{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:16:33Z","timestamp":1778080593570,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3290070","type":"journal-article","created":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T17:38:33Z","timestamp":1687887513000},"page":"72295-72305","source":"Crossref","is-referenced-by-count":2,"title":["CLIP Driven Few-Shot Panoptic Segmentation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5632-7780","authenticated-orcid":false,"given":"Pengfei","family":"Xian","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5185-1492","authenticated-orcid":false,"given":"Lai-Man","family":"Po","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8561-2206","authenticated-orcid":false,"given":"Yuzhi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9559-1055","authenticated-orcid":false,"given":"Wing-Yin","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9586-2812","authenticated-orcid":false,"given":"Kwok-Wai","family":"Cheung","sequence":"additional","affiliation":[{"name":"School of Communication, The Hang Seng University of Hong Kong, Siu Lek Yuen, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref31","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref10","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Computer Vision-ECCV"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00657"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref38","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"gu","year":"2021","journal-title":"arXiv 2104 13921"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00719"},{"key":"ref18","article-title":"Learning to fuse things and stuff","author":"li","year":"2018","journal-title":"arXiv 1812 01192"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00073"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref23","article-title":"DeeperLab: Single-shot image parser","author":"yang","year":"2019","journal-title":"arXiv 1902 05093"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref26","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref47","author":"wu","year":"2019","journal-title":"Detectron2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref42","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00745"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00847"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref28","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref29","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref8","article-title":"Language-driven semantic segmentation","author":"li","year":"2022","journal-title":"arXiv 2201 03546"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref4","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","author":"fang","year":"2021","journal-title":"arXiv 2106 11097"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10164075.pdf?arnumber=10164075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T18:13:51Z","timestamp":1694456031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10164075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3290070","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}