{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:40:30Z","timestamp":1761648030066},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,1,25]],"date-time":"2013-01-25T00:00:00Z","timestamp":1359072000000},"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":[[2014,5]]},"DOI":"10.1007\/s11042-012-1352-1","type":"journal-article","created":{"date-parts":[[2013,1,24]],"date-time":"2013-01-24T11:37:41Z","timestamp":1359027461000},"page":"495-523","source":"Crossref","is-referenced-by-count":28,"title":["Robust semi-automatic head pose labeling for real-world face video sequences"],"prefix":"10.1007","volume":"70","author":[{"given":"Meltem","family":"Demirkus","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James J.","family":"Clark","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tal","family":"Arbel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,1,25]]},"reference":[{"key":"1352_CR1","doi-asserted-by":"crossref","unstructured":"Aghajanian J, Prince S (2009) Face pose estimation in uncontrolled environments. In: Proceedings of the British Machine Vision Conference. pp 1\u201311","DOI":"10.5244\/C.23.76"},{"key":"1352_CR2","doi-asserted-by":"crossref","unstructured":"Ahn L, Liu R, Blum M (2006) Peekaboom: A game for locating objects in images. In: Proceedings of the SIGCHI conference on Human Factors in computing system pp 55\u201364. doi: 10.1145\/1124772.1124782","DOI":"10.1145\/1124772.1124782"},{"key":"1352_CR3","doi-asserted-by":"crossref","unstructured":"Ambardekar A, Nicolescu M, Dascalu S (2009) Ground Truth Verification Tool (GTVT) for Video Surveillance Systems. In: Proceedings of the Second International Conferences on Advances in Computer-Human Interactions. doi: 10.1109\/ACHI.2009.17","DOI":"10.1109\/ACHI.2009.17"},{"key":"1352_CR4","doi-asserted-by":"crossref","unstructured":"Ballerini L (2003) Multiple Genetic Snakes for People Segmentation in Video Sequences. In: Proceedings of the 13th Scandinavian conference on Image analysis pp 275\u2013282","DOI":"10.1007\/3-540-45103-X_38"},{"key":"1352_CR5","doi-asserted-by":"crossref","unstructured":"Bederson BB (2001) Photomesa: A zoomable image browser using quantum treemaps and bubblemaps. In: Proceedings of the annual ACM symposium on User interface software and technology, pp 71\u201380. doi: 10.1145\/502348.502359","DOI":"10.1145\/502348.502359"},{"key":"1352_CR6","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1162\/089976603321780317","volume":"15","author":"M Belkin","year":"2003","unstructured":"Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15:1373\u20131396. doi: 10.1162\/089976603321780317","journal-title":"Neural Comput"},{"key":"1352_CR7","first-page":"1158","volume":"2","author":"ST Birchfield","year":"2005","unstructured":"Birchfield ST, Rangarajan S (2005) Spatiograms versus histograms for region-based tracking. Proc IEEE Conf Comput Vis Pattern Recognit 2:1158\u20131163","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"1352_CR8","first-page":"454","volume":"2","author":"V Blanz","year":"2005","unstructured":"Blanz V, Grother P, Vetter T (2005) Face recognition based on frontal views generated from non-frontal images. Proc IEEE Conf Comput Vis Pattern Recognit 2:454\u2013461. doi: 10.1109\/CVPR.2005.150","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"1352_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/19416521003654160","volume":"4","author":"SJ Blunsden","year":"2010","unstructured":"Blunsden SJ, Fisher RB (2010) The BEHAVE video dataset: ground truthed video for multi-person behavior classification. Ann BMVA 4:1\u201312","journal-title":"Ann BMVA"},{"issue":"9","key":"1352_CR10","doi-asserted-by":"crossref","first-page":"1980","DOI":"10.1016\/j.patcog.2010.07.022","volume":"44","author":"BJ Boom","year":"2011","unstructured":"Boom BJ, Spreeuwers LJ, Veldhuis RNJ (2011) Virtual illumination grid for correction of uncontrolled illumination in facial images. Pattern Recog 44(9):1980\u20131989. doi: 10.1016\/j.patcog.2010.07.022","journal-title":"Pattern Recog"},{"issue":"4","key":"1352_CR11","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/TPAMI.2007.70716","volume":"30","author":"A Bosch","year":"2008","unstructured":"Bosch A, Zisserman A, Mu\u00f1oz X (2008) Scene classification using a hybrid generative\/discriminative approach. IEEE Trans Pattern Anal Mach Intell 30(4):712\u2013727. doi: 10.1109\/TPAMI.2007.70716","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"1352_CR12","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.patcog.2009.03.024","volume":"43","author":"P Bruneau","year":"2010","unstructured":"Bruneau P, Picarougne F, Gelgon M (2010) Interactive unsupervised classification and visualization for browsing an image collection. Pattern Recog 43(2):485\u2013493. doi: 10.1016\/j.patcog.2009.03.024","journal-title":"Pattern Recog"},{"key":"1352_CR13","doi-asserted-by":"crossref","unstructured":"Chen Y, Han C, Wang C, Jeng B, Fan K. A CNN-Based Face Detector with a Simple Feature Map and a Coarse-to-fine Classifier. Accepted for IEEE Trans on Pattern Analysis and Machine Intelligence. doi: 10.1109\/TPAMI.2007.70798","DOI":"10.1109\/TPAMI.2007.70798"},{"key":"1352_CR14","unstructured":"Color FERET face database (2003) http:\/\/www.nist.gov\/itl\/iad\/ig\/feret.cfm . Accessed 1 June 2012"},{"key":"1352_CR15","unstructured":"Delezoide B, Precioso F, Redi M, Merialdo B, Granjon L, Pellerin D, Rombaut M, J\u00e9gou H, Vieux R, Mansencal B, Benois-Pineau J et al. (2011) IRIM at TRECVID 2011: Semantic Indexing and Instance Search. In: Proceedings of TREC Video Retrieval Evaluation Online"},{"key":"1352_CR16","doi-asserted-by":"crossref","unstructured":"Demirkus M, Oreshkin B, Clark J, Arbel T (2011) Spatial and probabilistic codebook template based head pose estimation from unconstrained environments. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), pp 573\u2013576","DOI":"10.1109\/ICIP.2011.6116613"},{"key":"1352_CR17","doi-asserted-by":"crossref","unstructured":"Demirkus M, Precup D, Clark J, Arbel T (2012) Soft Biometric Trait Classification from Real-world Face Videos Conditioned on Head Pose Estimation. In: Proceedings of the IEEE Computer Society Workshop on Biometrics in association with the IEEE Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPRW.2012.6239227"},{"key":"1352_CR18","unstructured":"Dhall A, Goecke R, Lucey S, Gedeon T (2012) A semi-automatic method for collecting richly labelled large facial expression databases from movies. IEEE Multimedia (99):1. URL: http:\/\/doi.ieeecomputersociety.org\/10.1109\/MMUL.2012.26"},{"key":"1352_CR19","doi-asserted-by":"crossref","unstructured":"Doerman D, Mihalcik D (2000) Tools and techniques for video performance evaluation. In: Proceedings of International Conference on Pattern Recognition 4:167:170","DOI":"10.1109\/ICPR.2000.902888"},{"key":"1352_CR20","unstructured":"Furht B, Marques O (2003) Handbook of video databases: Design and applications. CRC Press. http:\/\/www.crcpress.com\/ecommerce_product\/product_detail.jsf?catno=7006&isbn=0000000000000&parent_id=441&pc=http:\/\/flylib.com\/books\/en\/2.495.1.3\/1\/"},{"key":"1352_CR21","unstructured":"Gao W, Cao B, Shan SG (2004) The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations. Technical report of JDL"},{"key":"1352_CR22","doi-asserted-by":"crossref","unstructured":"Giro-i-Nieto X, Martos M (2012) Multiscale annotation of still images with GAT In: Proceedings of the First International Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications. doi: 10.1145\/2304496.2304497","DOI":"10.1145\/2304496.2304497"},{"issue":"5","key":"1352_CR23","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1016\/j.imavis.2009.08.002","volume":"28","author":"R Gross","year":"2009","unstructured":"Gross R, Matthews I, Cohn JF, Kanade T, Baker S (2009) Multi-PIE. Image Vis Comput 28(5):807\u2013813. doi: 10.1016\/j.imavis.2009.08.002","journal-title":"Image Vis Comput"},{"key":"1352_CR24","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1007\/978-3-540-69423-6_57","volume":"1","author":"H Hacid","year":"2006","unstructured":"Hacid H (2006) Neighborhood graphs for semi-automatic annotation of large image databases. Adv Multimedia Model 1:586\u2013595. doi: 10.1007\/978-3-540-69423-6_57","journal-title":"Adv Multimedia Model"},{"key":"1352_CR25","doi-asserted-by":"crossref","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten I H (2009) The WEKA Data Mining Software. An Update, SIGKDD Explorations 11(1)","DOI":"10.1145\/1656274.1656278"},{"key":"1352_CR26","doi-asserted-by":"crossref","unstructured":"He J, Rijke M, Sevenster M, Ommering RV, Qian Y (2011) Generation to Backgroun Knowledge: A Case Study in Annotating Radiology Reports. In: Proceedings of the 20th ACM Conference on Information and Knowledge Management pp 1867\u20131876. doi: 10.1145\/2063576.2063845","DOI":"10.1145\/2063576.2063845"},{"key":"1352_CR27","first-page":"693","volume":"7131","author":"M Hildebrand","year":"2012","unstructured":"Hildebrand M, van Ossenbruggen J (2012) Linking user-generated video annotations to the web of data. Proc Int Conf Multimed Model 7131:693\u2013704. doi: 10.1007\/978-3-642-27355-1_74","journal-title":"Proc Int Conf Multimed Model"},{"issue":"10","key":"1352_CR28","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1016\/j.ijhcs.2009.07.008","volume":"67","author":"M Hildebrand","year":"2009","unstructured":"Hildebrand M, van Ossenbruggen JR, Hardman L, Jacobs G (2009) Supporting subject matter annotation using heterogeneous thesauri: a user study in web data reuse. Int J Hum Comput Stud 67(10):888\u2013903. doi: 10.1016\/j.ijhcs.2009.07.008 , doi: 10.1016\/2Fj.ijhcs.2009.07.008","journal-title":"Int J Hum Comput Stud"},{"key":"1352_CR29","unstructured":"Huang GB, Ramesh M, Berg T, Learned-Miller E (2007) Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. University of Massachusetts, Amherst, Technical Report 07-49"},{"key":"1352_CR30","doi-asserted-by":"crossref","unstructured":"Jones M, Rehg JM (2002) Statistical color models with application to skin detection. Int J Comput Vis 81\u201396. doi: 10.1023\/A:1013200319198","DOI":"10.1023\/A:1013200319198"},{"key":"1352_CR31","doi-asserted-by":"crossref","unstructured":"Karaman S, Benois-Pineau J, M\u00e9gret R, Bugeau A (2012) Multi-layer local graph words for object recognition. Advances in Multimedia Modeling 29\u201339","DOI":"10.1007\/978-3-642-27355-1_6"},{"key":"1352_CR32","doi-asserted-by":"crossref","unstructured":"Kavasidis I, Palazzo S, Salvo RD, Giordano D, Spampinato C (2012) A Semi-automatic Tool for Detection and Tracking Ground Truth Generation in Videos. In: Proceedings of the First Int. Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications. doi: 10.1145\/2304496.2304502","DOI":"10.1145\/2304496.2304502"},{"key":"1352_CR33","doi-asserted-by":"crossref","unstructured":"Kumar N, Berg AC, Belhumeur PN, Nayar SK (2009) Attribute and Simila Classifiers for Face Verification. In: Proceedings of the International Conference on Computer Vision pp 365\u2013372. doi: 10.1109\/ICCV.2009.5459250","DOI":"10.1109\/ICCV.2009.5459250"},{"key":"1352_CR34","doi-asserted-by":"crossref","first-page":"1962","DOI":"10.1109\/TPAMI.2011.48","volume":"33","author":"N Kumar","year":"2011","unstructured":"Kumar N, Berg A, Belhumeur P, Nayar S (2011) Describable visual attributes for face verification and image search. IEEE Trans Pattern Anal Mach Intell 33:1962\u20131977. doi: 10.1109\/TPAMI.2011.48","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1352_CR35","first-page":"2169","volume":"2","author":"S Lazebnik","year":"2006","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. Proc IEEE Comput Vis Pattern Recognit 2:2169\u20132178","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"1352_CR36","unstructured":"Lin C, Tseng BL, Smith JR (2003) Video collaborative annotation forum: Establishing ground-truth labels on large multimedia datasets. In: Proceedings of the TRECVID Workshop"},{"issue":"2","key":"1352_CR37","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110. doi: 10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int J Comput Vis"},{"key":"1352_CR38","unstructured":"McGill Real-World Face Video Database (2012) http:\/\/www.cim.mcgill.ca\/~rfvdb . Accessed 10 Nov 2012"},{"key":"1352_CR39","doi-asserted-by":"crossref","unstructured":"Mezaris V, Dimou A, Kompatsiaris I (2010) On the use of feature tracks for dynamic concept detection in video. In: Proceedings of IEEE International Conference on Image Processing pp 4697\u20134700","DOI":"10.1109\/ICIP.2010.5653867"},{"key":"1352_CR40","doi-asserted-by":"crossref","unstructured":"Moehrmann J, Heidemann G (2012) Efficient annotation of image data sets for computer vision applications. In: Proceedings of the First International Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications. doi: 10.1145\/2304496.2304498","DOI":"10.1145\/2304496.2304498"},{"issue":"4","key":"1352_CR41","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1109\/TPAMI.2008.106","volume":"31","author":"E Murphy-Chutorian","year":"2009","unstructured":"Murphy-Chutorian E, Trivedi MM (2009) Head pose estimation in computer vision: a survey. IEEE Trans Pattern Anal Mach Intell 31(4):607\u2013626. doi: 10.1109\/TPAMI.2008.106","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1352_CR42","first-page":"947","volume":"1","author":"PJ Phillips","year":"2005","unstructured":"Phillips PJ, Flynn PJ, Scruggs T, Bowyer KW, Chang J, Hoffman, Marques J, Min J, Worek W (2005) Overview of the face recognition grand challenge. Proc IEEE Conf Comput Vis Pattern Recognit 1:947\u2013954. doi: 10.1109\/CVPR.2005.268","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"1352_CR43","doi-asserted-by":"crossref","unstructured":"Shi J, Tomasi C (1994) Good Features to Track. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp 593\u2013600. doi: 10.1109\/CVPR.1994.323794","DOI":"10.1109\/CVPR.1994.323794"},{"key":"1352_CR44","doi-asserted-by":"crossref","unstructured":"Shneiderman B, Kang H (2000) Direct annotation: A drag-and-drop strategy for labeling photos. In: Proceedings of the IEEE Conference on Information Visualization pp 88\u201395","DOI":"10.1109\/IV.2000.859742"},{"key":"1352_CR45","doi-asserted-by":"crossref","unstructured":"Spampinato C, Boom B, He J (2012) First International Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications","DOI":"10.1145\/2254556.2254727"},{"issue":"9","key":"1352_CR46","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1109\/TPAMI.2008.233","volume":"31","author":"M Toews","year":"2009","unstructured":"Toews M, Arbel T (2009) Detection, localization and sex classification of faces from arbitrary viewpoints and under occlusion. IEEE Trans Pattern Anal Mach Intell 31(9):1567\u20131581, http:\/\/doi.ieeecomputersociety.org\/10.1109\/TPAMI.2008.233","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1352_CR47","doi-asserted-by":"crossref","unstructured":"Torki M, Elgammal AM (2011) Regression from local features for viewpoint and pose estimation. In: Proceedings of the International Conference on Computer Vision pp 2603\u20132610 URL: http:\/\/doi.ieeecomputersociety.org\/10.1109\/ICCV.2011.6126549","DOI":"10.1109\/ICCV.2011.6126549"},{"key":"1352_CR48","doi-asserted-by":"crossref","unstructured":"Volkmer T, Smith JR, Natsev AP (2005) A web-based system for collaborative annotation of large image and video collections: An evaluation and user study. In: Proceedings of the 13th annual ACM international conference on Multimedia. doi: 10.1145\/1101149.1101341","DOI":"10.1145\/1101149.1101341"},{"key":"1352_CR49","doi-asserted-by":"crossref","unstructured":"Weston J, Ratle F, Collobert R (2008) Deep learning via semi-supervised embedding. In: Proceedings of the 25th International Conference on Machine Learning pp 1168\u20131175. doi: 10.1145\/1390156.1390303","DOI":"10.1145\/1390156.1390303"},{"issue":"3","key":"1352_CR50","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.1109\/TIP.2011.2169269","volume":"21","author":"Y Yang","year":"2012","unstructured":"Yang Y, Wu F, Nie F, Shen HT, Zhuang Y, Hauptmann AG (2012) Web and personal image annotation by mining label correlation with relaxed visual graph embedding. IEEE Trans Image Process 21(3):1339\u20131351. doi: 10.1109\/TIP.2011.2169269","journal-title":"IEEE Trans Image Process"},{"key":"1352_CR51","unstructured":"Zhou SK, Chellappa R, Zhao W (2005) Unconstrained face recognition. Springer. http:\/\/scholar.google.ca\/citations?view_op=view_citation&hl=en&user=8eNm2GMAAAAJ&citation_for_view=8eNm2GMAAAAJ:8k81kl-MbHgC"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1352-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-012-1352-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1352-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,8]],"date-time":"2019-07-08T21:03:12Z","timestamp":1562619792000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-012-1352-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1,25]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,5]]}},"alternative-id":["1352"],"URL":"https:\/\/doi.org\/10.1007\/s11042-012-1352-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,1,25]]}}}