{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:55Z","timestamp":1777865335685,"version":"3.51.4"},"reference-count":39,"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":["62325111,62306214,U22B2011"],"award-info":[{"award-number":["62325111,62306214,U22B2011"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00329","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3445-3454","source":"Crossref","is-referenced-by-count":0,"title":["Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation"],"prefix":"10.1109","author":[{"given":"Guopeng","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Yan","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shouhong","family":"Ding","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Wuhan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gui-Song","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Wuhan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3577","article-title":"Learning lightweight object detectors via multi-teacher progressive distillation","volume-title":"International Conference on Machine Learning","author":"Cao","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01163"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref4","article-title":"Coatnet: Marrying convolution and attention for all data sizes","author":"Dai","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3483"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2443"},{"key":"ref13","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01582"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00671"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"ref17","article-title":"Function-consistent feature distillation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.048"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02002-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref23","article-title":"How do vision transformers work?","volume-title":"International Conference on Learning Representations (ICLR)","author":"Park","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref26","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref27","article-title":"Do vision transformers see like convolutional neural networks?","author":"Raghu","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01627"},{"key":"ref29","article-title":"Fitnets: Hints for thin deep nets","volume-title":"International Conference on Learning Representations (ICLR)","author":"Romero","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"ref33","article-title":"Contrastive representation distillation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tian","year":"2020"},{"key":"ref34","article-title":"Mlp-mixer: An all-mlp architecture for vision","author":"Tolstikhin","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref35","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning (ICML)","author":"Touvron","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref37","article-title":"Aligning in a compact space: Contrastive knowledge distillation between heterogeneous architectures","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00565"}],"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\/11446235.pdf?arnumber=11446235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:27Z","timestamp":1777529787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00329","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}