{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,28]],"date-time":"2024-07-28T11:57:28Z","timestamp":1722167848244},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2016,8,1]],"date-time":"2016-08-01T00:00:00Z","timestamp":1470009600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2016,8]]},"DOI":"10.1016\/j.cviu.2016.02.016","type":"journal-article","created":{"date-parts":[[2016,6,7]],"date-time":"2016-06-07T11:26:44Z","timestamp":1465298804000},"page":"98-112","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":36,"special_numbering":"C","title":["You-Do, I-Learn: Egocentric unsupervised discovery of objects and their modes of interaction towards video-based guidance"],"prefix":"10.1016","volume":"149","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-8804-6238","authenticated-orcid":false,"given":"Dima","family":"Damen","sequence":"first","affiliation":[]},{"given":"Teesid","family":"Leelasawassuk","sequence":"additional","affiliation":[]},{"given":"Walterio","family":"Mayol-Cuevas","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.cviu.2016.02.016_bib0001","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2015.2409731","article-title":"The evolution of first person vision methods: a survey","volume":"25","author":"Betancourt","year":"2015","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2016.02.016_bib0002","series-title":"German Research Center for Artificial Intelligence, DFKI Research Reports (RR)","article-title":"Cognitive workflow capturing and rendering with on- body sensor networks (cognito)","author":"Bleser","year":"2013"},{"key":"10.1016\/j.cviu.2016.02.016_bib0003","series-title":"Ego-object discovery in lifelogging datasets","author":"Bolanos","year":"2015"},{"key":"10.1016\/j.cviu.2016.02.016_bib0004","series-title":"International Symposium on Mixed and Augmented Reality (ISMAR)","article-title":"Integrating 3D object detection, modelling and tracking on a mobile phone","author":"Bunnun","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0005","series-title":"International Conference on Robotics and Automation (ICRA)","article-title":"Exploiting domain knowledge for object discovery","author":"Collet","year":"2013"},{"key":"10.1016\/j.cviu.2016.02.016_bib0006","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Histograms of oriented gradients for human detection","author":"Dalal","year":"2005"},{"key":"10.1016\/j.cviu.2016.02.016_bib0007","series-title":"British Machine Vision Conference (BMVC)","article-title":"Real-time learning and detection of 3D texture-less objects: A scalable approach","author":"Damen","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0008","series-title":"ECCV Workshop on Assistive Computer Vision and Robotics (ACVR)","article-title":"Multi-user egocentric online system for unsupervised assistance on object usage","author":"Damen","year":"2014"},{"key":"10.1016\/j.cviu.2016.02.016_bib0009","series-title":"British Machine Vision Conference (BMVC)","article-title":"You-do, i-learn: Discovering task relevant objects and their modes of interaction from multi-user egocentric video","author":"Damen","year":"2014"},{"issue":"2","key":"10.1016\/j.cviu.2016.02.016_bib0010","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","article-title":"A cluster separation measure","volume":"1","author":"Davies","year":"1979","journal-title":"Pattern Anal. Mach. Intell. (PAMI)"},{"key":"10.1016\/j.cviu.2016.02.016_bib0011","series-title":"Workshop on Perasive Eye Traking and Mobile Eye-based Interaction (PETMEI)","article-title":"Automatic analysis of eye-tracking data using object detection algorithms","author":"De Beugher","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0012","series-title":"European Conference on Computer Vision (ECCV)","article-title":"Learning to recognize daily actions using gaze","author":"Fathi","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0013","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Modeling actions through state changes","author":"Fathi","year":"2013"},{"key":"10.1016\/j.cviu.2016.02.016_bib0014","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Learning to recognise objects in egocentric activities","author":"Fathi","year":"2011"},{"key":"10.1016\/j.cviu.2016.02.016_bib0015","article-title":"Saliency-based object recognition in video","author":"Gonzalez-Diaz","year":"2014","journal-title":"HAL Arch."},{"key":"10.1016\/j.cviu.2016.02.016_bib0016","series-title":"International Symposium on Mixed and Augmented Reality (ISMAR)","article-title":"Task support system by displaying instructional video onto ar workspace","author":"Goto","year":"2010"},{"key":"10.1016\/j.cviu.2016.02.016_bib0017","series-title":"International Conference on Artificial Reality and Telexistence","article-title":"Improvement of wearable view sharing system for skill training","author":"Hashimoto","year":"2011"},{"key":"10.1016\/j.cviu.2016.02.016_bib0018","series-title":"International Conference on Robotics and Automation (ICRA)","article-title":"Toward object discovery and modeling via 3-d scene comparison","author":"Herbst","year":"2011"},{"key":"10.1016\/j.cviu.2016.02.016_bib0019","series-title":"Mixed and Augmented Reality Workshops (ISMARW)","article-title":"Efficient texture-less object detection for augmented reality guidance","author":"Hodan","year":"2015"},{"issue":"17","key":"10.1016\/j.cviu.2016.02.016_bib0020","doi-asserted-by":"crossref","DOI":"10.1523\/JNEUROSCI.21-17-06917.2001","article-title":"Eye-hand coordination in object manipulation","volume":"21","author":"Johansson","year":"2001","journal-title":"J. Neurosci."},{"issue":"1","key":"10.1016\/j.cviu.2016.02.016_bib0021","article-title":"Data-driven objectness. IEEE trans","volume":"37","author":"Kang","year":"2015","journal-title":"Pattern Anal. Mach. Intell. (PAMI)"},{"key":"10.1016\/j.cviu.2016.02.016_bib0022","series-title":"International Conference on Computer Vision (ICCV)","article-title":"Discovering object instances from scenes of daily living","author":"Kang","year":"2011"},{"key":"10.1016\/j.cviu.2016.02.016_bib0023","series-title":"International Conference on Robotics and Automation (ICRA)","article-title":"Determination of motion breakpoints in a task sequence from human hand motion","author":"Kang","year":"1994"},{"key":"10.1016\/j.cviu.2016.02.016_bib0024","series-title":"International Conference on Robotics and Automation (ICRA)","article-title":"Object discovery in 3d scenes via shape analysis","author":"Karpathy","year":"2013"},{"key":"10.1016\/j.cviu.2016.02.016_bib0025","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Unsupervised modeling of object categories using link analysis techniques","author":"Kim","year":"2008"},{"key":"10.1016\/j.cviu.2016.02.016_bib0026","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Fast unsupervised ego-action learning for first-person sports videos","author":"Kitani","year":"2011"},{"key":"10.1016\/j.cviu.2016.02.016_bib0027","series-title":"International Symposium on Mixed and Augmented Reality (ISMAR)","article-title":"Parallel tracking and mapping for small AR workspaces","author":"Klein","year":"2007"},{"key":"10.1016\/j.cviu.2016.02.016_bib0028","unstructured":"A.S. Laboratories, Mobile Eye-XG, 2011, http:\/\/www.asleyetracking.com\/."},{"issue":"3","key":"10.1016\/j.cviu.2016.02.016_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.preteyeres.2006.01.002","article-title":"Eye movements and the control of actions in everyday life","volume":"25","author":"Land","year":"2006","journal-title":"Prog. Retin. Eye Res."},{"issue":"11","key":"10.1016\/j.cviu.2016.02.016_bib0030","doi-asserted-by":"crossref","DOI":"10.1068\/p2935","article-title":"The roles of vision and eye movements in the control of activities of daily living","volume":"28","author":"Land","year":"1999","journal-title":"Perception"},{"issue":"2","key":"10.1016\/j.cviu.2016.02.016_bib0031","article-title":"On space-time interest points","volume":"64","author":"Laptev","year":"2005","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"10.1016\/j.cviu.2016.02.016_bib0032","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Discovering important people and objects for egocentric video summarization","author":"Lee","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0033","series-title":"International Symposium on Wearable Computers (ISWC)","article-title":"Estimating visual attention from a head mounted imu","author":"Leelasawassuk","year":"2015"},{"key":"10.1016\/j.cviu.2016.02.016_bib0034","series-title":"International Symposium on Wearable Computers (ISWC)","article-title":"3D from looking: Using wearable gaze tracking for hands-free and feedback-free object modelling","author":"Leelasawassuk","year":"2013"},{"key":"10.1016\/j.cviu.2016.02.016_bib0035","series-title":"International Conference on Computer Vision (ICCV)","article-title":"Learning to predict gaze in egocentric video","author":"Li","year":"2013"},{"key":"10.1016\/j.cviu.2016.02.016_bib0036","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Story-driven summarization for egocentric video","author":"Lu","year":"2013"},{"key":"10.1016\/j.cviu.2016.02.016_bib0037","series-title":"International Conference on Intelligent Robots and Systems (IROS)","article-title":"Object disappearance for object discovery","author":"Mason","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0038","series-title":"Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","article-title":"An attention-based activity recognition for egocentric video","author":"Matsuo","year":"2014"},{"key":"10.1016\/j.cviu.2016.02.016_bib0039","article-title":"On the choice and placement of wearable vision sensors","volume":"39","author":"Mayol","year":"2009","journal-title":"IEEE Trans. on Systems Man And Cybernetics"},{"key":"10.1016\/j.cviu.2016.02.016_bib0040","series-title":"International Symposium on Robotics Research","article-title":"Applying active vision and SLAM to wearables","author":"Mayol-Cuevas","year":"2004"},{"key":"10.1016\/j.cviu.2016.02.016_bib0041","series-title":"IEEE International Symposium on Wearable Computers (ISWC)","article-title":"Wearable hand activity recognition for event summarization","author":"Mayol-Cuevas","year":"2005"},{"key":"10.1016\/j.cviu.2016.02.016_bib0042","series-title":"Advances in Neural Information Processing Systems (NIPS)","article-title":"On spectral clustering: analysis and an algorithm","author":"Ng","year":"2002"},{"issue":"1","key":"10.1016\/j.cviu.2016.02.016_bib0043","doi-asserted-by":"crossref","DOI":"10.3390\/s16010072","article-title":"Recognition of activities of daily living with egocentric vision: a review","volume":"16","author":"Nguyen","year":"2016","journal-title":"Sensors"},{"key":"10.1016\/j.cviu.2016.02.016_bib0044","series-title":"Computer Vision and Pattern Recognition Workshops (CVPRW)","article-title":"Coupling eye-motion and ego-motion features for first-person activity recognition","author":"Ogaki","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0045","series-title":"International Symposium on Mixed and Augmented Reality (ISMAR)","article-title":"Learning task structure from video examples for workflow tracking and authoring","author":"Petersen","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0046","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Detecting acitivites of daily living in first-person camera views","author":"Pirsiavash","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0047","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Figure-ground segmentation improves handled object recognition in egocentric video","author":"Ren","year":"2010"},{"key":"10.1016\/j.cviu.2016.02.016_bib0048","series-title":"Computer Vision and Pattern Recognition Workshop (CVPRW)","article-title":"Egocentric recognition of handled objects: Benchmark and analysis","author":"Ren","year":"2009"},{"key":"10.1016\/j.cviu.2016.02.016_bib0049","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"Using multiple segmentations to discover objects and their extent in image collections","author":"Russell","year":"2006"},{"key":"10.1016\/j.cviu.2016.02.016_bib0050","series-title":"Symposium on Eye Tracking Research & Applications","article-title":"Identifying fixations and saccades in eye-tracking protocols","author":"Salvucci","year":"2000"},{"key":"10.1016\/j.cviu.2016.02.016_bib0051","series-title":"International Conference on Pattern Recongition (ICPR)","article-title":"A theory of the quasi-static world","author":"Sanders","year":"2002"},{"key":"10.1016\/j.cviu.2016.02.016_bib0052","series-title":"Computer Vision and Pattern Recognition (CVPR)","article-title":"D - clutter: Building object model library from unsupervised segmentation of cluttered scenes","author":"Somanath","year":"2009"},{"key":"10.1016\/j.cviu.2016.02.016_bib0053","series-title":"Computer Vision and Pattern Recognition Workshop (CVPRW)","article-title":"EyeWatchMe - 3D hand and object tracking for inside out activity analysis","author":"Sun","year":"2009"},{"key":"10.1016\/j.cviu.2016.02.016_bib0054","series-title":"First Workshop on Egocentric Vision, Computer Vision and Pattern Recognition (CVPRW)","article-title":"High level activity recognition using low resolution wearable vision","author":"Sundaram","year":"2009"},{"key":"10.1016\/j.cviu.2016.02.016_bib0055","series-title":"International Conference on Robotics and Automation (ICRA)","article-title":"What are we doing here? egocentric activity recognition on the move for contextual mapping","author":"Sundaram","year":"2012"},{"key":"10.1016\/j.cviu.2016.02.016_bib0056","series-title":"Symposium on Eye-Tracking Research & Applications (ETRA)","article-title":"Estimating 3d point-of-regard and visualizing gaze trajectories under natural head movements","author":"Takemura","year":"2010"},{"issue":"2","key":"10.1016\/j.cviu.2016.02.016_bib0057","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-009-0271-8","article-title":"Unsupervised object discovery: a comparison","volume":"88","author":"Tuytelaars","year":"2010","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"10.1016\/j.cviu.2016.02.016_bib0058","series-title":"Asian Conference on Computer Vision (ACCV)","article-title":"Recognizing daily activities from first-person videos with multi-task clustering","author":"Yan","year":"2014"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/api.elsevier.com\/content\/article\/PII:S1077314216000709?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/api.elsevier.com\/content\/article\/PII:S1077314216000709?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,9,9]],"date-time":"2019-09-09T06:15:04Z","timestamp":1568009704000},"score":1,"resource":{"primary":{"URL":"http:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314216000709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8]]},"references-count":58,"alternative-id":["S1077314216000709"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2016.02.016","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2016,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"You-Do, I-Learn: Egocentric unsupervised discovery of objects and their modes of interaction towards video-based guidance","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"http:\/\/dx.doi.org\/10.1016\/j.cviu.2016.02.016","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2016 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}
