{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:25:15Z","timestamp":1766136315593},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2012,6,1]],"date-time":"2012-06-01T00:00:00Z","timestamp":1338508800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1007\/s11042-012-1117-x","type":"journal-article","created":{"date-parts":[[2012,5,31]],"date-time":"2012-05-31T21:55:41Z","timestamp":1338501341000},"page":"743-771","source":"Crossref","is-referenced-by-count":44,"title":["Hierarchical Hidden Markov Model in detecting activities of daily living in wearable videos for studies of dementia"],"prefix":"10.1007","volume":"69","author":[{"given":"Svebor","family":"Karaman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jenny","family":"Benois-Pineau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladislavs","family":"Dovgalecs","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R\u00e9mi","family":"M\u00e9gret","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Pinquier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R\u00e9gine","family":"Andr\u00e9-Obrecht","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yann","family":"Ga\u00ebstel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Fran\u00e7ois","family":"Dartigues","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,6,1]]},"reference":[{"issue":"5","key":"1117_CR1","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1002\/ana.21509","volume":"64","author":"H Amieva","year":"2008","unstructured":"Amieva H, Le Goff M, Millet X, Orgogozo J-M, P\u00e9r\u00e8s K, Barberger-Gateau P, Jacqmin-Gadda H, Dartigues J-F (2008) Prodromal Alzheimer\u2019s disease: successive emergence of the clinical symptoms. Ann Neurol 64(5):492\u2013498","journal-title":"Ann Neurol"},{"issue":"1","key":"1117_CR2","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/29.1486","volume":"36","author":"R Andr\u00e9-Obrecht","year":"1988","unstructured":"Andr\u00e9-Obrecht R (1988) A new statistical approach for automatic speech segmentation. IEEE Trans Audio Speech Signal Process 36(1):29\u201340","journal-title":"IEEE Trans Audio Speech Signal Process"},{"issue":"1","key":"1117_CR3","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s11042-010-0643-7","volume":"51","author":"L Ballan","year":"2011","unstructured":"Ballan L, Bertini M, Del Bimbo A, Seidenari L, Serra G (2011) Event detection and recognition for semantic annotation of video. Multimed Tool Appl 51(1):279\u2013302","journal-title":"Multimed Tool Appl"},{"issue":"3","key":"1117_CR4","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay H, Tuytelaars T, Van Gool L (2008) SURF: speeded-up robust features. Comput Vis Image Understand 110(3):346\u2013359","journal-title":"Comput Vis Image Understand"},{"key":"1117_CR5","doi-asserted-by":"crossref","unstructured":"Bengio Y, Delalleau O, Le Roux N, Paiement J-F, Vincent P, Ouimet M (2006) Spectral dimensionality reduction. Feature Extraction. Foundations and Applications, Springer, pp. 519\u2013550","DOI":"10.1007\/978-3-540-35488-8_28"},{"key":"1117_CR6","unstructured":"Benois-Pineau J, Kramer P (2005) Camera motion detection in the rough indexing paradigm. TREC Video"},{"key":"1117_CR7","first-page":"3741","volume":"6","author":"JS Boreczky","year":"1998","unstructured":"Boreczky JS, Wilcox LD (1998) A Hidden Markov Model framework for video segmentation using audio and image features. Proc IEEE Int Conf Acoust Speech Signal Process 6:3741\u20133744","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"issue":"2","key":"1117_CR8","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1023\/A:1009715923555","volume":"2","author":"C Burges","year":"1998","unstructured":"Burges C (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2(2):121\u2013167","journal-title":"Data Min Knowl Discov"},{"key":"1117_CR9","doi-asserted-by":"crossref","unstructured":"Byrne D, Doherty AR, Jones GJF, Smeaton AF, Kumpulainen S, J\u00e4rvelin K (2008) The SenseCam as a tool for task observation. In Proceedings of the 22nd British CHI Group Annual Conference on HCI 2008: People and Computers XXII: Culture, Creativity, Interaction-Volume 2, 19\u201322","DOI":"10.14236\/ewic\/HCI2008.24"},{"issue":"9","key":"1117_CR10","doi-asserted-by":"crossref","first-page":"1657","DOI":"10.1109\/TPAMI.2008.215","volume":"31","author":"SP Chatzis","year":"2009","unstructured":"Chatzis SP, Kosmopoulos DI, Varvarigou TA (2009) Robust sequential data modeling using an outlier tolerant hidden markov model. IEEE Trans Pattern Anal Mach Intell 31(9):1657\u20131669","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"1117_CR11","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.cviu.2007.09.002","volume":"111","author":"M Delakis","year":"2008","unstructured":"Delakis M, Gravier G, Gros P (2008) Audiovisual integration with Segment Models for tennis video parsing. Comput Vis Image Understand 111(2):142\u2013154","journal-title":"Comput Vis Image Understand"},{"issue":"5","key":"1117_CR12","doi-asserted-by":"crossref","first-page":"1948","DOI":"10.1016\/j.chb.2011.05.002","volume":"27","author":"A Doherty","year":"2011","unstructured":"Doherty A, Caprani N, \u00d3conaire C, Kalnikaite V, Gurrin C, Smeaton AF, O\u2019Connor NE (2011) Passively recognising human activities through lifelogging. Comput Hum Behav 27(5):1948\u20131958","journal-title":"Comput Hum Behav"},{"key":"1117_CR13","unstructured":"First Workshop on Egocentric Vision, held in conjunction with CVPR (2009)"},{"key":"1117_CR14","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007469218079","volume":"32","author":"S Fine","year":"1998","unstructured":"Fine S, Singer Y, Tishby N (1998) The Hierarchical Hidden Markov Model: analysis and applications. Mach Learn 32:41\u201362","journal-title":"Mach Learn"},{"key":"1117_CR15","doi-asserted-by":"crossref","unstructured":"Ga\u00ebstelY, Onifade-Fagbemi C, Trophy F, Karaman S, Benois-Pineau J, M\u00e9gret R, Pinquier J, Andr\u00e9-Obrecht R, Dartigues J-F (2011) Autonomy at home and early diagnosis in Alzheimer Disease: usefulness of video indexing applied to clinical issues. The IMMED Project. Alzheimer\u2019s Association International Conference on Alzheimer\u2019s Disease\u2014AAICAD, 16\u201321 Juillet, France","DOI":"10.1016\/j.jalz.2011.05.694"},{"key":"1117_CR16","doi-asserted-by":"crossref","unstructured":"Gales M, Young J (1993) The theory of segmental Hidden Markov Models. University of Cambridge, Department of Engineering","DOI":"10.21437\/Eurospeech.1993-354"},{"key":"1117_CR17","doi-asserted-by":"crossref","unstructured":"Galliano S, Geofrois E, De Mosterfa, Bonastre JF, Gravier G (2005) The Ester phase II evaluation campaign for the rich transcription of the French broadcast news. EUROSPEECH, pp. 1149\u20131152","DOI":"10.21437\/Interspeech.2005-441"},{"key":"1117_CR18","doi-asserted-by":"crossref","unstructured":"Gao Z, Chen M, Hauptmann A, Cai A (2010) Comparing evaluation protocols on the KTH dataset. International Conference on Human Behavior Understanding\u2014HBU, LNCS volume 6219, pp. 88\u2013100","DOI":"10.1007\/978-3-642-14715-9_10"},{"key":"1117_CR19","unstructured":"Gorisse D, Precioso F, Gosselin P, Granjon L, Pellerin D, Rombaut M, Bredin H, Koenig L, Vieux R, Mansencal B, Benois-Pineau J, Boujut H, Morand C, J\u00e9gou H, Ayache S, Safadi B, Tong Y, Thollard F, Qu\u00e9not GM, Cord M, Beno\u00eet A, Lambert P (2010) IRIM at TRECVID 2010: semantic indexing and instance search. Proc. TRECVID 2010 Workshop"},{"key":"1117_CR20","doi-asserted-by":"crossref","unstructured":"Guyot P, Pinquier J, Andr\u00e9-Obrecht R (2012, June 27\u201329) Water flow detection from a wearable device with an new feature, the spectral cover. Submitted to CBMI\u20192012, IEEE Workshop, Annecy, France","DOI":"10.1109\/CBMI.2012.6269814"},{"key":"1117_CR21","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.1016\/j.artint.2009.05.002","volume":"173","author":"R Hamid","year":"2009","unstructured":"Hamid R, Maddi S, Johnson A, Bobick A, Essa I, Isbell Ch (2009) A novel sequence representation for unsupervised analysis of human activities. Artif Intell 173:1221\u20131244","journal-title":"Artif Intell"},{"key":"1117_CR22","doi-asserted-by":"crossref","unstructured":"Harte N, Lennon D, Kokaram A (2009) On parsing visual sequences with the hidden Markov model. EURASIP J Image Video Process, 2009:1\u201313","DOI":"10.1155\/2009\/924287"},{"key":"1117_CR23","unstructured":"Hill M, Hua G, Natsev A, Smith JR, Xie L, Huang B, Merler M, Ouyang H, Zhou M (2010) IBM research TRECVID-2010 video copy detection and multimedia event detection system. Proc. TRECVID 2010 Workshop"},{"key":"1117_CR24","doi-asserted-by":"crossref","unstructured":"Hodges S, Williams L, Berry E, Izadi S, Srinivasan J, Butler A, Smyth G, Kapur N, Wood KR (2006) Sensecam: a retrospective memory aid. UBICOMP\u20192006, pp. 177\u2013193","DOI":"10.1007\/11853565_11"},{"key":"1117_CR25","unstructured":"HTK Web-Site: http:\/\/htk.eng.cam.ac.uk"},{"issue":"8","key":"1117_CR26","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1109\/34.868686","volume":"22","author":"Y Ivanov","year":"2000","unstructured":"Ivanov Y, Bobick A (2000) Recognition of visual activities and interactions by stochastic parsing. IEEE Trans Pattern Anal Mach Intell 22(8):852\u2013872","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1117_CR27","doi-asserted-by":"crossref","unstructured":"Jurie F, Triggs B (2005) Creating efficient codebooks for visual recognition. Tenth IEEE International Conference on Computer Vision\u2014ICCV, 1, pp. 604\u2013610","DOI":"10.1109\/ICCV.2005.66"},{"key":"1117_CR28","doi-asserted-by":"crossref","unstructured":"Karaman S, Benois-Pineau J, Dartigues J-F, Ga\u00ebstel Y, M\u00e9gret R, Pinquier J (2011) Activities of daily living indexing by hierarchical HMM for dementia diagnostics. Content-Based Multimedia Indexing and retrieval\u2014CBMI\u20192011. IEEE Workshop, 13\u201315 Juin, Madrid, Espagne","DOI":"10.1109\/CBMI.2011.5972524"},{"key":"1117_CR29","first-page":"309","volume":"3","author":"E Kijak","year":"2003","unstructured":"Kijak E, Gravier G, Gros P, Oisel L, Bimbot F (2003) HMM based structuring of tennis videos using visual and audio cues. ICME 3:309\u2013312","journal-title":"ICME"},{"key":"1117_CR30","unstructured":"Lan Z-Z, Bao L, Yu S-I, Liu W, Hauptmann AG (2012) Double fusion for multimedia event detection. International Conference on Multimedia Modeling (MMM\u201912), pp. 173\u2013185"},{"key":"1117_CR31","doi-asserted-by":"crossref","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. IEEE Conference on Computer Vision and Pattern Recognition\u2014CVPR, 2, pp. 2169\u20132178","DOI":"10.1109\/CVPR.2006.68"},{"key":"1117_CR32","doi-asserted-by":"crossref","unstructured":"Liu J, Luo J, Shah M (2009) Recognizing realistic actions from videos \u2018in the wild\u2019. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1996\u20132003","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"1117_CR33","doi-asserted-by":"crossref","unstructured":"Megret R, Szolgay D, Benois-Pineau J, Joly P, Pinquier J, Dartigues J-F, Helmer C (2008) Wearable video monitoring of people with age dementia: video indexing at the service of healthcare. International Workshop on Content-Based Multimedia Indexing - CBMI, Conference Proceedings, art. no. 4564934, pp. 101\u2013108","DOI":"10.1109\/CBMI.2008.4564934"},{"key":"1117_CR34","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/89.536930","volume":"4","author":"M Ostendorf","year":"1995","unstructured":"Ostendorf M, Digalakis V, Kimball OA (1995) From HMMs to segment models: a unified view of stochastic modeling for speech recognition. IEEE Trans Speech Audio Process 4:360\u2013378","journal-title":"IEEE Trans Speech Audio Process"},{"key":"1117_CR35","doi-asserted-by":"crossref","unstructured":"Piccardi L, Noris B, Barbey O, Billard A, Schiavone G, Keller F, von Hofsten C 2007 Wearcam: a head wireless camera for monitoring gaze attention and for the diagnosis of developmental disorders in young children. International Symposium on Robot & Human Interactive Communication, pp. 177\u2013193","DOI":"10.1109\/ROMAN.2007.4415154"},{"issue":"3","key":"1117_CR36","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1007\/s11042-006-0027-1","volume":"30","author":"J Pinquier","year":"2006","unstructured":"Pinquier J, Andr\u00e9-Obrecht R (2006) Audio indexing: primary components retrieval\u2014robust classification in audio documents. Multimed Tool Appl 30(3):313\u2013330","journal-title":"Multimed Tool Appl"},{"issue":"6","key":"1117_CR37","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe R (2010) A survey on vision-based human action recognition. Image Vis Comput 28(6):976\u2013990","journal-title":"Image Vis Comput"},{"key":"1117_CR38","doi-asserted-by":"crossref","unstructured":"Quenot G, Benois-Pineau J, Mansencal B, Rossi E et al (2008) Rushes summarization by IRIM consortium: redundancy removal and multi-feature fusion. VS\u201908 (Trec Video Summarization),","DOI":"10.1145\/1463563.1463577"},{"issue":"2","key":"1117_CR39","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner LR (1989) A tutorial on hidden markov models and selected applications in speech recognition. Proc IEEE 77(2):257\u2013286","journal-title":"Proc IEEE"},{"issue":"6","key":"1117_CR40","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1162\/089976698300017467","volume":"10","author":"B Scholkopf","year":"1998","unstructured":"Scholkopf B, Smola A, Muller KR (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10(6):1299\u20131319","journal-title":"Neural Comput"},{"key":"1117_CR41","doi-asserted-by":"crossref","unstructured":"Schuldt C, Laptev I, Caputo B (2004) Recognizing human actions: a local SVM approach. Proceedings of the 17th International Conference on Pattern Recognition (ICPR\u20192004), pp. 32\u201336","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"1117_CR42","unstructured":"Sikora T, Manjunath B, Salembier P (2002) Introduction to MPEG-7: multimedia content description interface"},{"key":"1117_CR43","doi-asserted-by":"crossref","unstructured":"Spriggs EH, De La Torre F, Hebert M (2009) Temporal segmentation and activity classification from first-person sensing. In First Workshop on Egocentric Vision, pp. 17\u201324","DOI":"10.1109\/CVPRW.2009.5204354"},{"key":"1117_CR44","doi-asserted-by":"crossref","unstructured":"Sundaram S, Mayol-Cuevas W (2009) High level activity recognition using low resolution wearable vision. In First Workshop on Egocentric Vision, pp. 25\u201332","DOI":"10.1109\/CVPRW.2009.5204355"},{"key":"1117_CR45","doi-asserted-by":"crossref","unstructured":"Sundaram S, Mayol-Cuevas W (2010) Egocentric visual event classification with location-based priors. In International Symposium on Visual Computing, Lecture Notes in Computer Science volume 6454, pp. 596\u2013605","DOI":"10.1007\/978-3-642-17274-8_58"},{"key":"1117_CR46","doi-asserted-by":"crossref","unstructured":"Surie D, Pederson T, Lagriffoul F, Janlert L-E, Sj\u00f6lie D (2007) Activity recognition using an egocentric perspective of everyday objects. Ubiquitous Intelligence and Computing. Springer, pp. 246\u2013257","DOI":"10.1007\/978-3-540-73549-6_25"},{"key":"1117_CR47","unstructured":"Young S, Evermann G et al (1997) The HTK book"},{"key":"1117_CR48","unstructured":"Young SJ, Young S (1994) The HTK hidden Markov model toolkit: design and philosophy. Entropic Cambridge Research Laboratory, Ltd"},{"key":"1117_CR49","doi-asserted-by":"crossref","unstructured":"Zouba N, Bremond F, Anfonso A, Thonnat M, Pascual E, Guerin O (2010 May) Monitoring elderly activities at home. Gerontechnology 9(2):263","DOI":"10.4017\/gt.2010.09.02.285.00"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1117-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-012-1117-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1117-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T01:27:10Z","timestamp":1687483630000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-012-1117-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,1]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["1117"],"URL":"https:\/\/doi.org\/10.1007\/s11042-012-1117-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,1]]}}}