{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:14:26Z","timestamp":1781018066681,"version":"3.54.1"},"reference-count":39,"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"}],"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"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008081","name":"Southeast University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889170","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":3,"title":["CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models"],"prefix":"10.1109","author":[{"given":"Yeyuan","family":"Wang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,School of Automation,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dehong","family":"Gao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Cybersecurity,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Automation,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rujiao","family":"Long","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yi","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Cai","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Automation,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Libin","family":"Yang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Cybersecurity,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southeast University,The Key Laboratory of Measurement and Control of CSE, Ministry of Education, School of Automation,Nanjing,China,210096"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanqing","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Xuan","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"issue":"3","key":"ref2","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref3","doi-asserted-by":"crossref","article-title":"Chatgpt based contrastive learning for radiology report summarization","author":"Jiang","DOI":"10.2139\/ssrn.4485806"},{"key":"ref4","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref6","article-title":"Instructblip: Towards general-purpose visionlanguage models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref7","author":"Ge","year":"2023","journal-title":"Making llama see and draw with seed tokenizer"},{"key":"ref8","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref9","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_23"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32869"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref15","first-page":"4904","article-title":"Scaling up visual and visionlanguage representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"ref17","article-title":"Filip: Fine-grained interactive language-image pre-training","volume-title":"International Conference on Learning Representations","author":"Yao"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.56"},{"key":"ref19","author":"Chen","year":"2023","journal-title":"Positionenhanced visual instruction tuning for multimodal large language models"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01313"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref23","article-title":"Fine-grained visual prompting","volume":"36","author":"Yang","year":"2024","journal-title":"Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref25","author":"Yang","year":"2023","journal-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01255"},{"key":"ref28","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.98"},{"key":"ref30","author":"Wu","year":"2023","journal-title":"Next-gpt: Any-to-any multimodal llm"},{"key":"ref31","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref32","author":"Chen","year":"2023","journal-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic"},{"key":"ref33","author":"Bai","year":"2023","journal-title":"Qwen-vl: A frontier large vision-language model with versatile abilities"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref35","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref38","author":"Shao","year":"2024","journal-title":"Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models"},{"key":"ref39","author":"Luan","year":"2024","journal-title":"Textcot: Zoom in for enhanced multimodal text-rich image understanding"}],"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\/10889170.pdf?arnumber=10889170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:13Z","timestamp":1774416373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889170\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889170","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}