{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:13:21Z","timestamp":1761894801706,"version":"build-2065373602"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209313","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["MP-FIRE: An End-to-End Cross-Modal Framework for Complex Multi-Page Document Question Answering"],"prefix":"10.1109","author":[{"given":"Yongqi","family":"Yu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinxu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref2","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27828"},{"article-title":"Longformer: The long-document transformer","year":"2020","author":"Beltagy","key":"ref5"},{"key":"ref6","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"article-title":"Internlm-xcomposer2-4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4k hd","year":"2024","author":"Dong","key":"ref10"},{"key":"ref11","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"article-title":"Visrag: Vision-based retrieval-augmented generation on multi-modality documents","year":"2024","author":"Yu","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"article-title":"Jina clip: Your clip model is also your text retriever","year":"2024","author":"Koukounas","key":"ref16"},{"article-title":"Rankzephyr: Effective and robust zero-shot listwise reranking is a breeze!","year":"2023","author":"Pradeep","key":"ref17"},{"article-title":"The llama 3 herd of models","year":"2024","author":"Dubey","key":"ref18"},{"article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","key":"ref19"},{"issue":"140","key":"ref20","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"article-title":"Baichuan 2: Open large-scale language models","year":"2023","author":"Yang","key":"ref21"},{"key":"ref22","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref23"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209313.pdf?arnumber=11209313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:36:20Z","timestamp":1761888980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209313","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}