{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:24:44Z","timestamp":1759332284166,"version":"3.37.3"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0160300"],"award-info":[{"award-number":["2022ZD0160300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101137","62071127"],"award-info":[{"award-number":["62101137","62071127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["23ZR1402900"],"award-info":[{"award-number":["23ZR1402900"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3410532","type":"journal-article","created":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:30:34Z","timestamp":1717695034000},"page":"10720-10730","source":"Crossref","is-referenced-by-count":2,"title":["Lightweight Model Pre-Training via Language Guided Knowledge Distillation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3758-0018","authenticated-orcid":false,"given":"Mingsheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5293-9169","authenticated-orcid":false,"given":"Lin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhen","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6744-0671","authenticated-orcid":false,"given":"Zilong","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent GY-Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5570-2710","authenticated-orcid":false,"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent GY-Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7494-0255","authenticated-orcid":false,"given":"Jiayuan","family":"Fan","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9818","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00895"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20120"},{"key":"ref3","first-page":"24031","article-title":"Self-supervised models are good teaching assistants for vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2022"},{"key":"ref4","article-title":"SEED: Self-supervised distillation for visual representation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fang","year":"2021"},{"key":"ref5","article-title":"Bag of instances aggregation boosts self-supervised distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_17"},{"key":"ref7","first-page":"12980","article-title":"Compress: Self-supervised learning by compressing representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Abbasi Koohpayegani","year":"2020"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266169"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3147032"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3276708"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3152086"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3324588"},{"key":"ref20","first-page":"1","article-title":"DisCo: Remedy self-supervised learning on lightweight models with distilled contrastive learning","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Gao","year":"2022"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3283916"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237166"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref25","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref26","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"Yao","year":"2022","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"article-title":"ActionCLIP: A new paradigm for video action recognition","year":"2021","author":"Wang","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref31","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Deep Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref33","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2015","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref34","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2017","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref37","article-title":"Contrastive representation distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","year":"2023","author":"Liu","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"year":"2007","key":"ref42","article-title":"Caltech-256 object category dataset"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"article-title":"MMDetection: Open MMLab detection toolbox and benchmark","year":"2019","author":"Chen","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref53","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2020","journal-title":"Proc. Int. Conf. Learn. Representations"},{"article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","year":"2020","author":"Contributors","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"article-title":"Point-bind & point-LLM: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following","year":"2023","author":"Guo","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref60","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10551493.pdf?arnumber=10551493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:25:38Z","timestamp":1732667138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10551493\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3410532","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2024]]}}}