{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:09:33Z","timestamp":1778080173670,"version":"3.51.4"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3196959","type":"journal-article","created":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T19:56:11Z","timestamp":1659988571000},"page":"1-16","source":"Crossref","is-referenced-by-count":32,"title":["Glance and Focus Networks for Dynamic Visual Recognition"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1363-0234","authenticated-orcid":false,"given":"Yulin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"given":"Kangchen","family":"Lv","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"given":"Haojun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]},{"given":"Wenhui","family":"Huang","sequence":"additional","affiliation":[{"name":"China Mobile Research Insitute, Beijing, China"}]},{"given":"Pengfei","family":"Qi","sequence":"additional","affiliation":[{"name":"China Mobile Research Insitute, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-1770","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2918284"},{"key":"ref7","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref8","first-page":"103","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref9","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654948"},{"key":"ref11","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref14","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00641"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00357"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref26","article-title":"Multi-scale dense networks for resource efficient image classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref27","first-page":"458","article-title":"SpeedBoost: Anytime prediction with uniform near-optimality","volume-title":"Proc. 15th Int. Conf. Artif. Intell. Statist.","author":"Grubb"},{"key":"ref28","first-page":"2432","article-title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref29","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle"},{"key":"ref30","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref31","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref33","article-title":"Rethinking the value of network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref35","first-page":"4107","article-title":"Binarized neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hubara"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref37","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NeurIPS Deep Learn. Workshop","author":"Hinton"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3117837"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00198"},{"key":"ref41","first-page":"527","article-title":"Adaptive neural networks for efficient inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bolukbasi"},{"key":"ref42","first-page":"11960","article-title":"Not all images are worth 16 x 16 words: Dynamic transformers for efficient image recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref43","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00196"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"ref48","first-page":"2181","article-title":"Runtime neural pruning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_31"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3125263"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00353"},{"key":"ref55","first-page":"1884","article-title":"Channel gating neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hua"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref61","first-page":"1243","article-title":"Learning to combine foveal glimpses with a third-order boltzmann machine","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Larochelle"},{"key":"ref62","article-title":"Multiple object recognition with visual attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ba"},{"key":"ref63","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jaderberg"},{"key":"ref64","first-page":"1368","article-title":"Joint active feature acquisition and classification with variable-size set encoding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shim"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00984"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.016"},{"key":"ref69","first-page":"8930","article-title":"This looks like that: Deep learning for interpretable image recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042276"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00412"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00593"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00779"},{"key":"ref80","first-page":"14943","article-title":"Semantic-guided multi-attention localization for zero-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00286"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref83","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175354"},{"key":"ref85","first-page":"12 635","article-title":"Implicit semantic data augmentation for deep networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21227-7_23"},{"key":"ref87","first-page":"3282","article-title":"Processing megapixel images with deep attention-sampling models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref90","article-title":"Proxylessnas: Direct neural architecture search on target task and hardware","author":"Cai","year":"2018"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref94","article-title":"Adafuse: Adaptive temporal fusion network for efficient action recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng"},{"key":"ref95","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref97","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref98","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref99","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.26599\/air.2022.9150011"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09851927.pdf?arnumber=9851927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T04:24:35Z","timestamp":1709353475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9851927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3196959","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":[[2022]]}}}