{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:10:34Z","timestamp":1761894634478,"version":"build-2065373602"},"reference-count":40,"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\/100017366","name":"Key Research and Development Program of Heilongjiang","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017366","id-type":"DOI","asserted-by":"publisher"}]},{"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","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\/icme59968.2025.11209794","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":["History Tracker: Retrieving Historical Image Embeddings for Efficient Fine-Grained Reasoning in Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Jiahua","family":"Bao","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxing","family":"Du","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqian","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changjiang","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TPAMI.2024.3369699"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR52733.2024.02520"},{"year":"2024","author":"Han","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1007\/978-981-97-9437-9_9"},{"year":"2024","author":"Han","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1093\/nsr\/nwae403"},{"year":"2021","author":"Zeng","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","key":"ref7"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref9","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref10","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"issue":"2","key":"ref11","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023"},{"year":"2024","author":"Lauren\u00e7on","article-title":"Building and better understanding vision-language models: insights and future directions","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/tpami.2023.3339661"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICCV51070.2023.02031"},{"year":"2024","author":"Jin","article-title":"Efficient multimodal large language models: A survey","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ASRU57964.2023.10389632"},{"key":"ref17","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu","year":"2022","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1007\/978-3-031-19827-4_41"},{"year":"2023","author":"Kopiczko","article-title":"Vera: Vector-based random matrix adaptation","key":"ref19"},{"volume-title":"The Twelfth International Conference on Learning Representations","author":"Shih-Ying","article-title":"Navigating text-to-image customization: From lycoris fine-tuning to model evaluation","key":"ref20"},{"year":"2021","author":"Hyeon-Woo","article-title":"Fedpara: Low-rank hadamard product for communication-efficient federated learning","key":"ref21"},{"year":"2023","author":"Zhang","article-title":"Adalora: Adaptive budget allocation for parameter-efficient fine-tuning","key":"ref22"},{"year":"2023","author":"Zhao","article-title":"Tuning layernorm in attention: Towards efficient multi-modal llm finetuning","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICME57554.2024.10687875"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/ICME57554.2024.10688155"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref27","first-page":"37484","article-title":"Singular value fine-tuning: Few-shot segmentation requires few-parameters fine-tuning","volume":"35","author":"Sun","year":"2022","journal-title":"NeurIPS"},{"year":"2023","author":"Lin","article-title":"Sharegpt4v: Improving large multi-modal models with better captions","key":"ref28"},{"year":"2023","article-title":"Gpt-4 technical report","key":"ref29"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref31","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.18653\/v1\/2023.acl-long.41"},{"year":"2024","article-title":"Textocr-gpt4o","key":"ref33"},{"year":"2023","author":"Oikonomou","article-title":"Chart captioning dataset","key":"ref34"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.18653\/v1\/2024.findings-emnlp.268"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1007\/978-3-319-46493-0_15"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/CVPR52733.2024.01363"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1007\/978-3-031-72658-3_13"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1093\/oed\/1158993139"},{"key":"ref40","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu","year":"2022","journal-title":"NeurIPS"}],"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\/11209794.pdf?arnumber=11209794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:32:15Z","timestamp":1761888735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209794","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}