{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:33:32Z","timestamp":1776785612511,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888359","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["SiQA: A Large Multi-Modal Question Answering Model for Structured Images Based on RAG"],"prefix":"10.1109","author":[{"given":"Jiawang","family":"Liu","sequence":"first","affiliation":[{"name":"Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Tao","sequence":"additional","affiliation":[{"name":"Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiugong","family":"Qin","sequence":"additional","affiliation":[{"name":"Beijing Research Institute of Automation for Machinery Industry Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref3","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref4","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Li"},{"key":"ref5","article-title":"Gpt-4v(ision) system card","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41676-7_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-aacl.15"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref9","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Advances in Neural Information Processing Systems.","volume":"36","author":"Liu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref12","article-title":"Textcot: Zoom in for enhanced multimodal text-rich image understanding","author":"Luan","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00285"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.734"},{"key":"ref15","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446792"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02570"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICAAIC60222.2024.10574972"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222423"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","article-title":"Pp-ocrv3: More attempts for the improvement of ultra lightweight ocr system","author":"Li","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref26","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3183068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref30","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-020-00361-1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_39"},{"key":"ref33","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681249"},{"key":"ref35","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888359.pdf?arnumber=10888359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:07Z","timestamp":1774416127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888359","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}