{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1390004222630188416.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1587/transinf.2019edp7284"}},{"identifier":{"@type":"URI","@value":"https://www.jstage.jst.go.jp/article/transinf/E103.D/10/E103.D_2019EDP7284/_pdf"}},{"identifier":{"@type":"NAID","@value":"130007920638"}}],"dc:title":[{"@language":"en","@value":"Efficient Salient Object Detection Model with Dilated Convolutional Networks"}],"dc:language":"en","description":[{"type":"abstract","notation":[{"@language":"en","@value":"<p>Introduction of Fully Convolutional Networks (FCNs) has made record progress in salient object detection models. However, in order to retain the input resolutions, deconvolutional networks with unpooling are applied on top of FCNs. This will cause the increase of the computation and network model size in segmentation task. In addition, most deep learning based methods always discard effective saliency prior knowledge completely, which are shown effective. Therefore, an efficient salient object detection method based on deep learning is proposed in our work. In this model, dilated convolutions are exploited in the networks to produce the output with high resolution without pooling and adding deconvolutional networks. In this way, the parameters and depth of the network are decreased sharply compared with the traditional FCNs. Furthermore, manifold ranking model is explored for the saliency refinement to keep the spatial consistency and contour preserving. Experimental results verify that performance of our method is superior with other state-of-art methods. Meanwhile, the proposed model occupies the less model size and fastest processing speed, which is more suitable for the wearable processing systems.</p>"}],"abstractLicenseFlag":"disallow"}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1410004222630188419","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000410316745"}],"foaf:name":[{"@language":"en","@value":"GUO Fei"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Faculty of Automation and Information Engineering, Xi'an University of Technology"}]},{"@id":"https://cir.nii.ac.jp/crid/1410004222630188417","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000410316746"}],"foaf:name":[{"@language":"en","@value":"YANG Yuan"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Faculty of Automation and Information Engineering, Xi'an University of Technology"}]},{"@id":"https://cir.nii.ac.jp/crid/1410004222630188418","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000410316747"}],"foaf:name":[{"@language":"en","@value":"GAO Yong"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Faculty of Automation and Information Engineering, Xi'an University of Technology"}]},{"@id":"https://cir.nii.ac.jp/crid/1410004222630188416","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000410316748"}],"foaf:name":[{"@language":"en","@value":"YU Ningmei"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Faculty of Automation and Information Engineering, Xi'an University of Technology"}]}],"publication":{"publicationIdentifier":[{"@type":"PISSN","@value":"09168532"},{"@type":"EISSN","@value":"17451361"}],"prism:publicationName":[{"@language":"en","@value":"IEICE Transactions on Information and Systems"},{"@language":"en","@value":"IEICE Trans. Inf. & Syst."}],"dc:publisher":[{"@language":"en","@value":"The Institute of Electronics, Information and Communication Engineers"},{"@language":"ja","@value":"一般社団法人 電子情報通信学会"}],"prism:publicationDate":"2020-10-01","prism:volume":"E103.D","prism:number":"10","prism:startingPage":"2199","prism:endingPage":"2207"},"reviewed":"false","url":[{"@id":"https://www.jstage.jst.go.jp/article/transinf/E103.D/10/E103.D_2019EDP7284/_pdf"}],"availableAt":"2020-10-01","foaf:topic":[{"@id":"https://cir.nii.ac.jp/all?q=saliency%20detection%20model","dc:title":"saliency detection model"},{"@id":"https://cir.nii.ac.jp/all?q=deep%20learning","dc:title":"deep learning"},{"@id":"https://cir.nii.ac.jp/all?q=dilated%20convolution","dc:title":"dilated convolution"}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360001114028088960","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Frequency-tuned salient region detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1360011143521467136","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Salient Object Detection: A Discriminative Regional Feature Integration Approach"}]},{"@id":"https://cir.nii.ac.jp/crid/1360282588959366272","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Learning to Detect a Salient Object"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292618721594624","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Non-local Neural Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292621603471104","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Non-local Deep Features for Salient Object Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574092888230656","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Learning Deconvolution Network for Semantic Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574095832637056","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The Panacousticon: by way of echo to Freddie Rokem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574096549798528","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Modeling the role of salience in the allocation of overt visual attention"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855569555180416","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Saliency filters: Contrast based filtering for salient region detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855570129941504","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"3-D Object Retrieval and Recognition With Hypergraph Analysis"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855570649372032","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Conditional Random Fields as Recurrent Neural Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855571378827904","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Contextual Hypergraph Modeling for Salient Object Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137044303895296","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137045434547584","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Saliency Detection via Graph-Based Manifold Ranking"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137046155806976","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The Secrets of Salient Object Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418520419817856","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Saliency Detection via Absorbing Markov Chain"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699994191580160","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Visual Tracking with Fully Convolutional Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699995019173760","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Hierarchical Saliency Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699996454219648","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Adaptive object tracking by learning background context"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981468492966912","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Geodesic Saliency Using Background Priors"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981469868865024","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981470260964992","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Computational modelling of visual attention"}]},{"@id":"https://cir.nii.ac.jp/crid/1362262944290464640","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep Contrast Learning for Salient Object Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1362262944832130432","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Center-surround divergence of feature statistics for salient object detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544419168643456","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Submodular Salient Region Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544419457695232","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A model of saliency-based visual attention for rapid scene analysis"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544420634667648","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Efficient Salient Region Detection with Soft Image Abstraction"}]},{"@id":"https://cir.nii.ac.jp/crid/1362825893371560192","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deeply Supervised Salient Object Detection with Short Connections"}]},{"@id":"https://cir.nii.ac.jp/crid/1362825895163346688","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107368816625280","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Intelligent Visual Media Processing: When Graphics Meets Vision"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107370446852480","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Saliency Detection via Dense and Sparse Reconstruction"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107371054744576","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Fully convolutional networks for semantic segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388844205415936","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Saliency driven total variation segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670318832590976","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Salient Object Detection with Recurrent Fully Convolutional Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670319538967296","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"STCT: Sequentially Training Convolutional Networks for Visual Tracking"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670320433810816","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670320627490304","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep networks for saliency detection via local estimation and global search"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951793409242624","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"What Makes a Patch Distinct?"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951793989400576","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951795808619264","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Dilated Residual Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951795944946816","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Global Contrast Based Salient Region Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233268363105536","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep Saliency with Encoded Low Level Distance Map and High Level Features"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233268402049280","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233268670584192","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"SLIC Superpixels Compared to State-of-the-Art Superpixel Methods"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233270815523072","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Automatic salient object segmentation based on context and shape prior"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233270940834816","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Image saliency by isocentric curvedness and color"}]},{"@id":"https://cir.nii.ac.jp/crid/1390011461952587648","@type":"Article","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@language":"en","@value":"BFF R-CNN: Balanced Feature Fusion for Object Detection"}]}],"dataSourceIdentifier":[{"@type":"JALC","@value":"oai:japanlinkcenter.org:2008066117"},{"@type":"CROSSREF","@value":"10.1587/transinf.2019edp7284"},{"@type":"CIA","@value":"130007920638"},{"@type":"CROSSREF","@value":"10.1587/transinf.2021edp7261_references_DOI_Pbx7UFnJpOTlpiEY7ebkUOtdbXo"}]}