":"10.1109\/ICCVW69036.2025.00649"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Jain, C., et al.: SimpleDoc: multi-modal document understanding with dual-cue page retrieval and iterative refinement. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 28410\u201328427 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1443"},{"key":"25_CR11","unstructured":"Edge, D., et al.: From local to global: a graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130 (2024)"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Gutierrez, B.J., Shu, Y., Gu, Y., Yasunaga, M., Su, Y.: HippoRAG: neurobiologically inspired long-term memory for large language models. In: Adv. Neural Inform. Process. Syst. 37 (2024)","DOI":"10.52202\/079017-1902"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Hu, Y., Lei, Z., Zhang, Z., Pan, B., Ling, C., Zhao, L.: GRAG: graph retrieval-augmented generation. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 4145\u20134157 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.232"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Lee, M.-C., et al.: HybGRAG: hybrid retrieval-augmented generation on textual and relational knowledge bases. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 879\u2013893 (2025)","DOI":"10.18653\/v1\/2025.acl-long.43"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: DocVQA: A dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"25_CR16","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. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2263\u20132279 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"25_CR17","first-page":"128","volume":"174","author":"R Tito","year":"2023","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Hierarchical multimodal transformers for multi-page DocVQA. Pattern Recogn. Lett. 174, 128\u2013134 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Van Landeghem, J., et al.: Document Understanding Dataset and Evaluation (DUDE). In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19528\u201319540 (2023)","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: MMLongBench-Doc: benchmarking long-context document understanding with visualizations. In: Advances in Neural Information Processing Systems (NeurIPS) 37, Datasets and Benchmarks Track (2024)","DOI":"10.52202\/079017-3041"},{"key":"25_CR20","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16548\u201316558 (2022)","DOI":"10.1109\/CVPR52688.2022.01605"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3432-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:40:14Z","timestamp":1783928414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3432-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234318","9789819234325"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3432-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}