{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T06:21:23Z","timestamp":1778998883392,"version":"3.51.4"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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","award":["62361166670,U24A20330"],"award-info":[{"award-number":["62361166670,U24A20330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020771","name":"Young Scientists Fund of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206134"],"award-info":[{"award-number":["62206134"]}],"id":[{"id":"10.13039\/501100020771","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["07063253222"],"award-info":[{"award-number":["07063253222"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00345","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3618-3627","source":"Crossref","is-referenced-by-count":1,"title":["Advancing Textual Prompt Learning with Anchored Attributes"],"prefix":"10.1109","author":[{"given":"Zheng","family":"Li","sequence":"first","affiliation":[{"name":"VCIP, College of Computer Science, Nankai University,PCA Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibing","family":"Song","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"VCIP, College of Computer Science, Nankai University,PCA Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"VCIP, College of Computer Science, Nankai University,PCA Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"VCIP, College of Computer Science, Nankai University,PCA Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bahng","year":"2022","journal-title":"Exploring visual prompts for adapting largescale models"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02252"},{"key":"ref5","author":"Ding","year":"2024","journal-title":"Tree of attributes prompt learning for vision-language models"},{"key":"ref6","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16\u00d7 16 words: Transformers for image recognition at scale"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref8","author":"Hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref9","first-page":"5632","article-title":"Unfolding the alternating optimization for blind super resolution","volume":"33","author":"Huang","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01436"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00164"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28064"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref20","author":"Li","year":"2024","journal-title":"Unbiased regionlanguage alignment for open-vocabulary dense prediction"},{"key":"ref21","first-page":"28243","article-title":"Cascade-CLIP: Cascaded visionlanguage embeddings alignment for zero-shot semantic segmentation","author":"Li","year":"2024","journal-title":"ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110422"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref26","author":"Liu","year":"2018","journal-title":"Darts: Differentiable architecture search"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0375-z"},{"key":"ref30","author":"Menon","year":"2022","journal-title":"Visual classification via description from large language models"},{"key":"ref31","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","author":"Pham","year":"2018","journal-title":"ICML"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref33","author":"Roy","year":"2023","journal-title":"Consistency-guided prompt learning for vision-language models"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1514"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02700"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28387"},{"key":"ref39","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_18"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01372"},{"key":"ref42","author":"Yang","year":"2023","journal-title":"Clip-kd: An empirical study of distilling clip models"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257878"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28524"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref47","author":"Zhang","year":"2024","journal-title":"Tar3d: Creating high-quality 3d assets via next-part prediction"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4233-9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02438"},{"key":"ref50","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444487.pdf?arnumber=11444487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:38Z","timestamp":1777613378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00345","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}