{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:47:56Z","timestamp":1771458476176,"version":"3.50.1"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.00209","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:30:52Z","timestamp":1692725452000},"page":"2102-2112","source":"Crossref","is-referenced-by-count":37,"title":["Top-Down Visual Attention from Analysis by Synthesis"],"prefix":"10.1109","author":[{"given":"Baifeng","family":"Shi","sequence":"first","affiliation":[{"name":"UC Berkeley"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref57","article-title":"Unsupervised learning of structured representations via closed-loop transcription","author":"tong","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref56","article-title":"Visual attention emerges from recurrent sparse reconstruction","author":"shi","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref59","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.5.889"},{"key":"ref58","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"2526","DOI":"10.1162\/neco.2008.03-07-486","article-title":"Sparse coding via thresholding and local competition in neural circuits","volume":"20","author":"christopher","year":"2008","journal-title":"Neural Computation"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2009.01.002"},{"key":"ref11","article-title":"Rethinking attention with performers","author":"choromanski","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref55","article-title":"Theory and dynamics of perceptual bistability","author":"schrater","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2010.05.013"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"1873","DOI":"10.1152\/jn.2001.85.5.1873","article-title":"Visual spatial characterization of macaque v1 neurons","volume":"85","author":"michael","year":"2001","journal-title":"Journal of Neurophysiology"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ne.18.030195.001205"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref51","first-page":"980","article-title":"Global filter networks for image classification","volume":"34","author":"rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1097\/01.wnr.0000183900.92901.fc"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16339"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1246946"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/00335558008248231"},{"key":"ref47","first-page":"2641","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","author":"bryan","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(02)00778-X"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-50138-8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.19-01-00431.1999"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"2530","DOI":"10.1152\/jn.00692.2001","article-title":"Nature and interaction of signals from the receptive field center and surround in macaque v1 neurons","volume":"88","author":"james","year":"2002","journal-title":"Journal of Neurophysiology"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2011.04.012"},{"key":"ref9","article-title":"Where to look: A unified attention model for visual recognition with reinforcement learning","author":"chen","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Beit: Bert pre-training of image transformers","author":"bao","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8334"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.20.001434"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-9384(02)00903-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref31","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref30","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"jaegle","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-4127-8_6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511984037"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.22-19-08633.2002"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref39","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"lu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref71","first-page":"27378","article-title":"Understanding the robustness in vision transformers","author":"zhou","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2006.05.002"},{"key":"ref23","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"hendrycks","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref67","article-title":"Inference, attention, and decision in a bayesian neural architecture","volume":"17","author":"yu","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199564668.001.0001"},{"key":"ref20","author":"everingham","year":"0","journal-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref63","first-page":"145","article-title":"Synthesize then compare: Detecting failures and anomalies for semantic segmentation","author":"xia","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref65","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"geoffrey","year":"2006","journal-title":"Neural Computation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref29","first-page":"535","article-title":"Neural networks with recurrent generative feedback","volume":"33","author":"huang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref60","article-title":"Learning robust global representations by penalizing local predictive power","volume":"32","author":"wang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6111"},{"key":"ref61","first-page":"568","article-title":"Pyra-mid vision transformer: A versatile backbone for dense prediction without convolutions","author":"wang","year":"0","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2023,6,17]]},"end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10203869.pdf?arnumber=10203869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:59:11Z","timestamp":1694455151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10203869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/cvpr52729.2023.00209","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}