{"@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/1390845713080148864.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1587/transinf.2018cep0001"}},{"identifier":{"@type":"URI","@value":"https://www.jstage.jst.go.jp/article/transinf/E102.D/7/E102.D_2018CEP0001/_pdf"}},{"identifier":{"@type":"NAID","@value":"130007671323"}}],"resourceType":"学術雑誌論文(journal article)","dc:title":[{"@language":"en","@value":"Webly-Supervised Food Detection with Foodness Proposal"}],"dc:language":"en","description":[{"type":"abstract","notation":[{"@language":"en","@value":"<p>To minimize the annotation costs associated with training semantic segmentation models and object detection models, weakly supervised detection and weakly supervised segmentation approaches have been extensively studied. However most of these approaches assume that the domain between training and testing is the same, which at times results in considerable performance drops. For example, if we train an object detection network using only web images showing a large object at the center, it can be difficult for the network to detect multiple small objects. In this paper, we focus on training a CNN with only web images and achieve object detection in the wild. A proposal-based approach can address the problem associated with differences in domains because web images are similar to images of the proposal. In both domains, the target object is located at the center of the image and the ratio of the size of the target object to the size of the image is large. Several proposal methods have been proposed to detect regions with high “object-ness.” However, many of these proposals generate a large number of candidates to increase the recall rate. Considering the recent advent of deep CNNs, methods that generate a large number of proposals exhibit problems in terms of processing time for practical use. Therefore, we propose a CNN-based “food-ness” proposal method in this paper that requires neither pixel-wise annotation nor bounding box annotation. Our method generates proposals through backpropagation and most of these proposals focus only on food objects. In addition, we can easily control the number of proposals. Through experiments, we trained a network model using only web images and tested the model on the UEC FOOD 100 dataset. We demonstrate that the proposed method achieves high performance compared to traditional proposal methods in terms of the trade-off between accuracy and computational cost. Therefore, in this paper, we propose an intermediate approach between the traditional proposal approach and the fully convolutional approach. In particular, we propose a novel proposal method that generates high“food-ness” regions using fully convolutional networks based on the backward approach by training food images gathered from the web.</p>"}],"abstractLicenseFlag":"disallow"}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1410845713080148865","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000403158288"}],"foaf:name":[{"@language":"en","@value":"SHIMODA Wataru"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Department of Informatics, The University of Electro-Communications"}]},{"@id":"https://cir.nii.ac.jp/crid/1420001326229259776","@type":"Researcher","personIdentifier":[{"@type":"KAKEN_RESEARCHERS","@value":"20301179"},{"@type":"NRID","@value":"1000020301179"},{"@type":"CINII_AUTHOR_ID","@value":"DA19918691"},{"@type":"URI","@value":"https://ci.nii.ac.jp/author/DA19918691#entity"},{"@type":"URI","@value":"https://viaf.org/viaf/NII%7CDA19918691"},{"@type":"NRID","@value":"9000004836106"},{"@type":"NRID","@value":"9000297484638"},{"@type":"NRID","@value":"9000287153191"},{"@type":"NRID","@value":"9000397675910"},{"@type":"NRID","@value":"9000334734529"},{"@type":"NRID","@value":"9000402383649"},{"@type":"NRID","@value":"9000280560681"},{"@type":"NRID","@value":"9000375844801"},{"@type":"NRID","@value":"9000388995322"},{"@type":"NRID","@value":"9000404235944"},{"@type":"NRID","@value":"9000389547809"},{"@type":"NRID","@value":"9000402294837"},{"@type":"NRID","@value":"9000342440241"},{"@type":"NRID","@value":"9000404290355"},{"@type":"NRID","@value":"9000397674189"},{"@type":"NRID","@value":"9000397663630"},{"@type":"NRID","@value":"9000380485612"},{"@type":"NRID","@value":"9000368927824"},{"@type":"NRID","@value":"9000388992522"},{"@type":"NRID","@value":"9000356628181"},{"@type":"NRID","@value":"9000397662365"},{"@type":"NRID","@value":"9000388993069"},{"@type":"NRID","@value":"9000403023307"},{"@type":"NRID","@value":"9000368927892"},{"@type":"NRID","@value":"9000391395619"},{"@type":"NRID","@value":"9000397673872"},{"@type":"NRID","@value":"9000403158268"},{"@type":"NRID","@value":"9000403158289"},{"@type":"NRID","@value":"9000388996068"},{"@type":"NRID","@value":"9000356642749"},{"@type":"NRID","@value":"9000397670789"},{"@type":"NRID","@value":"9000375844829"},{"@type":"NRID","@value":"9000388996493"},{"@type":"NRID","@value":"9000404290335"},{"@type":"NRID","@value":"9000399579788"},{"@type":"NRID","@value":"9000261655024"},{"@type":"NRID","@value":"9000283106799"},{"@type":"NRID","@value":"9000253214496"},{"@type":"NRID","@value":"9000404290357"},{"@type":"NRID","@value":"9000397674746"},{"@type":"NRID","@value":"9000397678072"},{"@type":"NRID","@value":"9000368928674"},{"@type":"NRID","@value":"9000287153255"},{"@type":"NRID","@value":"9000397675069"},{"@type":"NRID","@value":"9000397651484"},{"@type":"NRID","@value":"9000345288118"},{"@type":"NRID","@value":"9000397666660"},{"@type":"NRID","@value":"9000368928610"},{"@type":"NRID","@value":"9000004808175"},{"@type":"NRID","@value":"9000287153194"},{"@type":"NRID","@value":"9000283623276"},{"@type":"NRID","@value":"9000388994994"},{"@type":"RESEARCHMAP","@value":"https://researchmap.jp/read0191078"}],"foaf:name":[{"@language":"en","@value":"YANAI Keiji"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Department of Informatics, The University of Electro-Communications"}]}],"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":"2019-07-01","prism:volume":"E102.D","prism:number":"7","prism:startingPage":"1230","prism:endingPage":"1239"},"reviewed":"false","dcterms:accessRights":"http://purl.org/coar/access_right/c_abf2","url":[{"@id":"https://www.jstage.jst.go.jp/article/transinf/E102.D/7/E102.D_2018CEP0001/_pdf"}],"availableAt":"2019-07-01","foaf:topic":[{"@id":"https://cir.nii.ac.jp/all?q=food%20segmentation","dc:title":"food segmentation"},{"@id":"https://cir.nii.ac.jp/all?q=convolutional%20neural%20network","dc:title":"convolutional neural network"},{"@id":"https://cir.nii.ac.jp/all?q=deep%20learning","dc:title":"deep learning"},{"@id":"https://cir.nii.ac.jp/all?q=UEC-FOOD100","dc:title":"UEC-FOOD100"}],"project":[{"@id":"https://cir.nii.ac.jp/crid/1040000781959264256","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"17H06100"},{"@type":"JGN","@value":"JP17H06100"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-17H06100/"}],"notation":[{"@language":"ja","@value":"機械可読時代における文字科学の創成と応用展開"},{"@language":"en","@value":"From Text Engineering to Text Science"}]},{"@id":"https://cir.nii.ac.jp/crid/1040000781961743872","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"17J10261"},{"@type":"JGN","@value":"JP17J10261"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-17J10261/"}],"notation":[{"@language":"ja","@value":"深層学習を用いた弱教師あり学習による画像に対する物体位置推定"}]},{"@id":"https://cir.nii.ac.jp/crid/1040282256931462400","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"17H01745"},{"@type":"JGN","@value":"JP17H01745"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-17H01745/"}],"notation":[{"@language":"ja","@value":"自動食事診断実現のための深層学習とWeb知識を用いた食事写真カロリー量推定"},{"@language":"en","@value":"Automatic Food Calorie Estimation from Photos Employing Deep Learning and Food-related Knowledge on the Web"}]},{"@id":"https://cir.nii.ac.jp/crid/1040282256935854976","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"17H05972"},{"@type":"JGN","@value":"JP17H05972"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PUBLICLY-17H05972/"}],"notation":[{"@language":"ja","@value":"低消費電力リアルタイム画像認識実現のためのモバイル深層学習技術"},{"@language":"en","@value":"Deep Learning for Mobile Devices which Recognize Images in A Real-Time Way with Low Power Consumption"}]},{"@id":"https://cir.nii.ac.jp/crid/1040282256935897344","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"17H06026"},{"@type":"JGN","@value":"JP17H06026"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PUBLICLY-17H06026/"}],"notation":[{"@language":"ja","@value":"単機能の重ね合せにより新機能を創発するマルチファンクショナル深層学習ネットワーク"},{"@language":"en","@value":"Multi-functional CNN by Piping up Single Functions for Emergence of New Functions"}]},{"@id":"https://cir.nii.ac.jp/crid/1040282256992040064","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"19H04929"},{"@type":"JGN","@value":"JP19H04929"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PUBLICLY-19H04929/"}],"notation":[{"@language":"ja","@value":"モバイル深層学習技術を活用した動物ロギングのためのリアルタイム行動認識"},{"@language":"en","@value":"Real-time activity recognition for animal logging based on mobile deep learning techniques"}]}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360011144005116032","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Measuring Calorie and Nutrition From Food Image"}]},{"@id":"https://cir.nii.ac.jp/crid/1360285705545340416","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1360285706385335168","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"FoodCam: A real-time food recognition system on a smartphone"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292619642964352","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Combining global and local features for food identification in dietary assessment"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292620728038272","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Weakly Supervised Cascaded Convolutional Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574094340921600","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Real-Time Mobile Food Recognition System"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574094450350592","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"DietCam: Automatic dietary assessment with mobile camera phones"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855567865740544","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep Residual Learning for Image Recognition"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855568933465088","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Food image recognition with deep convolutional features"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855570070213120","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137045698371456","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Weakly Supervised Deep Detection Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137046108759808","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Webly Supervised Learning of Convolutional Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418519961274112","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Automatic Chinese food identification and quantity estimation"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418520100613248","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699993890572800","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Food region segmentation in meal images using touch points"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981471322180352","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Representative Discovery of Structure Cues for Weakly-Supervised Image Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1362262945416469888","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Food-101 – Mining Discriminative Components with Random Forests"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544419162969728","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544420599749760","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"\"GrabCut\""}]},{"@id":"https://cir.nii.ac.jp/crid/1362544420615067648","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Food image analysis: Segmentation, identification and weight estimation"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544420717908864","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Simultaneous Detection and Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544420722848384","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Food Detection and Recognition Using Convolutional Neural Network"}]},{"@id":"https://cir.nii.ac.jp/crid/1362825894435760000","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Selective Search for Object Recognition"}]},{"@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/1362825895250317568","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Recognition of Multiple-Food Images by Detecting Candidate Regions"}]},{"@id":"https://cir.nii.ac.jp/crid/1362825895665112448","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Unsupervised segmentation of color-texture regions in images and video"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107369522552704","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Constrained Convolutional Neural Networks for Weakly Supervised Segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107370153088896","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Is object localization for free? - Weakly-supervised learning with convolutional neural networks"}]},{"@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/1363388843981760640","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Two-Phase Learning for Weakly Supervised Object Localization"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670319394536832","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"From image-level to pixel-level labeling with Convolutional Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951793723433728","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Multiscale Combinatorial Grouping"}]},{"@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/1363951794000700160","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Going deeper with convolutions"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951794211117184","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Weakly supervised structured output learning for semantic segmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951795450215936","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233269827906048","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Im2Calories: Towards an Automated Mobile Vision Food Diary"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233270050445312","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Object Detection with Discriminatively Trained Part-Based Models"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233271237168256","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"ImageNet classification with deep convolutional neural networks"}]}],"dataSourceIdentifier":[{"@type":"JALC","@value":"oai:japanlinkcenter.org:2007281153"},{"@type":"CROSSREF","@value":"10.1587/transinf.2018cep0001"},{"@type":"CIA","@value":"130007671323"},{"@type":"KAKEN","@value":"PRODUCT-22205901"},{"@type":"KAKEN","@value":"PRODUCT-22396287"},{"@type":"KAKEN","@value":"PRODUCT-22912032"},{"@type":"KAKEN","@value":"PRODUCT-22205605"},{"@type":"KAKEN","@value":"PRODUCT-22857514"},{"@type":"KAKEN","@value":"PRODUCT-22866855"},{"@type":"OPENAIRE","@value":"doi_dedup___::459f686538fd983f23da1a5636275e17"}]}