{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T08:22:29Z","timestamp":1776846149205,"version":"3.51.2"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"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":[[2026,2,5]]},"DOI":"10.1109\/icara69401.2026.11480420","type":"proceedings-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:47:13Z","timestamp":1776800833000},"page":"457-462","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Semantic Segmentation Research of Vision Language Models"],"prefix":"10.1109","author":[{"given":"Xinyan","family":"Tan","sequence":"first","affiliation":[{"name":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangxing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haotong","family":"He","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqing","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohai","family":"He","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weimin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.295913"},{"key":"ref2","first-page":"265","article-title":"Stochastic watershed segmentation","author":"Angulo","year":"2007","journal-title":"in ISMM"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2008.2010437"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"in Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref10","article-title":"PaLI: A jointly-scaled multilingual language-image model","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"Chen","year":"2016","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref13","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0972-7_27"},{"key":"ref17","article-title":"ZegOT: Zero-shot segmentation through optimal transport of text prompts","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref23","article-title":"Semantic segmentation using adversarial networks","author":"Luc","year":"2016","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2305073"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref26","article-title":"Attention U-Net: Learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"issue":"140","key":"ref30","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"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587503"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02171-y"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref36","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Tan"},{"key":"ref37","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.60"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00183"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref41","article-title":"SEGLLM: Multi-round reasoning segmentation with large language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_16"},{"key":"ref43","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2016","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3504816"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"event":{"name":"2026 12th International Conference on Automation, Robotics and Applications (ICARA)","location":"Istanbul, Turkiye","start":{"date-parts":[[2026,2,5]]},"end":{"date-parts":[[2026,2,7]]}},"container-title":["2026 12th International Conference on Automation, Robotics and Applications (ICARA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11480269\/11480271\/11480420.pdf?arnumber=11480420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:25:04Z","timestamp":1776842704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11480420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icara69401.2026.11480420","relation":{},"subject":[],"published":{"date-parts":[[2026,2,5]]}}}