{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:58:49Z","timestamp":1774454329272,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["62125603"],"award-info":[{"award-number":["62125603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tpami.2023.3263826","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:30:35Z","timestamp":1680543035000},"page":"10883-10897","source":"Crossref","is-referenced-by-count":51,"title":["Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3952-8753","authenticated-orcid":false,"given":"Yongming","family":"Rao","sequence":"first","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6943-3085","authenticated-orcid":false,"given":"Zuyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0920-1576","authenticated-orcid":false,"given":"Wenliang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"High-performance large-scale image recognition without normalization","author":"Brock","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.180"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00084"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref7","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref9","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref14","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014"},{"key":"ref15","article-title":"Submanifold sparse convolutional networks","author":"Graham","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1133"},{"key":"ref17","article-title":"Transformer in transformer","author":"Han","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref21","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref22","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref23","first-page":"1","article-title":"Categorical reparameterization with Gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref24","article-title":"Token labeling: Training a 85.5% top-1 accuracy vision transformer with 56M parameters on imagenet","author":"Jiang","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref27","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"ref29","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","author":"Liang","year":"2022"},{"key":"ref30","first-page":"2178","article-title":"Runtime neural pruning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11630"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref36","article-title":"Rethinking the value of network pruning","author":"Liu","year":"2018"},{"key":"ref37","article-title":"Token pooling in vision transformers","author":"Marin","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00984"},{"key":"ref40","first-page":"24898","article-title":"IA-RED: Interpretability-aware redundancy reduction for vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2878258"},{"key":"ref45","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref49","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01185"},{"key":"ref51","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref52","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref57","first-page":"2432","article-title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification","volume":"33","author":"Wang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00226"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref65","article-title":"Slimmable neural networks","author":"Yu","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.15"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref73","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10091227.pdf?arnumber=10091227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:54:30Z","timestamp":1719345270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":73,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3263826","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,1]]}}}