{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T18:55:01Z","timestamp":1769626501829,"version":"3.49.0"},"reference-count":87,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2022,4,24]],"date-time":"2022-04-24T00:00:00Z","timestamp":1650758400000},"content-version":"am","delay-in-days":235,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA9453-18-1-0039"],"award-info":[{"award-number":["FA9453-18-1-0039"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1016\/j.neunet.2021.03.003","type":"journal-article","created":{"date-parts":[[2021,4,20]],"date-time":"2021-04-20T21:47:22Z","timestamp":1618955242000},"page":"145-159","update-policy":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":8,"special_numbering":"C","title":["Unsupervised foveal vision neural architecture with top-down attention"],"prefix":"10.1016","volume":"141","author":[{"given":"Ryan","family":"Burt","sequence":"first","affiliation":[]},{"given":"Nina N.","family":"Thigpen","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Keil","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/orcid.org\/0000-0002-3449-3531","authenticated-orcid":false,"given":"Jose C.","family":"Principe","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2021.03.003_b1","series-title":"IEEE computer vision and pattern recognition","first-page":"1597","article-title":"Frequency-tuned salient region detection","author":"Achanta","year":"2009"},{"key":"10.1016\/j.neunet.2021.03.003_b2","series-title":"Acoustics, speech and signal processing (ICASSP), 2013 IEEE international conference on","first-page":"2596","article-title":"A multi-resolution saliency framework to drive foveation","author":"Advani","year":"2013"},{"key":"10.1016\/j.neunet.2021.03.003_b3","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Carreira, J., & Malik, J. (2015). Learning to see by moving. In Proceedings of the IEEE International conference on computer vision (pp. 37\u201345).","DOI":"10.1109\/ICCV.2015.13"},{"key":"10.1016\/j.neunet.2021.03.003_b4","series-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2018"},{"key":"10.1016\/j.neunet.2021.03.003_b5","unstructured":"Bazzani, L., Freitas, N., & Ting, J. (2011). Learning attentional mechanisms for simultaneous object tracking and recognition with deep networks. In International Conference on machine learning."},{"key":"10.1016\/j.neunet.2021.03.003_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2020.07.047","article-title":"Modeling bottom-up and top-down attention with neurodynamic model of V1","author":"Berga","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2021.03.003_b7","series-title":"A large scale fixation dataset for boosting saliency research","author":"Borji","year":"2015"},{"issue":"1","key":"10.1016\/j.neunet.2021.03.003_b8","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/TIP.2012.2210727","article-title":"Quantitative analysis of human-model agreement in visual saliency modeling: A comparative study","volume":"22","author":"Borji","year":"2013","journal-title":"IEEE Transactions on Image Processing"},{"issue":"11","key":"10.1016\/j.neunet.2021.03.003_b9","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1111\/j.1469-8986.2011.01223.x","article-title":"Scan patterns when viewing natural scenes: Emotion, complexity, and repetition","volume":"48","author":"Bradley","year":"2011","journal-title":"Psychophysiology"},{"issue":"9","key":"10.1016\/j.neunet.2021.03.003_b10","doi-asserted-by":"crossref","DOI":"10.1167\/7.9.950","article-title":"Attention based on information maximization","volume":"7","author":"Bruce","year":"2007","journal-title":"Journal of Vision"},{"key":"10.1016\/j.neunet.2021.03.003_b11","series-title":"IEEE international conference on acoustics, speech and signal processing","first-page":"1606","article-title":"Predicting visual attention using gamma kernels","author":"Burt","year":"2016"},{"key":"10.1016\/j.neunet.2021.03.003_b12","series-title":"Mit saliency benchmark","author":"Bylinskii","year":"2015"},{"issue":"9","key":"10.1016\/j.neunet.2021.03.003_b13","first-page":"1992","article-title":"Context dependent encoding using convolutional dynamic networks","volume":"26","author":"Chalasani","year":"2015","journal-title":"IEEE Transactions on Neural Networks and Intelligent Systems"},{"issue":"5","key":"10.1016\/j.neunet.2021.03.003_b14","doi-asserted-by":"crossref","first-page":"29 1","DOI":"10.1167\/9.5.29","article-title":"Post-saccadic location judgments reveal remapping of saccade targets to non-foveal locations","volume":"9","author":"Collins","year":"2009","journal-title":"Journal of Vision"},{"key":"10.1016\/j.neunet.2021.03.003_b15","series-title":"Review of visual saliency detection with comprehensive information","author":"Cong","year":"2018"},{"key":"10.1016\/j.neunet.2021.03.003_b16","series-title":"Mnistvqa","author":"Cudic","year":"2016"},{"key":"10.1016\/j.neunet.2021.03.003_b17","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.neucom.2018.02.065","article-title":"A flexible testing environment for visual question and answering with performance evaluation","volume":"291","author":"Cudic","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2021.03.003_b18","doi-asserted-by":"crossref","unstructured":"Cudic, M., & Principe, J. (2019). Using a Recurrent Kernel Learning Machine for Small-Sample Image Classification. In IEEE Proc. IEEE IJCNN 2019, Budapest.","DOI":"10.1109\/IJCNN.2019.8852004"},{"key":"10.1016\/j.neunet.2021.03.003_b19","series-title":"IEEE computer vision and pattern recognition","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2021.03.003_b20","series-title":"Emergent properties of foveated perceptual systems","author":"Deza","year":"2020"},{"issue":"8\u20139","key":"10.1016\/j.neunet.2021.03.003_b21","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1016\/j.visres.2005.08.032","article-title":"Differences of monkey and human overt attention under natural conditions","volume":"46","author":"Einhauser","year":"2006","journal-title":"Vision Research"},{"key":"10.1016\/j.neunet.2021.03.003_b22","series-title":"Visualizing higher-layer features of a deep network (Vol. 1341)","first-page":"3","author":"Erhan","year":"2009"},{"issue":"1","key":"10.1016\/j.neunet.2021.03.003_b23","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1167\/19.1.12","article-title":"Temporal attention improves perception similarly at foveal and parafoveal locations","volume":"19","author":"Fern\u00e1ndez","year":"2019","journal-title":"Journal of Vision"},{"key":"10.1016\/j.neunet.2021.03.003_b24","series-title":"Pattern recognition","first-page":"117","article-title":"Goal-directed search with a top-down modulated computational attention system","author":"Frintrop","year":"2005"},{"key":"10.1016\/j.neunet.2021.03.003_b25","series-title":"Computer analysis of images and patterns","first-page":"261","article-title":"Saliency based on decorrelation and distinctiveness of local responses","author":"Garcia-Diaz","year":"2009"},{"key":"10.1016\/j.neunet.2021.03.003_b26","series-title":"Proceedings of the 2002 symposium on eye tracking research & applications","first-page":"83","article-title":"Real-time simulation of arbitrary visual fields","author":"Geisler","year":"2002"},{"issue":"9","key":"10.1016\/j.neunet.2021.03.003_b27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1167\/6.9.1","article-title":"Visual search: The role of peripheral information measured using gaze contingent displays","volume":"6","author":"Geisler","year":"2006","journal-title":"Journal of Vision"},{"key":"10.1016\/j.neunet.2021.03.003_b28","series-title":"Explaining explanations: An overview of interpretability of machine learning","author":"Gilpin","year":"2019"},{"key":"10.1016\/j.neunet.2021.03.003_b29","series-title":"IEEE computer vision and pattern recognition","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"issue":"10","key":"10.1016\/j.neunet.2021.03.003_b30","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1109\/TPAMI.2011.272","article-title":"Context-aware saliency detection","volume":"34","author":"Goferman","year":"2012","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10.1016\/j.neunet.2021.03.003_b31","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/0166-2236(92)90344-8","article-title":"Separate visual pathways for perception and action","volume":"15","author":"Goodale","year":"1992","journal-title":"Trends in Neuroscience"},{"key":"10.1016\/j.neunet.2021.03.003_b32","series-title":"Multi-digit number recognition from street view imagery using deep convolutional neural networks","author":"Goodfellow","year":"2013"},{"key":"10.1016\/j.neunet.2021.03.003_b33","doi-asserted-by":"crossref","unstructured":"Goroshin, R., Bruna, J., Tompson, J., Eigen, D., & LeCun, Y. (2015). Unsupervised learning of spatiotemporally coherent metrics. In Proceedings of the IEEE international conference on computer vision (pp. 4086\u20134093).","DOI":"10.1109\/ICCV.2015.465"},{"key":"10.1016\/j.neunet.2021.03.003_b34","series-title":"IEEE computer vision and pattern recognition (CVPR)","first-page":"1030","article-title":"Recognition using regions","author":"Gu","year":"2009"},{"issue":"#10","key":"10.1016\/j.neunet.2021.03.003_b35","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.1109\/LSP.2015.2413944","article-title":"Visual saliency detection with free energy theory","volume":"2","author":"Gu","year":"2015","journal-title":"IEEE Signal Processing Letters"},{"issue":"1","key":"10.1016\/j.neunet.2021.03.003_b36","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TIP.2009.2030969","article-title":"A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression","volume":"19","author":"Guo","year":"2010","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2021.03.003_b37","article-title":"Graph-based visual saliency","author":"Harel","year":"2007","journal-title":"Proceedings NIPS"},{"key":"10.1016\/j.neunet.2021.03.003_b38","doi-asserted-by":"crossref","unstructured":"Hasanbelliu, E., & Principe, J. (2008). Content addressable memories in reproducing kernel Hilbert spaces. In Proc. IEEE Workshop on machine learning for signal processing.","DOI":"10.1109\/MLSP.2008.4685447"},{"key":"10.1016\/j.neunet.2021.03.003_b39","series-title":"Deep residual learning for image recognition","author":"He","year":"2015"},{"key":"10.1016\/j.neunet.2021.03.003_b40","series-title":"IEEE computer vision and pattern recognition","first-page":"1","article-title":"Saliency detection: A spectral residual approach","author":"Hou","year":"2007"},{"issue":"10","key":"10.1016\/j.neunet.2021.03.003_b41","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1109\/TIP.2004.834657","article-title":"Automatic foveation for video compression using a neurobiological model of visual attention","volume":"13","author":"Itti","year":"2004","journal-title":"IEEE Transactions on Image Processing"},{"issue":"11","key":"10.1016\/j.neunet.2021.03.003_b42","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","article-title":"A model of saliency-based visual attention for rapid scene analysis","author":"Itti","year":"1998","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2021.03.003_b43","first-page":"2017","article-title":"Spatial transformer networks","author":"Jaderberg","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2021.03.003_b44","series-title":"A benchmark of computational models of saliency to predict human fixations","author":"Judd","year":"2012"},{"issue":"6\u20137","key":"10.1016\/j.neunet.2021.03.003_b45","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1080\/13506280902771138","article-title":"Sun: Top-down saliency using natural statistics","volume":"17","author":"Kanan","year":"2009","journal-title":"Visual Cognition"},{"key":"10.1016\/j.neunet.2021.03.003_b46","series-title":"DeepFovea: Neural reconstruction for foveated rendering and video compression using learned statistics of natural videos","author":"Kaplanyan A.\u00a0Sochenv","year":"2019"},{"key":"10.1016\/j.neunet.2021.03.003_b47","series-title":"Aerospace\/defense sensing and controls","first-page":"432","article-title":"New cfar stencil for target detections in synthetic aperture radar imagery","author":"Kim","year":"1996"},{"issue":"9","key":"10.1016\/j.neunet.2021.03.003_b48","doi-asserted-by":"crossref","first-page":"4446","DOI":"10.1109\/TIP.2017.2710620","article-title":"Deepfix: A fully convolutional neural network for predicting human eye fixations","volume":"26","author":"Kruthiventi","year":"2017","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"10.1016\/j.neunet.2021.03.003_b49","doi-asserted-by":"crossref","first-page":"251","DOI":"10.3758\/s13428-012-0226-9","article-title":"Methods for comparing scan paths and saliency maps: strengths and weaknesses","volume":"45","author":"Le\u00a0Meur","year":"2013","journal-title":"Behavior Research Methods"},{"issue":"Pt 1","key":"10.1016\/j.neunet.2021.03.003_b50","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1113\/jphysiol.2010.192658","article-title":"Visual pathways and psychophysical channels in the primate","volume":"589","author":"Lee","year":"2011","journal-title":"Journal of Physiology"},{"key":"10.1016\/j.neunet.2021.03.003_b51","series-title":"Proceedings of the 26th annual international conference on machine learning","first-page":"609","article-title":"Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations","author":"Lee","year":"2009"},{"key":"10.1016\/j.neunet.2021.03.003_b52","unstructured":"Li, J., Levine, M. D., An, X., & He, H. (0000). Saliency detection based on frequency and spatial domain analysis. In BMVC 2011."},{"key":"10.1016\/j.neunet.2021.03.003_b53","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.neucom.2020.10.083","article-title":"Attention-aware concentrated network for saliency prediction","volume":"429","author":"Li","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2021.03.003_b54","series-title":"IEEE image processing (ICIP)","first-page":"3093","article-title":"Incremental sparse saliency detection","author":"Li","year":"2009"},{"key":"10.1016\/j.neunet.2021.03.003_b55","doi-asserted-by":"crossref","DOI":"10.1037\/xhp0000202","article-title":"Worth a quick look? Initial scene previews can guide eye movements as a function of domain-specific expertise but can also have unforeseen costs","author":"Litchfield","year":"2016","journal-title":"Journal of Experimental Psychology, Human Perception and Performance"},{"key":"10.1016\/j.neunet.2021.03.003_b56","series-title":"Digital light field photography","author":"Ng","year":"2006"},{"issue":"01","key":"10.1016\/j.neunet.2021.03.003_b57","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1017\/S0140525X0200002X","article-title":"Two visual systems and two theories of perception: An attempt to reconcile the constructivist and ecological approaches","volume":"25","author":"Norman","year":"2002","journal-title":"Behavioral and Brain Sciences"},{"key":"10.1016\/j.neunet.2021.03.003_b58","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1023\/A:1011139631724","article-title":"Modeling the shape of the scene: A holistic representation of the spatial envelope","volume":"42","author":"Oliva","year":"2001","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2021.03.003_b59","unstructured":"Ozimek, P., Balog, L., Wong, R., Esparon, T., & Siebert, J. (2017). Egocentric Perception using a Biologically Inspired Software Retina Integrated with a Deep CNN. In ICCV 2017 workshop on egocentric perception, interaction and computing."},{"issue":"18","key":"10.1016\/j.neunet.2021.03.003_b60","doi-asserted-by":"crossref","first-page":"2397","DOI":"10.1016\/j.visres.2005.03.019","article-title":"Components of bottom-up gaze allocation in natural images","volume":"45","author":"Peters","year":"2005","journal-title":"Vision Research"},{"issue":"1A","key":"10.1016\/j.neunet.2021.03.003_b61","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/0028-3932(87)90049-2","article-title":"How do the parietal lobes direct covert attention?","volume":"25","author":"Posner","year":"1987","journal-title":"Neuropsychologia"},{"issue":"4","key":"10.1016\/j.neunet.2021.03.003_b62","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/JPROC.2014.2307023","article-title":"Cognitive architectures for sensory processing","volume":"102","author":"Principe","year":"2014","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2021.03.003_b63","doi-asserted-by":"crossref","unstructured":"Riche, N., Mancas, M., Gosselin, B., & Dutoit, T. (2012). Rare: A new bottom-up saliency model. In IEEE Int. conf. image proc. Orlando FL.","DOI":"10.1109\/ICIP.2012.6466941"},{"issue":"11","key":"10.1016\/j.neunet.2021.03.003_b64","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1038\/14819","article-title":"Hierarchical models of object recognition in cortex","volume":"2","author":"Riesenhuber","year":"1999","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.neunet.2021.03.003_b65","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1146\/annurev.neuro.29.051605.112939","article-title":"Cortical algorithms for perceptual grouping","volume":"29","author":"Roelfsema","year":"2006","journal-title":"Annual Review of Neuroscience"},{"key":"10.1016\/j.neunet.2021.03.003_b66","series-title":"Exploiting spatio-temporal structure with recurrent winner-take- all networks","author":"Santana","year":"2016"},{"key":"10.1016\/j.neunet.2021.03.003_b67","series-title":"International conference on multimodal interfaces","first-page":"6","article-title":"Focusing computational visual attention in multi-modal human\u2013robot interaction","author":"Schauerte","year":"2010"},{"key":"10.1016\/j.neunet.2021.03.003_b68","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Networks"},{"issue":"1","key":"10.1016\/j.neunet.2021.03.003_b69","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.tins.2008.09.012","article-title":"Low-frequency neuronal oscillations as instruments of sensory selection","volume":"32","author":"Schroeder","year":"2009","journal-title":"Trends in Neuroscience"},{"key":"10.1016\/j.neunet.2021.03.003_b70","doi-asserted-by":"crossref","unstructured":"Seo, H. J., & Milanfar, P. (2009). Nonparametric bottom-up saliency detection by self-resemblance. In IEEE computer vision and pattern recognition workshops (pp. 45\u201352).","DOI":"10.1109\/CVPRW.2009.5204207"},{"key":"10.1016\/j.neunet.2021.03.003_b71","series-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"Sermanet","year":"2013"},{"key":"10.1016\/j.neunet.2021.03.003_b72","series-title":"Image analysis","first-page":"666","article-title":"Fast and efficient saliency detection using sparse sampling and kernel density estimation","author":"Tavakoli","year":"2011"},{"key":"10.1016\/j.neunet.2021.03.003_b73","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/S0959-4388(98)80143-8","article-title":"Perceiving visually presented objects: Recognition, awareness, and modularity","volume":"8","author":"Treisman","year":"1998","journal-title":"Current Opinion in Neurobioloy"},{"issue":"9","key":"10.1016\/j.neunet.2021.03.003_b74","doi-asserted-by":"crossref","first-page":"3114","DOI":"10.1016\/j.patcog.2012.02.009","article-title":"A saliency map based on sampling an image into random rectangular regions of interest","volume":"45","author":"Vikram","year":"2012","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2021.03.003_b75","series-title":"Proceedings of the 25th international conference on machine learning","first-page":"1096","article-title":"Extracting and composing robust features with denoising autoencoders","author":"Vincent","year":"2008"},{"key":"10.1016\/j.neunet.2021.03.003_b76","unstructured":"Von\u00a0Helmholtz, H. (1867). Handbuch der physiologischen Optik: Mit 213 in den Text eingedruckten Holzschnitten und 11 Tafeln. Voss."},{"issue":"3","key":"10.1016\/j.neunet.2021.03.003_b77","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1109\/29.21701","article-title":"Phoneme recognition using time-delay neural networks","volume":"37","author":"Waibel","year":"1989","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"issue":"9","key":"10.1016\/j.neunet.2021.03.003_b78","doi-asserted-by":"crossref","first-page":"1395","DOI":"10.1016\/j.neunet.2006.10.001","article-title":"Modeling attention to salient proto objects","volume":"19","author":"Walther","year":"2006","journal-title":"Neural Networks"},{"issue":"1","key":"10.1016\/j.neunet.2021.03.003_b79","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.cviu.2004.09.004","article-title":"Selective visual attention enables learning and recognition of multiple objects in cluttered scenes","volume":"100","author":"Walther","year":"2005","journal-title":"Computer Vision and Image Understanding"},{"key":"10.1016\/j.neunet.2021.03.003_b80","doi-asserted-by":"crossref","unstructured":"Wang, X., & Gupta, A. (2015). Unsupervised learning of visual representations using videos. In Proceedings of the IEEE international conference on computer vision (pp. 2794\u20132802).","DOI":"10.1109\/ICCV.2015.320"},{"issue":"13","key":"10.1016\/j.neunet.2021.03.003_b81","doi-asserted-by":"crossref","first-page":"4386","DOI":"10.1523\/JNEUROSCI.6063-11.2012","article-title":"Network analysis of corticocortical connections reveals ventral and dorsal processing streams in mouse visual cortex","volume":"32","author":"Wang","year":"2012","journal-title":"Journal of Neuroscience"},{"issue":"3","key":"10.1016\/j.neunet.2021.03.003_b82","doi-asserted-by":"crossref","first-page":"0058","DOI":"10.1038\/s41562-017-0058","article-title":"Five factors that guide attention in visual search","volume":"1","author":"Wolfe","year":"2017","journal-title":"Nature Human Behaviour"},{"key":"10.1016\/j.neunet.2021.03.003_b83","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., & So\u00a0Kweon, I. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (pp. 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10.1016\/j.neunet.2021.03.003_b84","series-title":"Eye movements in vision","author":"Yarbus","year":"1967"},{"issue":"1","key":"10.1016\/j.neunet.2021.03.003_b85","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/TCYB.2015.2501373","article-title":"Coupled deep autoencoder for single image super-resolution","volume":"47","author":"Zeng","year":"2017","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.neunet.2021.03.003_b86","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wang, T., Qi, J., Lu, H., & Wang, G. (2018). Progressive attention guided recurrent network for salient object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 714\u2013722).","DOI":"10.1109\/CVPR.2018.00081"},{"key":"10.1016\/j.neunet.2021.03.003_b87","series-title":"Stacked what-where auto-encoders","author":"Zhao","year":"2016"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0893608021000836?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0893608021000836?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:46:22Z","timestamp":1760233582000},"score":1,"resource":{"primary":{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608021000836"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":87,"alternative-id":["S0893608021000836"],"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1016\/j.neunet.2021.03.003","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2021,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Unsupervised foveal vision neural architecture with top-down attention","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1016\/j.neunet.2021.03.003","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}