{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:08:40Z","timestamp":1753891720047,"version":"3.41.2"},"reference-count":57,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T00:00:00Z","timestamp":1668729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:p>We propose a brain inspired attentional search model for target search in a 3D environment, which has two separate channels\u2014one for the object classification, analogous to the \u201cwhat\u201d pathway in the human visual system, and the other for prediction of the next location of the camera, analogous to the \u201cwhere\u201d pathway. To evaluate the proposed model, we generated 3D Cluttered Cube datasets that consist of an image on one vertical face, and clutter or background images on the other faces. The camera goes around each cube on a circular orbit and determines the identity of the image pasted on the face. The images pasted on the cube faces were drawn from: MNIST handwriting digit, QuickDraw, and RGB MNIST handwriting digit datasets. The attentional input of three concentric cropped windows resembling the high-resolution central fovea and low-resolution periphery of the retina, flows through a Classifier Network and a Camera Motion Network. The Classifier Network classifies the current view into one of the target classes or the clutter. The Camera Motion Network predicts the camera's next position on the orbit (varying the azimuthal angle or \u201c\u03b8\u201d). Here the camera performs one of three actions: move right, move left, or do not move. The Camera-Position Network adds the camera's current position (\u03b8) into the higher features level of the Classifier Network and the Camera Motion Network. The Camera Motion Network is trained using Q-learning where the reward is 1 if the classifier network gives the correct classification, otherwise 0. Total loss is computed by adding the mean square loss of temporal difference and cross entropy loss. Then the model is trained end-to-end by backpropagating the total loss using Adam optimizer. Results on two grayscale image datasets and one RGB image dataset show that the proposed model is successfully able to discover the desired search pattern to find the target face on the cube, and also classify the target face accurately.<\/jats:p>","DOI":"10.3389\/fncom.2022.1012559","type":"journal-article","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T11:28:46Z","timestamp":1668770926000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["BIAS-3D: Brain inspired attentional search model fashioned after what and where\/how pathways for target search in 3D environment"],"prefix":"10.3389","volume":"16","author":[{"given":"Sweta","family":"Kumari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V. Y.","family":"Shobha Amala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Nivethithan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V. Srinivasa","family":"Chakravarthy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"6771","DOI":"10.1007\/s13369-017-2873-8","article-title":"Action-selection method for reinforcement learning based on cuckoo search algorithm","volume":"43","author":"Abed-alguni","year":"2018","journal-title":"Arab. J. Sci. Eng"},{"key":"B2","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1002\/cne.21060","article-title":"Contribution of feedforward thalamic afferents and corticogeniculate feedback to the spatial summation area of macaque V1 AND LGN","volume":"498","author":"Angelucci","year":"2006","journal-title":"J. Compar. Neurol"},{"journal-title":"Reward Management: A Handbook of Remuneration Strategy and Practice","year":"2007","author":"Armstrong","key":"B3"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.7755","article-title":"Multiple object recognition with visual attention","author":"Ba","year":"2014","journal-title":"arXiv preprint arXiv:1412.7755"},{"journal-title":"Gradient Flow in Recurrent Nets: The Difficulty of Learning Long-Term Dependencies","year":"2001","author":"Bengio","key":"B5"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5244\/C.25.85","article-title":"\u201cComputational modeling of top-down visual attention in interactive environments,\u201d","author":"Borji","year":"2011","journal-title":"BMVC, Vol. 85"},{"key":"B7","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1109\/CVPR.2012.6247710","article-title":"\u201cProbabilistic learning of task-specific visual attention,\u201d","author":"Borji","year":"2012","journal-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B8","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1007\/s00221-006-0666-5","article-title":"Later predicts saccade latency distributions in reading","volume":"177","author":"Carpenter","year":"2007","journal-title":"Exp. Brain Res"},{"key":"B9","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1038\/nn0708-851c","article-title":"Correction: Corrigendum: decision-making with multiple alternatives","volume":"11","author":"Churchland","year":"2008","journal-title":"Nat. Neurosci"},{"key":"B10","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/BF00114844","article-title":"Distributed representations, simple recurrent networks, and grammatical structure","volume":"7","author":"Elman","year":"1991","journal-title":"Mach. Learn"},{"key":"B11","first-page":"486","article-title":"\u201cA theoretical analysis of deep q-learning,\u201d","author":"Fan","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"B12","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1109\/TPAMI.2009.27","article-title":"Discriminant saliency, the detection of suspicious coincidences, and applications to visual recognition","volume":"31","author":"Gao","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B13","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1167\/8.7.13","article-title":"On the plausibility of the discriminant center-surround hypothesis for visual saliency","volume":"8","author":"Gao","year":"2008","journal-title":"J. Vis"},{"key":"B14","first-page":"481","article-title":"Discriminant saliency for visual recognition from cluttered scenes","volume":"17","author":"Gao","year":"2004","journal-title":"Adv. Neural Inform. Process. Syst"},{"key":"B15","first-page":"249","article-title":"\u201cUnderstanding the difficulty of training deep feedforward neural networks,\u201d","author":"Glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"journal-title":"Deep Learning, Vol. 1","year":"2016","author":"Goodfellow","key":"B16"},{"key":"B17","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s10827-005-5705-x","article-title":"Dopamine modulation in the basal ganglia locks the gate to working memory","volume":"20","author":"Gruber","year":"2006","journal-title":"J. Comput. Neurosci"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1109\/CVPR.2016.138","article-title":"\u201cRecurrent attention models for depth-based person identification,\u201d","author":"Haque","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B19","doi-asserted-by":"publisher","first-page":"2767","DOI":"10.1109\/IJCNN.2016.7727548","article-title":"\u201cDecision making with long delays using networks of flip-flop neurons,\u201d","author":"Holla","year":"2016","journal-title":"2016 International Joint Conference on Neural Networks (IJCNN)"},{"key":"B20","unstructured":"JongejanJ.\n            RowleyH.\n            KawashimaT.\n            KimJ.\n            Fox-GiegN.\n          The Quick, Draw!-AI Experiment2016"},{"journal-title":"Serial Order: A Parallel Distributed Processing Approach","year":"1986","author":"Jordan","key":"B21"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1613","DOI":"10.1109\/CVPRW.2017.206","article-title":"\u201cRATM: recurrent attentive tracking model,\u201d","author":"Kahou","year":"2017","journal-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"B23","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1080\/13506280902771138","article-title":"Sun: top-down saliency using natural statistics","volume":"17","author":"Kanan","year":"2009","journal-title":"Vis. Cogn"},{"key":"B24","doi-asserted-by":"publisher","first-page":"5010","DOI":"10.1109\/CVPR.2018.00526","article-title":"\u201cRotationnet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints,\u201d","author":"Kanezaki","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1001\/archopht.1938.00850240232021","article-title":"An introduction to clinical perimetry","volume":"20","author":"Knapp","year":"1938","journal-title":"Arch. Ophthalmol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3390\/risks8020040","article-title":"Deep arbitrage-free learning in a generalized HJM framework via arbitrage-regularization","volume":"8","author":"Kratsios","year":"2020","journal-title":"Risks"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inform. Process. Syst"},{"key":"B29","doi-asserted-by":"publisher","first-page":"10397","DOI":"10.1109\/CVPR42600.2020.01041","article-title":"\u201cSaccadeNet: a fast and accurate object detector,\u201d","author":"Lan","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B30","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1109\/TPAMI.2006.86","article-title":"A coherent computational approach to model bottom-up visual attention","volume":"28","author":"Le Meur","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B31","unstructured":"LeCunY.\n            CortesC.\n            BurgesC. J. C.\n          The MNIST Database of Handwritten Digits (New York, NY)1998"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3104651","article-title":"Enhanced attention tracking with multi-branch network for egocentric activity recognition","author":"Liu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2022.3202835","article-title":"Holistic-guided disentangled learning with cross-video semantics mining for concurrent first-person and third-person activity recognition","volume":"32","author":"Liu","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B34","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1145\/375735.376414","article-title":"\u201cA reinforcement learning model of selective visual attention,\u201d","author":"Minut","year":"2001","journal-title":"Proceedings of the fifth international conference on Autonomous agents"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.6247","article-title":"Recurrent models of visual attention","author":"Mnih","year":"2014","journal-title":"arXiv preprint arXiv:1406.6247"},{"key":"B36","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","volume":"10","author":"Nair","year":"2010","journal-title":"Icml"},{"key":"B37","doi-asserted-by":"publisher","first-page":"9475","DOI":"10.1523\/JNEUROSCI.22-21-09475.2002","article-title":"Response of neurons in the lateral intraparietal area during a combined visual discrimination reaction time task","volume":"22","author":"Roitman","year":"2002","journal-title":"J. Neurosci"},{"journal-title":"Fundamentals of Logic Design","year":"2020","author":"Roth","key":"B38"},{"key":"B39","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1016\/j.neuroimage.2010.02.045","article-title":"Action selection: a race model for selected and non-selected actions distinguishes the contribution of premotor and prefrontal areas","volume":"51","author":"Rowe","year":"2010","journal-title":"Neuroimage"},{"key":"B40","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1080\/17588920903388950","article-title":"Do we have independent visual streams for perception and action?","volume":"1","author":"Schenk","year":"2010","journal-title":"Cogn Neurosci"},{"key":"B41","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-642-15825-4_10","article-title":"\u201cEvaluation of pooling operations in convolutional architectures for object recognition,\u201d","author":"Scherer","year":"2010","journal-title":"International Conference on Artificial Neural Networks"},{"journal-title":"The openGLr Graphics System: A Specification (Version 4.0 (Core Profile))","year":"2010","author":"Segal","key":"B42"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.1109\/ISBI.2019.8759214","article-title":"\u201cRecurrent attention mechanism networks for enhanced classification of biomedical images,\u201d","author":"Shaikh","year":"2019","journal-title":"2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1109\/TIP.2014.2302892","article-title":"Lazy random walks for superpixel segmentation","volume":"23","author":"Shen","year":"2014","journal-title":"IEEE Trans. Image Process"},{"key":"B45","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1109\/ICCV.2015.114","article-title":"\u201cMulti-view convolutional neural networks for 3D shape recognition,\u201d","author":"Su","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"journal-title":"Introduction to Reinforcement Learning, Vol. 135","year":"1998","author":"Sutton","key":"B46"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1101\/2021.11.16.468605","article-title":"The flip-flop neuron - a memory efficient alternative for solving challenging sequence processing and decision-making problems","author":"Sweta","year":"2021","journal-title":"BioRxiv"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.47760\/ijcsmc.2021.v10i01.001","article-title":"Unfolding the evolution of machine learning and its expediency","volume":"10","author":"Voleti","year":"2021","journal-title":"IJCSMC"},{"key":"B49","first-page":"3395","article-title":"\u201cSaliency-aware geodesic video object segmentation,\u201d","author":"Wang","year":"","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B50","doi-asserted-by":"publisher","first-page":"4185","DOI":"10.1109\/TIP.2015.2460013","article-title":"Consistent video saliency using local gradient flow optimization and global refinement","volume":"24","author":"Wang","year":"","journal-title":"IEEE Trans. Image Process"},{"key":"B51","first-page":"1912","article-title":"\u201c3D shapenets: a deep representation for volumetric shapes,\u201d","author":"Wu","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1109\/TMI.2019.2962013","article-title":"Attention by selection: A deep selective attention approach to breast cancer classification","volume":"39","author":"Xu","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B53","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1109\/TMM.2016.2626959","article-title":"Discriminative multi-instance multitask learning for 3d action recognition","volume":"19","author":"Yang","year":"","journal-title":"IEEE Trans. Multim"},{"key":"B54","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1109\/TCYB.2016.2519448","article-title":"Latent max-margin multitask learning with skelets for 3-D action recognition","volume":"47","author":"Yang","year":"","journal-title":"IEEE Trans. Cybern"},{"key":"B55","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.sigpro.2015.10.035","article-title":"Multi-task human action recognition via exploring super-category","volume":"124","author":"Yang","year":"","journal-title":"Signal Process"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.1109\/TIP.2017.2658957","article-title":"Revealing event saliency in unconstrained video collection","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process"},{"key":"B57","doi-asserted-by":"publisher","first-page":"4623","DOI":"10.1109\/TIP.2015.2465159","article-title":"Shadow remover: image shadow removal based on illumination recovering optimization","volume":"24","author":"Zhang","year":"2015","journal-title":"IEEE Trans. Image Process"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2022.1012559\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T11:29:03Z","timestamp":1668770943000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2022.1012559\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,18]]},"references-count":57,"alternative-id":["10.3389\/fncom.2022.1012559"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2022.1012559","relation":{},"ISSN":["1662-5188"],"issn-type":[{"type":"electronic","value":"1662-5188"}],"subject":[],"published":{"date-parts":[[2022,11,18]]},"article-number":"1012559"}}