@inproceedings{bb256200, AUTHOR = "Mujal, M. and Kirlin, R.L.", TITLE = "Compression enhancement of video motion of mouth region using joint audio and video coding", BOOKTITLE = Southwest02, YEAR = "2002", PAGES = "82-86", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251011"} @inproceedings{bb256201, AUTHOR = "Arya, A. and Hamidzadeh, B.", TITLE = "Talking Face: Using Facial Feature Detection and Image Transformations for Visual Speech", BOOKTITLE = ICIP01, YEAR = "2001", PAGES = "III: 943-946", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251012"} @inproceedings{bb256202, AUTHOR = "Potamianos, G. and Neti, C.", TITLE = "Improved ROI and Within Frame Discriminant Features for Lipreading", BOOKTITLE = ICIP01, YEAR = "2001", PAGES = "III: 250-253", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251013"} @inproceedings{bb256203, AUTHOR = "Kshirsagar, S. and Magnenat Thalmann, N.", TITLE = "Lip Synchronization Using Linear Predictive Analysis", BOOKTITLE = ICME00, YEAR = "2000", PAGES = "TP8", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251014"} @inproceedings{bb256204, AUTHOR = "Caplier, A. and Delmas, P. and Lam, D.", TITLE = "Robust Initialisation for Lips Edges Detection", BOOKTITLE = SCIA99, YEAR = "1999", PAGES = "Image Analysis", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251015"} @inproceedings{bb256205, AUTHOR = "Vanegas, O. and Tokuda, K. and Kitamura, T.", TITLE = "Location Normalization of HMM-Based Lip Reading: Experiments for the M2VTS Database", BOOKTITLE = ICIP99, YEAR = "1999", PAGES = "II:343-347", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251016"} @inproceedings{bb256206, AUTHOR = "Gao, L. and Mukaigawa, Y. and Ohta, Y.", TITLE = "Synthesis of Facial Images with Lip Motion from Several Real Views", BOOKTITLE = AFGR98, YEAR = "1998", PAGES = "181-186", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251017"} @inproceedings{bb256207, AUTHOR = "Kumar, V.P. and Oren, M. and Osuna, E. and Poggio, T.", TITLE = "Real Time Analysis and Tracking of Mouths for Expression Recognition", BOOKTITLE = DARPA98, YEAR = "1998", PAGES = "151-155", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251018"} @inproceedings{bb256208, AUTHOR = "Kumar, V.P. and Poggio, T.", TITLE = "Recognizing Expressions by Direct Estimation of the Parameters of a Pixel Morphable Model", BOOKTITLE = BMCV02, YEAR = "2002", PAGES = "519 ff.", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251019"} @inproceedings{bb256209, AUTHOR = "Kumar, V.P. and Poggio, T.", TITLE = "Learning-Based Approach to Estimation of Morphable Model Parameters", BOOKTITLE = "MIT AI Memo", YEAR = "2000", PAGES = "LMM", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251020"} @inproceedings{bb256210, AUTHOR = "Kumar, V.P.", TITLE = "Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis", BOOKTITLE = "MIT AI-TR", YEAR = "2002", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251021"} @inproceedings{bb256211, AUTHOR = "Kumar, V.P. and Poggio, T.", TITLE = "Learning-Based Approach to Real Time Tracking and Analysis of Faces", BOOKTITLE = AFGR00, YEAR = "2000", PAGES = "96-101", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251022"} @inproceedings{bb256212, AUTHOR = "Yu, K. and Jiang, X. and Bunke, H.", TITLE = "Automatic Lipreading of Sentences Combining Hidden Markov Models and Grammars", BOOKTITLE = AVBPA99, YEAR = "1999", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251023"} @inproceedings{bb256213, AUTHOR = "Baig, A.R. and Seguier, R. and Vaucher, G.", TITLE = "Image sequence analysis using a spatio-temporal coding for automatic lipreading", BOOKTITLE = CIAP99, YEAR = "1999", PAGES = "544-549", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251024"} @inproceedings{bb256214, AUTHOR = "Sridharan, S. and Wark, T.J. and Chandran, V.", TITLE = "An Approach to Statistical Lip Modelling for Speaker Identification via Chromatic Feature Extraction", BOOKTITLE = ICPR98, YEAR = "1998", PAGES = "Vol I: 123-125", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251025"} @inproceedings{bb256215, AUTHOR = "Wark, T.J. and Sridharan, S. and Chandran, V.", TITLE = "Robust Speaker Verification via Asynchronous Fusion of Speech and Lip Information", BOOKTITLE = AVBPA99, YEAR = "1999", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251026"} @inproceedings{bb256216, AUTHOR = "Potamianos, G. and Graf, H.P. and Cosatto, E.", TITLE = "An image transform approach for HMM based automatic lipreading", BOOKTITLE = ICIP98, YEAR = "1998", PAGES = "III: 173-177", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251027"} @inproceedings{bb256217, AUTHOR = "Jung, J.Y. and Kim, M.H.", TITLE = "Motion Estimation of Lips in Pronouncing Korean Vowels Based on Fuzzy Constraint Line Clustering", BOOKTITLE = ICIP96, YEAR = "1996", PAGES = "III: 507-510", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251028"} @inproceedings{bb256218, AUTHOR = "Bregler, C. and Omohundro, S.M.", TITLE = "Learning Visual Models for Lipreading", BOOKTITLE = MBR97, YEAR = "1997", PAGES = "Chapter 13", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251029"} @inproceedings{bb256219, AUTHOR = "Bregler, C. and Covell, M. and Slaney, M.", TITLE = "Video Rewrite: Driving Visual Speech with Audio", BOOKTITLE = "SIGGraph-97", YEAR = "1997", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251030"} @inproceedings{bb256220, AUTHOR = "Bregler, C. and Omohundro, S.", TITLE = "Nonlinear Manifold Learning for Visual Speech Recognition", BOOKTITLE = ICCV95, YEAR = "1995", PAGES = "494-499", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251031"} @inproceedings{bb256221, AUTHOR = "Stork, D.G. and Hennecke, M.E.", TITLE = "Speechreading: an overview of image processing, feature extraction, sensory integration and pattern recognition techniques", BOOKTITLE = AFGR96, YEAR = "1996", PAGES = "xvi-xxvi", BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT251032"} @article{bb256222, AUTHOR = "Wu, J.X. and Chan, C.", TITLE = "Recognition of phonetic labels of the TIMIT speech corpus by means of an artificial neural network", JOURNAL = PR, VOLUME = "24", YEAR = "1991", NUMBER = "11", PAGES = "1085-1091", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251033"} @article{bb256223, AUTHOR = "Wu, J.T. and Tamura, S. and Mitsumoto, H. and Kawai, H. and Kurosu, K. and Okazaki, K.", TITLE = "Neural network vowel-recognition jointly using voice features and mouth shape image", JOURNAL = PR, VOLUME = "24", YEAR = "1991", NUMBER = "10", PAGES = "921-927", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251034"} @article{bb256224, AUTHOR = "Lavagetto, F.", TITLE = "Time-Delay Neural Networks for Estimating Lip Movements from Speech Analysis: A Useful Tool in Audio Video Synchronization", JOURNAL = CirSysVideo, VOLUME = "7", YEAR = "1997", NUMBER = "5", MONTH = "October", PAGES = "786-800", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251035"} @article{bb256225, AUTHOR = "Movellan, J.R. and Mineiro, P.", TITLE = "Robust Sensor Fusion: Analysis and Application to Audio-Visual Speech Recognition", JOURNAL = MachLearn, VOLUME = "32", YEAR = "1998", NUMBER = "2", MONTH = "August", PAGES = "85-100", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251036"} @article{bb256226, AUTHOR = "Wachsmuth, S. and Socher, G. and Brandt Pook, H. and Kummert, F. and Sagerer, G.F.", TITLE = "Integration of Vision and Speech Understanding Using Bayesian Networks", JOURNAL = Videre, VOLUME = "1", YEAR = "2000", NUMBER = "4", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251037"} @inproceedings{bb256227, AUTHOR = "Wachsmuth, S. and Brandt Pook, H. and Socher, G. and Kummert, F. and Sagerer, G.F.", TITLE = "Multilevel Integration of Vision and Speech Understanding Using Bayesian Networks", BOOKTITLE = CVS99, YEAR = "1999", PAGES = "231 ff.", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251038"} @article{bb256228, AUTHOR = "Chien, J.T. and Lin, M.S.", TITLE = "Frame-synchronous noise compensation for hands-free speech recognition in car environments", JOURNAL = VISP, VOLUME = "147", YEAR = "2000", NUMBER = "6", MONTH = "December", PAGES = "508-515", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251039"} @article{bb256229, AUTHOR = "Patel, D. and Turner, L.F.", TITLE = "Effects of ATM network impairments on audio-visual broadcast applications", JOURNAL = VISP, VOLUME = "147", YEAR = "2000", NUMBER = "5", MONTH = "October", PAGES = "436-444", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251040"} @article{bb256230, AUTHOR = "Aleksic, P.S. and Williams, J.J. and Wu, Z.L. and Katsaggelos, A.K.", TITLE = "Audio-Visual Speech Recognition Using MPEG-4 Compliant Visual Features", JOURNAL = JASP, VOLUME = "2002", YEAR = "2002", NUMBER = "11", MONTH = "November", PAGES = "1213", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251041"} @inproceedings{bb256231, AUTHOR = "Aleksic, P.S. and Williams, J.J. and Wu, Z.L. and Katsaggelos, A.K.", TITLE = "Audio-visual continuous speech recognition using MPEG-4 compliant visual features", BOOKTITLE = ICIP02, YEAR = "2002", PAGES = "I: 960-963", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251042"} @article{bb256232, AUTHOR = "Aleksic, P.S. and Katsaggelos, A.K.", TITLE = "Audio-Visual Biometrics", JOURNAL = PIEEE, VOLUME = "94", YEAR = "2006", NUMBER = "11", MONTH = "November", PAGES = "2025-2044", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251043"} @article{bb256233, AUTHOR = "Aleksic, P.S. and Katsaggelos, A.K.", TITLE = "Speech-to-video synthesis using MPEG-4 compliant visual features", JOURNAL = CirSysVideo, VOLUME = "14", YEAR = "2004", NUMBER = "5", MONTH = "May", PAGES = "682-692", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251044"} @inproceedings{bb256234, AUTHOR = "Aleksic, P.S. and Katsaggelos, A.K.", TITLE = "Comparison of MPEG-4 Facial Animation Parameter Groups with Respect to Audio-Visual Speech Recognition Performance", BOOKTITLE = ICIP05, YEAR = "2005", PAGES = "III: 501-504", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251045"} @article{bb256235, AUTHOR = "Jiang, J.T. and Alwan, A. and Keating, P.A. and Auer, E.T. and Bernstein, L.E.", TITLE = "On the Relationship between Face Movements, Tongue Movements, and Speech Acoustics", JOURNAL = JASP, VOLUME = "2002", YEAR = "2002", NUMBER = "11", MONTH = "November", PAGES = "1174", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251046"} @article{bb256236, AUTHOR = "Sodoyer, D. and Schwartz, J.L. and Girin, L. and Klinkisch, J. and Jutten, C.", TITLE = "Separation of Audio-Visual Speech Sources: A New Approach Exploiting the Audio-Visual Coherence of Speech Stimuli", JOURNAL = JASP, VOLUME = "2002", YEAR = "2002", NUMBER = "11", MONTH = "November", PAGES = "1165", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251047"} @article{bb256237, AUTHOR = "Heckmann, M. and Berthommier, F. and Kroschel, K.", TITLE = "Noise Adaptive Stream Weighting in Audio-Visual Speech Recognition", JOURNAL = JASP, VOLUME = "2002", YEAR = "2002", NUMBER = "11", MONTH = "November", PAGES = "1260", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251048"} @article{bb256238, AUTHOR = "Nefian, A.V. and Liang, L.H. and Pi, X.B. and Liu, X.X. and Murphy, K.P.", TITLE = "Dynamic Bayesian Networks for Audio-Visual Speech Recognition", JOURNAL = JASP, VOLUME = "2002", YEAR = "2002", NUMBER = "11", MONTH = "November", PAGES = "1274", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251049"} @inproceedings{bb256239, AUTHOR = "Nefian, A.V. and Liang, L.H. and Fu, T.Y. and Liu, X.X.", TITLE = "A Bayesian Approach to Audio-Visual Speaker Identification", BOOKTITLE = AVBPA03, YEAR = "2003", PAGES = "761-769", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251050"} @article{bb256240, AUTHOR = "Patterson, E.K. and Gurbuz, S. and Tufekci, Z. and Gowdy, J.N.", TITLE = "Moving-Talker, Speaker-Independent Feature Study, and Baseline Results Using the CUAVE Multimodal Speech Corpus", JOURNAL = JASP, VOLUME = "2002", YEAR = "2002", NUMBER = "11", MONTH = "November", PAGES = "1189", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251051"} @inproceedings{bb256241, AUTHOR = "Gurbuz, S. and Patterson, E.K. and Tufekci, Z. and Gowdy, J.N.", TITLE = "Affine-Invariant Visual Features Contain Supplementary Information to Enhance Speech Recognition", BOOKTITLE = AVBPA01, YEAR = "2001", PAGES = "175", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251052"} @article{bb256242, AUTHOR = "Kalberer, G.A. and Muller, P. and Van Gool, L.J.", TITLE = "Visual speech, a trajectory in viseme space", JOURNAL = IJIST, VOLUME = "13", YEAR = "2003", NUMBER = "1", PAGES = "74-84", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251053"} @article{bb256243, AUTHOR = "Sharma, R. and Yeasin, M. and Krahnstoever, N. and Rauschert, I. and Cai, G. and Brewer, I. and MacEachren, A.M. and Sengupta, K.", TITLE = "Speech-gesture driven multimodal interfaces for crisis management", JOURNAL = PIEEE, VOLUME = "91", YEAR = "2003", NUMBER = "9", MONTH = "September", PAGES = "1327-1354", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251054"} @article{bb256244, AUTHOR = "Potamianos, G. and Neti, C. and Gravier, G. and Garg, A. and Senior, A.W.", TITLE = "Recent advances in the automatic recognition of audiovisual speech", JOURNAL = PIEEE, VOLUME = "91", YEAR = "2003", NUMBER = "9", MONTH = "September", PAGES = "1306-1326", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251055"} @article{bb256245, AUTHOR = "Kaynak, M.N. and Zhi, Q. and Cheok, A.D. and Sengupta, K. and Jian, Z. and Chung, K.C.", TITLE = "Analysis of Lip Geometric Features for Audio-Visual Speech Recognition", JOURNAL = SMC-A, VOLUME = "34", YEAR = "2004", NUMBER = "4", MONTH = "July", PAGES = "564-570", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251056"} @article{bb256246, AUTHOR = "Foo, S.W. and Lian, Y. and Dong, L.", TITLE = "Recognition of visual speech elements using adaptively boosted hidden Markov models", JOURNAL = CirSysVideo, VOLUME = "14", YEAR = "2004", NUMBER = "5", MONTH = "May", PAGES = "693-705", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251057"} @article{bb256247, AUTHOR = "Albiol, A. and Torres, L. and Delp, E.J.", TITLE = "Fully automatic face recognition system using a combined audio-visual approach", JOURNAL = VISP, VOLUME = "152", YEAR = "2005", NUMBER = "3", MONTH = "June", PAGES = "318-326", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251058"} @inproceedings{bb256248, AUTHOR = "Albiol, A. and Torres, L. and Delp, E.J.", TITLE = "A Fast Anchor Person Searching Scheme in News Sequences", BOOKTITLE = AVBPA01, YEAR = "2001", PAGES = "366", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251059"} @inproceedings{bb256249, AUTHOR = "Albiol, A. and Torres, L. and Delp, E.J.", TITLE = "An Unsupervised Color Image Segmentation Algorithm for Face Detection Applications", BOOKTITLE = ICIP01, YEAR = "2001", PAGES = "II: 681-684", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251060"} @inproceedings{bb256250, AUTHOR = "Albiol, A. and Torres, L. and Delp, E.J.", TITLE = "Optimum Color Spaces for Skin Detection", BOOKTITLE = ICIP01, YEAR = "2001", PAGES = "I: 122-124", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251061"} @article{bb256251, AUTHOR = "Kleindienst, J. and Macek, T. and Seredi, L. and Sedivy, J.", TITLE = "Interaction framework for home environment using speech and vision", JOURNAL = IVC, VOLUME = "25", YEAR = "2007", NUMBER = "12", MONTH = "December", PAGES = "1836-1847", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251062"} @inproceedings{bb256252, AUTHOR = "Kleindienst, J. and Macek, T. and Seredi, L. and Sedivy, J.", TITLE = "Djinn: Interaction Framework for Home Environment Using Speech and Vision", BOOKTITLE = CVHCI04, YEAR = "2004", PAGES = "153-164", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251063"} @article{bb256253, AUTHOR = "Palanivel, S. and Yegnanarayana, B.", TITLE = "Multimodal person authentication using speech, face and visual speech", JOURNAL = CVIU, VOLUME = "109", YEAR = "2008", NUMBER = "1", MONTH = "January", PAGES = "44-55", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251064"} @article{bb256254, AUTHOR = "Chetty, G. and Wagner, M.", TITLE = "Robust face-voice based speaker identity verification using multilevel fusion", JOURNAL = IVC, VOLUME = "26", YEAR = "2008", NUMBER = "9", MONTH = "September", PAGES = "1249-1260", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251065"} @inproceedings{bb256255, AUTHOR = "Chetty, G. and Wagner, M.", TITLE = "Audio Visual Speaker Verification Based on Hybrid Fusion of Cross Modal Features", BOOKTITLE = PReMI07, YEAR = "2007", PAGES = "469-478", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251066"} @inproceedings{bb256256, AUTHOR = "Chetty, G. and Wagner, M.", TITLE = "Face-Voice Authentication Based on 3D Face Models", BOOKTITLE = ACCV06, YEAR = "2006", PAGES = "I:559-568", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251067"} @article{bb256257, AUTHOR = "Delakis, M. and Gravier, G. and Gros, P.", TITLE = "Audiovisual integration with Segment Models for tennis video parsing", JOURNAL = CVIU, VOLUME = "111", YEAR = "2008", NUMBER = "2", MONTH = "August", PAGES = "142-154", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251068"} @article{bb256258, AUTHOR = "Gravier, G. and Guinaudeau, C. and Lecorve, G. and Sebillot, P.", TITLE = "Exploiting Speech for Automatic TV Delinearization: From Streams to Cross-Media Semantic Navigation", JOURNAL = JIVP, VOLUME = "2011", YEAR = "2011", NUMBER = "2011", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251069"} @article{bb256259, AUTHOR = "Vajaria, H. and Sankar, R. and Kasturi, R.", TITLE = "Exploring Co-Occurence Between Speech and Body Movement for Audio-Guided Video Localization", JOURNAL = CirSysVideo, VOLUME = "18", YEAR = "2008", NUMBER = "11", MONTH = "November", PAGES = "1608-1617", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251070"} @inproceedings{bb256260, AUTHOR = "Vajaria, H. and Islam, T. and Sarkar, S. and Sankar, R. and Kasturi, R.", TITLE = "Audio Segmentation and Speaker Localization in Meeting Videos", BOOKTITLE = ICPR06, YEAR = "2006", PAGES = "II: 1150-1153", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251071"} @article{bb256261, AUTHOR = "Hospedales, T.M. and Vijayakumar, S.", TITLE = "Structure Inference for Bayesian Multisensory Scene Understanding", JOURNAL = PAMI, VOLUME = "30", YEAR = "2008", NUMBER = "12", MONTH = "December", PAGES = "2140-2157", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251072"} @article{bb256262, AUTHOR = "Liu, Z.C. and Cohen, M. and Bhatnagar, D. and Cutler, R. and Zhang, Z.Y.", TITLE = "Head-Size Equalization for Improved Visual Perception in Video Conferencing", JOURNAL = MultMed, VOLUME = "9", YEAR = "2007", NUMBER = "7", MONTH = "November", PAGES = "1520-1527", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251073"} @inproceedings{bb256263, AUTHOR = "Liu, Z.C. and Cutler, R. and Cohen, M. and Zhang, Z.Y.", TITLE = "System and method for head size equalization in 360 degree panoramic images", BOOKTITLE = US_Patent, YEAR = "2007", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251074"} @inproceedings{bb256264, AUTHOR = "Cutler, R.", TITLE = "User interface for a system and method for head size equalization in 360 degree panoramic images", BOOKTITLE = US_Patent, YEAR = "2006", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251075"} @inproceedings{bb256265, AUTHOR = "Cutler, R. and Kapoor, A.", TITLE = "System and method for audio/video speaker detection", BOOKTITLE = US_Patent, YEAR = "2008", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251076"} @article{bb256266, AUTHOR = "Heracleous, P. and Aboutabit, N. and Beautemps, D.", TITLE = "Lip Shape and Hand Position Fusion for Automatic Vowel Recognition in Cued Speech for French", JOURNAL = SPLetters, VOLUME = "16", YEAR = "2009", NUMBER = "5", MONTH = "May", PAGES = "339-342", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251077"} @article{bb256267, AUTHOR = "Zhang, C. and Yin, P. and Rui, Y. and Cutler, R. and Viola, P. and Sun, X.D. and Pinto, N. and Zhang, Z.Y.", TITLE = "Boosting-Based Multimodal Speaker Detection for Distributed Meeting Videos", JOURNAL = MultMed, VOLUME = "10", YEAR = "2008", NUMBER = "8", MONTH = "December", PAGES = "1541-1552", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251078"} @article{bb256268, AUTHOR = "Lee, J.S. and Park, C.H.", TITLE = "Robust Audio-Visual Speech Recognition Based on Late Integration", JOURNAL = MultMed, VOLUME = "10", YEAR = "2008", NUMBER = "5", MONTH = "August", PAGES = "767-779", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251079"} @article{bb256269, AUTHOR = "Saenko, K. and Livescu, K. and Glass, J. and Darrell, T.J.", TITLE = "Multistream Articulatory Feature-Based Models for Visual Speech Recognition", JOURNAL = PAMI, VOLUME = "31", YEAR = "2009", NUMBER = "9", MONTH = "September", PAGES = "1700-1707", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251080"} @inproceedings{bb256270, AUTHOR = "Saenko, K. and Livescu, K. and Siracusa, M. and Wilson, K. and Glass, J. and Darrell, T.J.", TITLE = "Visual Speech Recognition with Loosely Synchronized Feature Streams", BOOKTITLE = ICCV05, YEAR = "2005", PAGES = "II: 1424-1431", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251081"} @article{bb256271, AUTHOR = "Schuller, B. and Muller, R. and Eyben, F. and Gast, J. and Hornler, B. and Wollmer, M. and Rigoll, G. and Hothker, A. and Konosu, H.", TITLE = "Being bored? Recognising natural interest by extensive audiovisual integration for real-life application", JOURNAL = IVC, VOLUME = "27", YEAR = "2009", NUMBER = "12", MONTH = "November", PAGES = "1760-1774", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251082"} @inproceedings{bb256272, AUTHOR = "Eyben, F. and Wollmer, M. and Valstar, M.F. and Gunes, H. and Schuller, B. and Pantic, M.", TITLE = "String-based audiovisual fusion of behavioural events for the assessment of dimensional affect", BOOKTITLE = FG11, YEAR = "2011", PAGES = "322-329", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251083"} @inproceedings{bb256273, AUTHOR = "Althoff, F. and McGlaun, G. and Lang, M.K. and Rigoll, G.", TITLE = "Evaluating Multimodal Interaction Patterns in Various Application Scenarios", BOOKTITLE = GW03, YEAR = "2003", PAGES = "421-435", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251084"} @article{bb256274, AUTHOR = "Casanovas, A.L. and Monaci, G. and Vandergheynst, P. and Gribonval, R.", TITLE = "Blind Audiovisual Source Separation Based on Sparse Redundant Representations", JOURNAL = MultMed, VOLUME = "12", YEAR = "2010", NUMBER = "5", PAGES = "358-371", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251085"} @inproceedings{bb256275, AUTHOR = "Casanovas, A.L. and Monaci, G. and Vandergheynst, P.", TITLE = "Blind Audiovisual Source Separation using Sparse Representations", BOOKTITLE = ICIP07, YEAR = "2007", PAGES = "III: 301-304", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251086"} @article{bb256276, AUTHOR = "Esch, J.", TITLE = "Audiovisual Information Fusion in Human-Computer Interfaces and Intelligent Environments: A Survey", JOURNAL = PIEEE, VOLUME = "98", YEAR = "2010", NUMBER = "10", MONTH = "October", PAGES = "1690-1691", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251087"} @article{bb256277, AUTHOR = "Shivappa, S.T. and Trivedi, M.M. and Rao, B.D.", TITLE = "Audiovisual Information Fusion in Human-Computer Interfaces and Intelligent Environments: A Survey", JOURNAL = PIEEE, VOLUME = "98", YEAR = "2010", NUMBER = "10", MONTH = "October", PAGES = "1692-1715", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251088"} @article{bb256278, AUTHOR = "Claussen, H. and Rosca, J. and Damper, R.I.", TITLE = "Signature extraction using mutual interdependencies", JOURNAL = PR, VOLUME = "44", YEAR = "2011", NUMBER = "3", MONTH = "March", PAGES = "650-661", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251089"} @inproceedings{bb256279, AUTHOR = "Higgins, J.E. and Damper, R.I.", TITLE = "An HMM-Based Subband Processing Approach to Speaker Identification", BOOKTITLE = AVBPA01, YEAR = "2001", PAGES = "169", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251090"} @article{bb256280, AUTHOR = "El Sallam, A.A. and Mian, A.S.", TITLE = "Correlation based speech-video synchronization", JOURNAL = PRL, VOLUME = "32", YEAR = "2011", NUMBER = "6", MONTH = "April", PAGES = "780-786", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251091"} @inproceedings{bb256281, AUTHOR = "El Sallam, A.A. and Mian, A.S.", TITLE = "Speech-Video Synchronization Using Lips Movements and Speech Envelope Correlation", BOOKTITLE = ICIAR09, YEAR = "2009", PAGES = "397-407", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251092"} @article{bb256282, AUTHOR = "Petridis, S. and Pantic, M.", TITLE = "Audiovisual Discrimination Between Speech and Laughter: Why and When Visual Information Might Help", JOURNAL = MultMed, VOLUME = "13", YEAR = "2011", NUMBER = "2", PAGES = "216-234", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251093"} @article{bb256283, AUTHOR = "Petridis, S. and Pantic, M.", TITLE = "Prediction-Based Audiovisual Fusion for Classification of Non-Linguistic Vocalisations", JOURNAL = AffCom, VOLUME = "7", YEAR = "2016", NUMBER = "1", MONTH = "January", PAGES = "45-58", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251094"} @inproceedings{bb256284, AUTHOR = "Petridis, S. and Pantic, M.", TITLE = "Fusion of audio and visual cues for laughter detection", BOOKTITLE = CIVR08, YEAR = "2008", PAGES = "329-338", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251095"} @inproceedings{bb256285, AUTHOR = "Petridis, S. and Pantic, M. and Cohn, J.F.", TITLE = "Prediction-based classification for audiovisual discrimination between laughter and speech", BOOKTITLE = FG11, YEAR = "2011", PAGES = "619-626", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251096"} @article{bb256286, AUTHOR = "Moustakas, K. and Tzovaras, D. and Dybkjaer, L. and Bernsen, N. and Aran, O.", TITLE = "Using Modality Replacement to Facilitate Communication between Visually and Hearing-Impaired People", JOURNAL = MultMedMag, VOLUME = "18", YEAR = "2011", NUMBER = "2", MONTH = "April", PAGES = "26-37", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251097"} @article{bb256287, AUTHOR = "Tariquzzaman, M. and Kim, J.Y. and Na, S.Y. and Kim, H.G. and Har, D.S.", TITLE = "A Visual Signal Reliability for Robust Audio-Visual Speaker Identification", JOURNAL = IEICE, VOLUME = "E94-D", YEAR = "2011", NUMBER = "10", MONTH = "October", PAGES = "2052-2055", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251098"} @article{bb256288, AUTHOR = "Lee, J.S. and de Simone, F. and Ebrahimi, T.", TITLE = "Efficient video coding based on audio-visual focus of attention", JOURNAL = JVCIR, VOLUME = "22", YEAR = "2011", NUMBER = "8", MONTH = "November", PAGES = "704-711", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251099"} @article{bb256289, AUTHOR = "Tiawongsombat, P. and Jeong, M.H. and Yun, J.S. and You, B.J. and Oh, S.R.", TITLE = "Robust visual speakingness detection using bi-level HMM", JOURNAL = PR, VOLUME = "45", YEAR = "2012", NUMBER = "2", MONTH = "February", PAGES = "783-793", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251100"} @article{bb256290, AUTHOR = "Noulas, A. and Englebienne, G. and Krose, B.J.A.", TITLE = "Multimodal Speaker Diarization", JOURNAL = PAMI, VOLUME = "34", YEAR = "2012", NUMBER = "1", MONTH = "January", PAGES = "79-93", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251101"} @article{bb256291, AUTHOR = "Blauth, D.A. and Minotto, V.P. and Jung, C.R. and Lee, B. and Kalker, T.", TITLE = "Voice activity detection and speaker localization using audiovisual cues", JOURNAL = PRL, VOLUME = "33", YEAR = "2012", NUMBER = "4", MONTH = "March", PAGES = "373-380", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251102"} @inproceedings{bb256292, AUTHOR = "Montazzolli, S. and Jung, C.R. and Gelb, D.", TITLE = "Audiovisual voice activity detection using off-the-shelf cameras", BOOKTITLE = ICIP15, YEAR = "2015", PAGES = "3886-3890", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251103"} @article{bb256293, AUTHOR = "Minotto, V.P. and Jung, C.R. and Lee, B.", TITLE = "Simultaneous-Speaker Voice Activity Detection and Localization Using Mid-Fusion of SVM and HMMs", JOURNAL = MultMed, VOLUME = "16", YEAR = "2014", NUMBER = "4", MONTH = "June", PAGES = "1032-1044", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251104"} @article{bb256294, AUTHOR = "Minotto, V.P. and Jung, C.R. and Lee, B.", TITLE = "Multimodal Multi-Channel On-Line Speaker Diarization Using Sensor Fusion Through SVM", JOURNAL = MultMed, VOLUME = "17", YEAR = "2015", NUMBER = "10", MONTH = "October", PAGES = "1694-1705", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251105"} @article{bb256295, AUTHOR = "Nicolaou, M.A. and Gunes, H. and Pantic, M.", TITLE = "Output-associative RVM regression for dimensional and continuous emotion prediction", JOURNAL = IVC, VOLUME = "30", YEAR = "2012", NUMBER = "3", MONTH = "March", PAGES = "186-196", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251106"} @inproceedings{bb256296, AUTHOR = "Pantic, M. and Gunes, H. and Nicolaou, M.A.", TITLE = "Output-associative RVM regression for dimensional and continuous emotion prediction", BOOKTITLE = FG11, YEAR = "2011", PAGES = "16-23", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251106"} @inproceedings{bb256297, AUTHOR = "Nicolaou, M.A. and Gunes, H. and Pantic, M.", TITLE = "Designing frameworks for automatic affect prediction and classification in dimensional space", BOOKTITLE = Gesture11, YEAR = "2011", PAGES = "20-26", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251107"} @article{bb256298, AUTHOR = "Nicolaou, M.A. and Gunes, H. and Pantic, M.", TITLE = "Continuous Prediction of Spontaneous Affect from Multiple Cues and Modalities in Valence-Arousal Space", JOURNAL = AffCom, VOLUME = "2", YEAR = "2011", NUMBER = "2", PAGES = "92-105", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251108"} @inproceedings{bb256299, AUTHOR = "Nicolaou, M.A. and Gunes, H. and Pantic, M.", TITLE = "Audio-Visual Classification and Fusion of Spontaneous Affective Data in Likelihood Space", BOOKTITLE = ICPR10, YEAR = "2010", PAGES = "3695-3699", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251109"}