{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:58:05Z","timestamp":1730249885538,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687501","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["SDViT: Towards Efficient Visual Foundation Model via Unifying Sparse and Dense Representation Learning"],"prefix":"10.1109","author":[{"given":"Yin","family":"Tang","sequence":"first","affiliation":[{"name":"Nanjing Tech University,College of Computer and IE & AI,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing Normal University,College of Computer and EI & AI,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xili","family":"Wan","sequence":"additional","affiliation":[{"name":"Nanjing Tech University,College of Computer and IE & AI,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref5","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"ICML","author":"Tan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3401450"},{"key":"ref8","first-page":"11963","article-title":"Scaling up your kernels to 31x31: Revisiting large kernel design in cnns","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Ding"},{"article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani","key":"ref9"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref10"},{"key":"ref11","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"ICML","author":"Touvron"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"article-title":"Focal self-attention for local-global interactions in vision transformers","year":"2021","author":"Yang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243616"},{"article-title":"Uniformer: Unified transformer for efficient spatialtemporal representation learning","volume-title":"ICLR","author":"Li","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref25"},{"article-title":"mixup: Beyond empirical risk minimization","year":"2017","author":"Zhang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref30","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687501.pdf?arnumber=10687501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:36:47Z","timestamp":1727764607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687501","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}