UNSUPERVISED DANCE FIGURE ANALYSIS FROM VIDEO FOR DANCING AVATAR ANIMATION. Ofli, F., Erzin, E., Yemez, Y., Tekalp, A. M., Erdem, C. E., Erdem, A. T., Abaci, T., & Ozkan, M. K. In 2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5, of IEEE International Conference on Image Processing (ICIP), pages 1484-1487, 2008. IEEE Signal Proc Soc. 15th IEEE International Conference on Image Processing (ICIP 2008), San Diego, CA, OCT 12-15, 2008doi abstract bibtex This paper presents a framework for unsupervised video analysis in the context of dance performances, where gestures and 3D movements of a dancer are characterized by repetition of a set of unknown dance figures. The system is trained in an unsupervised manner using Hidden Markov Models (HMMs) to automatically segment multi-view video recordings of a dancer into recurring elementary temporal body motion patterns to identify the dance figures. That is, a parallel HMM structure is employed to automatically determine the number and the temporal boundaries of different dance figures in a given dance video. The success of the analysis framework has been evaluated by visualizing these dance figures on a dancing avatar animated by the computed 3D analysis parameters. Experimental results demonstrate that the proposed framework enables synthetic agents and/or robots to learn dance figures from video automatically.
@inproceedings{ ISI:000265921400372,
Author = {Ofli, F. and Erzin, E. and Yemez, Y. and Tekalp, A. M. and Erdem, C. E.
and Erdem, A. T. and Abaci, T. and Ozkan, M. K.},
Book-Group-Author = {{IEEE}},
Title = {{UNSUPERVISED DANCE FIGURE ANALYSIS FROM VIDEO FOR DANCING AVATAR
ANIMATION}},
Booktitle = {{2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5}},
Series = {{IEEE International Conference on Image Processing (ICIP)}},
Year = {{2008}},
Pages = {{1484-1487}},
Note = {{15th IEEE International Conference on Image Processing (ICIP 2008), San
Diego, CA, OCT 12-15, 2008}},
Organization = {{IEEE Signal Proc Soc}},
Abstract = {{This paper presents a framework for unsupervised video analysis in the
context of dance performances, where gestures and 3D movements of a
dancer are characterized by repetition of a set of unknown dance
figures. The system is trained in an unsupervised manner using Hidden
Markov Models (HMMs) to automatically segment multi-view video
recordings of a dancer into recurring elementary temporal body motion
patterns to identify the dance figures. That is, a parallel HMM
structure is employed to automatically determine the number and the
temporal boundaries of different dance figures in a given dance video.
The success of the analysis framework has been evaluated by visualizing
these dance figures on a dancing avatar animated by the computed 3D
analysis parameters. Experimental results demonstrate that the proposed
framework enables synthetic agents and/or robots to learn dance figures
from video automatically.}},
DOI = {{10.1109/ICIP.2008.4712047}},
ISSN = {{1522-4880}},
ISBN = {{978-1-4244-1765-0}},
ResearcherID-Numbers = {{Erzin, Engin/H-1716-2011
Eroglu Erdem, Cigdem/J-4216-2012}},
ORCID-Numbers = {{Erzin, Engin/0000-0002-2715-2368
Eroglu Erdem, Cigdem/0000-0002-9264-5652}},
Unique-ID = {{ISI:000265921400372}},
}
Downloads: 0
{"_id":"hS7XR3KwtAZQHMhTB","bibbaseid":"ofli-erzin-yemez-tekalp-erdem-erdem-abaci-ozkan-unsuperviseddancefigureanalysisfromvideofordancingavataranimation-2008","downloads":0,"creationDate":"2015-12-09T21:23:15.012Z","title":"UNSUPERVISED DANCE FIGURE ANALYSIS FROM VIDEO FOR DANCING AVATAR ANIMATION","author_short":["Ofli, F.","Erzin, E.","Yemez, Y.","Tekalp, A. M.","Erdem, C. E.","Erdem, A. T.","Abaci, T.","Ozkan, M. K."],"year":2008,"bibtype":"inproceedings","biburl":"https://drive.google.com/uc?export=download&id=1d5Wvl98W_buJq6prXBz16a_6uF9Cdt-7","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Ofli"],"firstnames":["F."],"suffixes":[]},{"propositions":[],"lastnames":["Erzin"],"firstnames":["E."],"suffixes":[]},{"propositions":[],"lastnames":["Yemez"],"firstnames":["Y."],"suffixes":[]},{"propositions":[],"lastnames":["Tekalp"],"firstnames":["A.","M."],"suffixes":[]},{"propositions":[],"lastnames":["Erdem"],"firstnames":["C.","E."],"suffixes":[]},{"propositions":[],"lastnames":["Erdem"],"firstnames":["A.","T."],"suffixes":[]},{"propositions":[],"lastnames":["Abaci"],"firstnames":["T."],"suffixes":[]},{"propositions":[],"lastnames":["Ozkan"],"firstnames":["M.","K."],"suffixes":[]}],"book-group-author":"IEEE","title":"UNSUPERVISED DANCE FIGURE ANALYSIS FROM VIDEO FOR DANCING AVATAR ANIMATION","booktitle":"2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5","series":"IEEE International Conference on Image Processing (ICIP)","year":"2008","pages":"1484-1487","note":"15th IEEE International Conference on Image Processing (ICIP 2008), San Diego, CA, OCT 12-15, 2008","organization":"IEEE Signal Proc Soc","abstract":"This paper presents a framework for unsupervised video analysis in the context of dance performances, where gestures and 3D movements of a dancer are characterized by repetition of a set of unknown dance figures. The system is trained in an unsupervised manner using Hidden Markov Models (HMMs) to automatically segment multi-view video recordings of a dancer into recurring elementary temporal body motion patterns to identify the dance figures. That is, a parallel HMM structure is employed to automatically determine the number and the temporal boundaries of different dance figures in a given dance video. The success of the analysis framework has been evaluated by visualizing these dance figures on a dancing avatar animated by the computed 3D analysis parameters. Experimental results demonstrate that the proposed framework enables synthetic agents and/or robots to learn dance figures from video automatically.","doi":"10.1109/ICIP.2008.4712047","issn":"1522-4880","isbn":"978-1-4244-1765-0","researcherid-numbers":"Erzin, Engin/H-1716-2011 Eroglu Erdem, Cigdem/J-4216-2012","orcid-numbers":"Erzin, Engin/0000-0002-2715-2368 Eroglu Erdem, Cigdem/0000-0002-9264-5652","unique-id":"ISI:000265921400372","bibtex":"@inproceedings{ ISI:000265921400372,\nAuthor = {Ofli, F. and Erzin, E. and Yemez, Y. and Tekalp, A. M. and Erdem, C. E.\n and Erdem, A. T. and Abaci, T. and Ozkan, M. K.},\nBook-Group-Author = {{IEEE}},\nTitle = {{UNSUPERVISED DANCE FIGURE ANALYSIS FROM VIDEO FOR DANCING AVATAR\n ANIMATION}},\nBooktitle = {{2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5}},\nSeries = {{IEEE International Conference on Image Processing (ICIP)}},\nYear = {{2008}},\nPages = {{1484-1487}},\nNote = {{15th IEEE International Conference on Image Processing (ICIP 2008), San\n Diego, CA, OCT 12-15, 2008}},\nOrganization = {{IEEE Signal Proc Soc}},\nAbstract = {{This paper presents a framework for unsupervised video analysis in the\n context of dance performances, where gestures and 3D movements of a\n dancer are characterized by repetition of a set of unknown dance\n figures. The system is trained in an unsupervised manner using Hidden\n Markov Models (HMMs) to automatically segment multi-view video\n recordings of a dancer into recurring elementary temporal body motion\n patterns to identify the dance figures. That is, a parallel HMM\n structure is employed to automatically determine the number and the\n temporal boundaries of different dance figures in a given dance video.\n The success of the analysis framework has been evaluated by visualizing\n these dance figures on a dancing avatar animated by the computed 3D\n analysis parameters. Experimental results demonstrate that the proposed\n framework enables synthetic agents and/or robots to learn dance figures\n from video automatically.}},\nDOI = {{10.1109/ICIP.2008.4712047}},\nISSN = {{1522-4880}},\nISBN = {{978-1-4244-1765-0}},\nResearcherID-Numbers = {{Erzin, Engin/H-1716-2011\n Eroglu Erdem, Cigdem/J-4216-2012}},\nORCID-Numbers = {{Erzin, Engin/0000-0002-2715-2368\n Eroglu Erdem, Cigdem/0000-0002-9264-5652}},\nUnique-ID = {{ISI:000265921400372}},\n}\n\n","author_short":["Ofli, F.","Erzin, E.","Yemez, Y.","Tekalp, A. M.","Erdem, C. E.","Erdem, A. T.","Abaci, T.","Ozkan, M. K."],"key":"ISI:000265921400372","id":"ISI:000265921400372","bibbaseid":"ofli-erzin-yemez-tekalp-erdem-erdem-abaci-ozkan-unsuperviseddancefigureanalysisfromvideofordancingavataranimation-2008","role":"author","urls":{},"metadata":{"authorlinks":{"erzin, e":"http://home.ku.edu.tr/"}}},"search_terms":["unsupervised","dance","figure","analysis","video","dancing","avatar","animation","ofli","erzin","yemez","tekalp","erdem","erdem","abaci","ozkan"],"keywords":[],"authorIDs":["56689bc2b3110c264a000354","566927fe71adeb5a05000063","s4rze5RZET4EY5wXY"],"dataSources":["P7SB4qiBxZPhjXYRW","ziFHh7RJJaJNc9iie","eoMYcQtZLjtLCGT3K"]}