{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T19:53:50Z","timestamp":1789156430291,"version":"build-2803163510"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CoCoSys, one of seven centers in JUMP 2.0, a Semiconductor Research Corporation (SRC) program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcds.2024.3390597","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T17:37:51Z","timestamp":1713375471000},"page":"1843-1860","source":"Crossref","is-referenced-by-count":3,"title":["Toward Two-Stream Foveation-Based Active Vision Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8849-8971","authenticated-orcid":false,"given":"Timur","family":"Ibrayev","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2704-3580","authenticated-orcid":false,"given":"Amitangshu","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3446-0243","authenticated-orcid":false,"given":"Sai Aparna","family":"Aketi","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0735-9695","authenticated-orcid":false,"given":"Kaushik","family":"Roy","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2833071"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3185028"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3210278"},{"key":"ref7","first-page":"6972","article-title":"Learning to combine top-down and bottom-up signals in recurrent neural networks with attention over modules","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mittal","year":"2020"},{"key":"ref8","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3274179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2651643"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2706975"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3197616"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3025057"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3149602"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3350982"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2915763"},{"key":"ref17","first-page":"702","article-title":"Saccader: Improving accuracy of hard attention models for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Elsayed","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161164"},{"key":"ref19","article-title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(92)90344-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3389\/fnint.2016.00037"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X0200002X"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref24","article-title":"The Caltech-UCSD Birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/science.163.3870.895"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(83)90190-X"},{"key":"ref29","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.834657"},{"key":"ref32","article-title":"Emergent properties of foveated perceptual systems","author":"Deza","year":"2020"},{"key":"ref33","article-title":"Unbiased teacher for semi-supervised object detection","author":"Liu","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00879"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"ref40","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref41","article-title":"Localizing objects with self-supervised transformers and no labels","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Sim\u00e9oni","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.286"},{"key":"ref45","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Mnih","year":"2014"},{"key":"ref46","first-page":"1","article-title":"Multiple object recognition with visual attention","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Ba","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref48","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32","author":"Paszke","year":"2019"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00732"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01347"},{"key":"ref54","first-page":"1","article-title":"Exploring foveation and saccade for improved weakly-supervised localization","volume-title":"Proc. NeurIPS Workshop Gaze Meets ML","author":"Ibrayev","year":"2023"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7274989\/10716573\/10504691-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10716573\/10504691.pdf?arnumber=10504691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T04:43:56Z","timestamp":1728967436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":54,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2024.3390597","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}