{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T20:24:58Z","timestamp":1783110298447,"version":"3.54.6"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["20HW-1 220785"],"award-info":[{"award-number":["20HW-1 220785"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Philip Leverhulme Prize"},{"name":"Royal Society Wolfson Fellowship"},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S026045\/1"],"award-info":[{"award-number":["EP\/S026045\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T003553\/1"],"award-info":[{"award-number":["EP\/T003553\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N014588\/1"],"award-info":[{"award-number":["EP\/N014588\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T017961\/1"],"award-info":[{"award-number":["EP\/T017961\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["215733\/Z\/19\/Z"],"award-info":[{"award-number":["215733\/Z\/19\/Z"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCMI"},{"DOI":"10.13039\/100012338","name":"Alan Turing Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012338","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3664982","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:07:48Z","timestamp":1771276068000},"page":"5450-5460","source":"Crossref","is-referenced-by-count":0,"title":["Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5831-0170","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3281-1202","authenticated-orcid":false,"given":"Chun-Wun","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9044-3504","authenticated-orcid":false,"given":"Junyi","family":"He","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8350-7637","authenticated-orcid":false,"given":"Yushun","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0099-6306","authenticated-orcid":false,"given":"Carola-Bibiane","family":"Sch\u00f6nlieb","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2647-8286","authenticated-orcid":false,"given":"Zhihai","family":"He","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8878-0325","authenticated-orcid":false,"given":"Angelica I.","family":"Aviles-Rivero","sequence":"additional","affiliation":[{"name":"Yau Mathematical Sciences Center, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0591"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25878-7_34"},{"key":"ref11","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu","year":"2019"},{"key":"ref12","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref13","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref14","article-title":"Plot: Prompt learning with optimal transport for vision-language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations, ICLR","author":"Chen","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521785"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521702"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127530"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521729"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref24","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557678"},{"key":"ref27","article-title":"Poincar embeddings for learning hierarchical representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Nickel","year":"2017"},{"key":"ref28","article-title":"Hyperbolic neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ganea","year":"2018"},{"key":"ref29","article-title":"Hyperbolic attention networks","author":"Gulcehre","year":"2018"},{"key":"ref30","article-title":"Hyperbolic graph convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Chami","year":"2019"},{"key":"ref31","article-title":"Hyperbolic graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Liu","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.104"},{"key":"ref33","article-title":"Probing BERT in hyperbolic spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20542"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/517"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3340550"},{"key":"ref37","first-page":"7694","article-title":"Hyperbolic image-text representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Desai","year":"2023"},{"key":"ref38","article-title":"Compositional entailment learning for hyperbolic vision-language models","author":"Pal","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680710"},{"key":"ref42","article-title":"Negative yields positive: Unified dual-path adapter for vision-language models","author":"Zhang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00499"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref47","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref54","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref55","first-page":"5389","article-title":"Do ImageNet classifiers generalize to imagenet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht","year":"2019"},{"key":"ref56","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"ref58","article-title":"Efficient and context-aware label propagation for zero-\/few-shot training-free adaptation of vision-language model","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Li","year":"2025"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11397207.pdf?arnumber=11397207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:53:35Z","timestamp":1783108415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397207\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3664982","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}