{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T13:15:43Z","timestamp":1782134143847,"version":"3.54.5"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100013546","name":"Key Research Base of Humanities and Social Sciences in Jiangxi Universities, in 2023","doi-asserted-by":"publisher","award":["JD23003"],"award-info":[{"award-number":["JD23003"]}],"id":[{"id":"10.13039\/100013546","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3408843","type":"journal-article","created":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T17:41:58Z","timestamp":1717436518000},"page":"87713-87727","source":"Crossref","is-referenced-by-count":21,"title":["Automatic Estimation for Visual Quality Changes of Street Space via Street-View Images and Multimodal Large Language Models"],"prefix":"10.1109","volume":"12","author":[{"given":"Hao","family":"Liang","sequence":"first","affiliation":[{"name":"College of Landscape Architecture, Nanjing Forestry University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6330-6723","authenticated-orcid":false,"given":"Jiaxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Architecture and Design College, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunqin","family":"Li","sequence":"additional","affiliation":[{"name":"Architecture and Design College, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2911-5595","authenticated-orcid":false,"given":"Bowen","family":"Wang","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, Osaka University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2435-4353","authenticated-orcid":false,"given":"Jingyong","family":"Huang","sequence":"additional","affiliation":[{"name":"Architecture and Design College, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cities.2021.103229"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2875759"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42949-023-00124-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.142391"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.landurbplan.2018.09.015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3292181"},{"key":"ref7","volume-title":"The Social Life of Small Urban Spaces","author":"Whyte","year":"1980"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2019.101888"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.landurbplan.2021.104217"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi11050282"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2015.10.004"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3005403"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref14","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/su11226424"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2022.104140"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00259"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.4324\/9781003205722-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3145035"},{"key":"ref22","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref23","volume-title":"OpenAI ChatGPT","year":"2023"},{"key":"ref24","article-title":"A survey on multimodal large language models","author":"Yin","year":"2023","journal-title":"arXiv:2306.13549"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3061756"},{"key":"ref26","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref27","article-title":"BLIP-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref28","article-title":"VideoChat: Chat-centric video understanding","author":"Li","year":"2023","journal-title":"arXiv:2305.06355"},{"key":"ref29","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. NIPS","author":"Liu"},{"key":"ref30","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref31","article-title":"Capabilities of GPT-4 on medical challenge problems","author":"Nori","year":"2023","journal-title":"arXiv:2303.13375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jenvman.2022.116826"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/rs14040826"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.landurbplan.2022.104603"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi9060341"},{"issue":"7","key":"ref38","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.3390\/land12071322","article-title":"Uncovering bias in objective mapping and subjective perception of urban building functionality: A machine learning approach to urban spatial perception","volume":"12","author":"Zhang","year":"2023","journal-title":"Land"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102463"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01055"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/17549170801903496"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/jcde\/qwac086"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.cities.2021.103482"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/00139165211014609"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/rs11111259"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1700035114"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref49","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref50","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv:2303.16199"},{"key":"ref51","article-title":"LLaMA-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv:2304.15010"},{"key":"ref52","article-title":"Multimodal-GPT: A vision and language model for dialogue with humans","author":"Gong","year":"2023","journal-title":"arXiv:2305.04790"},{"key":"ref53","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv:2305.16355"},{"key":"ref54","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref55","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023","journal-title":"arXiv:2308.01390"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103591"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref58","article-title":"Generative agents in the streets: Exploring the use of large language models (LLMs) in collecting urban perceptions","author":"Verma","year":"2023","journal-title":"arXiv:2312.13126"},{"key":"ref59","article-title":"MultiInstruct: Improving multi-modal zero-shot learning via instruction tuning","author":"Xu","year":"2022","journal-title":"arXiv:2212.10773"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref61","article-title":"Orca: Progressive learning from complex explanation traces of GPT-4","author":"Mukherjee","year":"2023","journal-title":"arXiv:2306.02707"},{"key":"ref62","article-title":"Exploring the reasoning abilities of multimodal large language models (MLLMs): A comprehensive survey on emerging trends in multimodal reasoning","author":"Wang","year":"2024","journal-title":"arXiv:2401.06805"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10546929.pdf?arnumber=10546929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T18:46:58Z","timestamp":1719600418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10546929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3408843","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}