{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:07:06Z","timestamp":1777889226171,"version":"3.51.4"},"reference-count":52,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00224","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2325-2335","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Variational Test-Time Prompt Generation for Zero-Shot Generalization"],"prefix":"10.1109","author":[{"given":"Zhaoyang","family":"Wu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education,Xi'an,China,710071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education,Xi'an,China,710071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education,Xi'an,China,710071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education,Xi'an,China,710071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Lingling","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education,Xi'an,China,710071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"LiXu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education,Xi'an,China,710071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education,Xi'an,China,710071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenping","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University,Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education,Xi'an,China,710071"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3525"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.299"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_12"},{"key":"ref7","first-page":"1","article-title":"Hierarchical variational memory for few-shot learning across domains","volume-title":"ICLR","author":"Du","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref12","article-title":"Domain adaptive neural networks for vision applications","volume-title":"Proceedings of the 14th IEEE International Conference on Image Processing (ICIP)","author":"Ghifary","year":"2016"},{"key":"ref13","first-page":"10712","article-title":"Semi-implicit graph variational auto-encoders","volume-title":"NeurIPS","author":"Hasanzadeh","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref15","article-title":"Augmix: A simple data processing method to improve robustness and uncertainty","volume-title":"International Conference on Learning Representations","author":"Hendrycks","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01832"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01832"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref23","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"6965","article-title":"A probabilistic u-net for segmentation of ambiguous images","volume-title":"NeurIPS","author":"Kohl","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref26","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","volume-title":"International Conference on Learning Representations","author":"Kumar","year":"2022"},{"key":"ref27","first-page":"1508","article-title":"Variational memory encoder-decoder","volume-title":"NeurIPS","author":"Le","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref30","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"12565","article-title":"Continuous hierarchical representations with poincar\u00e9 variational auto-encoders","volume-title":"NeurIPS","author":"Mathieu","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref34","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref36","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet","volume-title":"International Conference on Machine Learning","author":"Recht","year":"2019"},{"key":"ref37","article-title":"Adamatch: A unified approach to semi-supervised learning and domain adaptation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Saito","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref41","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"NIPS","author":"Sohn","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref43","first-page":"92299248. PMLR","article-title":"Test-time training with selfsupervision for generalization under distribution shifts","volume-title":"International Conference on Machine Learning","author":"Sun","year":"2020"},{"key":"ref44","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proceedings of the IEEE\/CVF International Conference on Learning Representations (ICLR)","author":"Wang","year":"2021"},{"key":"ref45","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems, 32"},{"key":"ref46","article-title":"Dynaprompt: Dynamic test-time prompt tuning","author":"Xiao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"C-tpt: Calibrated test-time prompt tuning for visionlanguage models via text feature dispersion","author":"Suk Yoon","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29611"},{"key":"ref50","article-title":"Tent++: Enhancing tent with higherorder regularization for test-time adaptation","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref52","first-page":"5499","article-title":"Learning to prompt for vision-language models","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhou","year":"2022"}],"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\/11443444.pdf?arnumber=11443444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:12Z","timestamp":1777612152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00224","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}