{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:05:09Z","timestamp":1780589109539,"version":"3.54.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"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":["62372329"],"award-info":[{"award-number":["62372329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2021YFB2501104"],"award-info":[{"award-number":["2021YFB2501104"]}]},{"name":"Shanghai Rising Star Program","award":["21QC1400900"],"award-info":[{"award-number":["21QC1400900"]}]},{"name":"Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab Project"},{"name":"Xiaomi Young Talents Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tai.2023.3326795","type":"journal-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T14:40:03Z","timestamp":1698072003000},"page":"2517-2525","source":"Crossref","is-referenced-by-count":15,"title":["GhostViT: Expediting Vision Transformers via Cheap Operations"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8225-858X","authenticated-orcid":false,"given":"Hu","family":"Cao","sequence":"first","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-time Systems, Technische Universität München, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5998-1390","authenticated-orcid":false,"given":"Zhongnan","family":"Qu","sequence":"additional","affiliation":[{"name":"ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7416-592X","authenticated-orcid":false,"given":"Guang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4883-0073","authenticated-orcid":false,"given":"Xinyi","family":"Li","sequence":"additional","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-time Systems, Technische Universität München, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6139-868X","authenticated-orcid":false,"given":"Lothar","family":"Thiele","sequence":"additional","affiliation":[{"name":"ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-time Systems, Technische Universität München, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref2","first-page":"10347","article-title":"Training data-efficient image transformers; distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3282567"},{"key":"ref11","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Systs."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref14","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Adv. Neural Inf. Process. Systs.","volume":"34","author":"Han","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref17","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rao","year":"2021"},{"key":"ref18","first-page":"24898","article-title":"IA-RED$^{2}$: Interpretability-aware redundancy reduction for vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Systs.","author":"Pan","year":"2021"},{"key":"ref19","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang","year":"2022"},{"key":"ref20","article-title":"Attention is all you need","volume-title":"Adv. Neural Inf. Process. Systs.","author":"Vaswani","year":"2017"},{"key":"ref21","article-title":"Unified visual transformer compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"ref23","first-page":"9782","article-title":"DynaBERT: Dynamic BERT with adaptive width and depth","volume-title":"Proc. Adv. Neural Inf. Process. Systs.","author":"Hou","year":"2020"},{"key":"ref24","first-page":"14037","article-title":"Are sixteen heads really better than one?","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Systs.","volume":"32","author":"Michel","year":"2019"},{"key":"ref25","first-page":"4365","article-title":"Revealing the dark secrets of BERT","volume-title":"Proc. 9th Int. Joint Conf. Natural Lang. Process.","author":"Kovaleva","year":"2019"},{"key":"ref26","first-page":"842","article-title":"A primer in BERTology: What we know about how BERT works","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"8","author":"Rogers","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref29","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. in Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref33","first-page":"28522","article-title":"Vitae: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xu","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3224314"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2918284"},{"key":"ref37","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Neural Inf. Process. Syst."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00061"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183586"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref46","first-page":"7281","article-title":"HRFormer: High-resolution vision transformer for dense predict","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yuan","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_36"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10571778\/10292927.pdf?arnumber=10292927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:04Z","timestamp":1755911344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10292927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tai.2023.3326795","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}