{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T22:04:16Z","timestamp":1770933856320,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["42327901"],"award-info":[{"award-number":["42327901"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZC20240838"],"award-info":[{"award-number":["GZC20240838"]}]},{"DOI":"10.13039\/501100001809","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M741952"],"award-info":[{"award-number":["2023M741952"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M751692"],"award-info":[{"award-number":["2024M751692"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3609549","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T17:32:12Z","timestamp":1757698332000},"page":"2123-2136","source":"Crossref","is-referenced-by-count":0,"title":["Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformer"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3913-5482","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2821-4847","authenticated-orcid":false,"given":"Jinchao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nannan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3227717"},{"key":"ref2","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248791"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277462"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3307789"},{"key":"ref6","first-page":"6009","article-title":"Head2Toe: Utilizing intermediate representations for better transfer learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Evci"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321480"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327605"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01393"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02194"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28345"},{"key":"ref14","first-page":"52548","article-title":"Efficient adaptation of large vision transformer via adapter re-composing","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Dong"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01918-3"},{"key":"ref16","first-page":"42689","article-title":"Res-tuning: A flexible and efficient tuning paradigm via unbinding tuner from backbone","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Jiang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00328"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28978"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196959"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3274214"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref24","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01604"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00746"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref28","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref29","first-page":"12991","article-title":"LST: Ladder side-tuning for parameter and memory efficient transfer learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Sung"},{"key":"ref30","article-title":"Towards efficient visual adaption via structural re-parameterization","author":"Luo","year":"2023","journal-title":"arXiv:2302.08106"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"ref32","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. NIPS","author":"Chen"},{"key":"ref33","first-page":"1","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"He"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01579"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02213"},{"key":"ref36","article-title":"Parameter-efficient is not sufficient: Exploring parameter, memory, and time efficient adapter tuning for dense predictions","author":"Yin","year":"2023","journal-title":"arXiv:2306.09729"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29096"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref39","article-title":"Low-rank attention side-tuning for parameter-efficient fine-tuning","author":"Tang","year":"2024","journal-title":"arXiv:2402.04009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106414"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01524"},{"key":"ref43","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0304"},{"key":"ref45","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lian"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.433"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435939"},{"key":"ref48","article-title":"Adapter-X: A novel general parameter-efficient fine-tuning framework for vision","author":"Li","year":"2024","journal-title":"arXiv:2406.03051"},{"key":"ref49","first-page":"8152","article-title":"Conditional adapters: Parameter-efficient transfer learning with fast inference","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lei"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3643"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_25"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26302"},{"key":"ref54","first-page":"1","article-title":"Multi-scale dense networks for resource efficient image classification","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Huang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3554028"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00198"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3067100"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2799214"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110300"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317877"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2910751"},{"key":"ref62","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"Zhai","year":"2019","journal-title":"arXiv:1910.04867"},{"key":"ref63","volume-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11174"},{"key":"ref66","first-page":"1","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/11162716.pdf?arnumber=11162716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:25Z","timestamp":1770930145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11162716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":66,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3609549","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}