{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T21:17:03Z","timestamp":1773868623412,"version":"3.50.1"},"reference-count":150,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T00:00:00Z","timestamp":1430438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Erasmus Mundus joint Doctorate in Interactive and Cognitive Environments, through the Education, Audiovisual and Culture Executive Agency, Agency of the European Commission under EMJD ICE"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1109\/tcsvt.2015.2409731","type":"journal-article","created":{"date-parts":[[2015,3,6]],"date-time":"2015-03-06T19:58:07Z","timestamp":1425671887000},"page":"744-760","source":"Crossref","is-referenced-by-count":156,"title":["The Evolution of First Person Vision Methods: A Survey"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3584-3118","authenticated-orcid":false,"given":"Alejandro","family":"Betancourt","sequence":"first","affiliation":[]},{"given":"Pietro","family":"Morerio","sequence":"additional","affiliation":[]},{"given":"Carlo S.","family":"Regazzoni","sequence":"additional","affiliation":[]},{"given":"Matthias","family":"Rauterberg","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2001.958135"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/VSMM.2001.969701"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2000.888484"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.757481"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACV.1998.732882"},{"key":"ref30","first-page":"1502","article-title":"Hand detection in first person vision","author":"morerio","year":"2013","journal-title":"Proc 18th Int Conf Inf Fusion"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/RATFG.2001.938920"},{"key":"ref36","first-page":"40","article-title":"VizWear: Toward human-centered interaction through wearable vision and visualization","volume":"2195","author":"kurata","year":"0","journal-title":"Advances in Multimedia Information Processing"},{"key":"ref35","first-page":"4","article-title":"The hand-mouse: A human interface suitable for augmented reality environments enabled by visual wearables","author":"kurata","year":"2000","journal-title":"Proc Symp Mixed Reality"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2000.888467"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.92"},{"key":"ref27","first-page":"1","article-title":"Egocentric recognition of handled objects: Benchmark and analysis","author":"philipose","year":"2009","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"ref29","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"ghosh","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.amepre.2012.11.008"},{"key":"ref22","first-page":"48","article-title":"FreeGlass for developers, ‘haccessibility’, and digital eye glass + lifeglogging research in a (sur\/sous)veillance society","author":"mann","year":"2013","journal-title":"Proc Int Conf Inf Soc"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(01)00102-X"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247805"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom.2014.6813944"},{"key":"ref26","first-page":"53","article-title":"Opportunistic detection methods for emotion-aware smartphone applications","author":"bisio","year":"2013","journal-title":"Creating Personal Social and Urban Awareness Through Pervasive Computing"},{"key":"ref100","article-title":"Video-based action detection using multiple wearable cameras","author":"zheng","year":"2014","journal-title":"Proc Workshop ChaLearn Looking People"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-5379-7"},{"key":"ref50","first-page":"9","article-title":"EYEWATCHME—3D hand and object tracking for inside out activity analysis","author":"sun","year":"2009","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit Workshops"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2005.10"},{"key":"ref150","first-page":"1","article-title":"Bio-inspired relevant interaction modelling in cognitive crowd management","author":"chiappino","year":"2014","journal-title":"J Ambient Intell Humanized Comput"},{"key":"ref146","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-014-0794-5","article-title":"Predicting important objects for egocentric video summarization","author":"lee","year":"2015","journal-title":"Int J Comput Vis"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2012.6256569"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.85"},{"key":"ref149","first-page":"242","article-title":"A bio-inspired knowledge representation method for anomaly detection in cognitive video surveillance systems","author":"chiappino","year":"2013","journal-title":"Proc 6th Int Conf Inf Fusion (Fusion)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1049"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408865"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.364109"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5244\/C.21.112"},{"key":"ref55","first-page":"62","article-title":"Touching the visualized invisible: Wearable AR with a multimodal interface","volume":"26","author":"k\u00f6lsch","year":"2006","journal-title":"IEEE Comput Graph Appl"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2006.66"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MMMC.2005.34"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1099083.1099092"},{"key":"ref40","first-page":"325","article-title":"Summarization of wearable videos using support vector machine","author":"ng","year":"2002","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref4","first-page":"177","article-title":"SenseCam: A retrospective memory aid","author":"hodges","year":"2006","journal-title":"Proc Int Conf Ubiquitous Comput"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/11008941_35","article-title":"Applying active vision and SLAM to wearables","volume":"15","author":"mayol","year":"2005","journal-title":"Springer Tracts Adv Robot"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.1998.729529"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2006.87"},{"key":"ref8","first-page":"1","article-title":"Situation aware computing with wearable computers","author":"schiele","year":"1999","journal-title":"Augmented Reality and Wearable Computers"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2005.57"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/34.735811"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/3-540-49256-9_4","article-title":"An interactive computer vision system DyPERS: Dynamic personal enhanced reality system","volume":"1542","author":"schiele","year":"1999","journal-title":"Computer Vision Systems"},{"key":"ref46","first-page":"158","article-title":"Fast 2D hand tracking with flocks of features and multi-cue integration","author":"kolsch","year":"2004","journal-title":"Proc Comput Vis Pattern Recognit Workshop"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2004.36"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1026653.1026654"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1026653.1026660"},{"key":"ref42","first-page":"146","article-title":"The memory glasses: Subliminal vs. overt memory support with imperfect information","author":"devaul","year":"2005","journal-title":"Proc 7th IEEE Int Symp Wearable Comput"},{"key":"ref41","first-page":"1","article-title":"The MyLifeBits lifetime store","author":"gemmell","year":"2002","journal-title":"Transactions on Multimedia Computing Communications and Applications"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/973264.973270"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1220850"},{"key":"ref127","article-title":"Egocentric video biometrics","author":"hoshen","year":"2014"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.89"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2362852"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/MNRAO.1994.346260"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995406"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995731"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.57"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0376-0"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2011.05.002"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247710"},{"key":"ref130","first-page":"28","article-title":"Learning to recognize human action sequences","author":"yu","year":"2002","journal-title":"Proc 2nd Int Conf Develop Learn"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22822-3_42"},{"key":"ref75","article-title":"A wearable device for first person vision","author":"devyver","year":"2011","journal-title":"Proc Int Symp Quality of Life Technology"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2004.7"},{"key":"ref134","volume":"6","author":"riva","year":"2005","journal-title":"Ambient Intelligence The Evolution of Technology Communication and Cognition Towards the Future of Human-Computer Interac-tion"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ACVMOT.2005.17"},{"key":"ref78","first-page":"314","article-title":"Learning to recognize daily actions using gaze","author":"fathi","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2005.22"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2012.28"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/MOBIQ.2004.1331713"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2011.02.007"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738769"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2013.06.032"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2008.4911577"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.12.012"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204354"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843609001863"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204355"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2009.5202661"},{"key":"ref140","article-title":"Event matching from significantly different views using motion barcodes","author":"ben-artzi","year":"2014"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540074"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1080\/01431160600746456"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2010.5529903"},{"key":"ref142","first-page":"1","article-title":"Event based switched dynamic Bayesian networks for autonomous cognitive crowd monitoring","author":"chiappino","year":"2013","journal-title":"Wide Area Surveillance"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0403-8"},{"key":"ref143","author":"camastra","year":"2007","journal-title":"Machine Learning for Audio Image and Video Analysis Theory and Applications"},{"key":"ref68","first-page":"762","article-title":"Discovering object instances from scenes of daily living","author":"kang","year":"2011","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2000.888470"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref145","first-page":"1","article-title":"A generative superpixel method","author":"morerio","year":"2014","journal-title":"Proc 17th IEEE Int Conf Inf Fusion (FUSION)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.1998.729538"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1021\/nn500614k"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2013.35"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.83"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553735"},{"key":"ref107","first-page":"4920","article-title":"Finger-fist detection in first-person view based on monocular vision using Haar-like features","author":"jingtao","year":"2014","journal-title":"Proc Chin Control Conf"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1097\/01.EEM.0000443910.87918.22"},{"key":"ref92","first-page":"1","article-title":"An egocentric vision based assistive co-robot","volume":"2013","author":"zhang","year":"2013","journal-title":"Proc IEEE Int Conf Rehabil Robot"},{"key":"ref105","first-page":"457","article-title":"Glimpse-Data: Towards continuous vision-based personal analytics","volume":"40","author":"han","year":"2014","journal-title":"J Experim Psychol Human Perception Perform"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.333"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.86"},{"key":"ref90","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/2505323.2505328","article-title":"Modeling instrumental activities of daily living in egocentric vision as sequences of active objects and context for alzheimer disease research","author":"d\u00edaz","year":"2013","journal-title":"Proc 1st ACM Int Workshop Multimedia Indexing Inf Retr Healthcare"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.718"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.91"},{"key":"ref111","first-page":"14","article-title":"3D hand pose detection in egocentric RGB-D images","author":"rogez","year":"2014","journal-title":"Int J Comput Vis"},{"key":"ref112","first-page":"9","article-title":"Egocentric pose recognition in four lines of code","author":"rogez","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref110","article-title":"Head motion signatures from egocentric videos","author":"poleg","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref98","article-title":"Multi-user egocentric online system for unsupervised assistance on object usage","author":"damen","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.325"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.82"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.87"},{"key":"ref10","article-title":"Wearable computing and contextual awareness","author":"starner","year":"1999"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.1999.806642"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/2.566147"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2505483.2505490"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"331","DOI":"10.24908\/ss.v1i3.3344","article-title":"Sousveillance: Inventing and using wearable computing devices for data collection in surveillance environments","volume":"1","author":"mann","year":"2003","journal-title":"Surveillance and Society"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.999"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.88"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICALIP.2014.7009793"},{"key":"ref82","first-page":"431","article-title":"3D social saliency from head-mounted cameras","author":"park","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref117","first-page":"1","article-title":"Video segmentation of life-logging videos","author":"bola\u00f1os","year":"0","journal-title":"Articulated Motion and Deformable Objects"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1620545.1620571"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2012.6402555"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2200554"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33885-4_44"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-53842-1_37"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.4103\/0256-4602.85975"},{"key":"ref83","first-page":"277","article-title":"Attention prediction in egocentric video using motion and visual saliency","author":"yamada","year":"2012","journal-title":"Proc 1st Pacific Rim Conf Adv Image Video Technol"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/2662996.2663007"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2014.23014"},{"key":"ref116","first-page":"541","article-title":"Efficient retrieval from large-scale egocentric visual data using a sparse graph representation","author":"chandrasekhar","year":"2014","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239188"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_19"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601198"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.399"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1999.786951"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01069.x"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/1315184.1315188"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.326"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.458"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/2444776.2444786"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1186\/1743-0003-10-114"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/7100973\/07055926.pdf?arnumber=7055926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:02:10Z","timestamp":1642003330000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7055926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5]]},"references-count":150,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2015.2409731","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5]]}}}