@article{bb259400, 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#TT254193"} @article{bb259401, 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#TT254194"} @article{bb259402, 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#TT254195"} @article{bb259403, 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#TT254196"} @inproceedings{bb259404, 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#TT254197"} @article{bb259405, 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#TT254198"} @article{bb259406, 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#TT254199"} @article{bb259407, 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#TT254200"} @inproceedings{bb259408, 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#TT254201"} @article{bb259409, 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#TT254202"} @article{bb259410, 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#TT254203"} @inproceedings{bb259411, 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#TT254204"} @article{bb259412, 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#TT254205"} @article{bb259413, 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#TT254206"} @article{bb259414, 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#TT254207"} @article{bb259415, 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#TT254208"} @inproceedings{bb259416, 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#TT254209"} @article{bb259417, 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#TT254210"} @inproceedings{bb259418, 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#TT254211"} @article{bb259419, 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#TT254212"} @article{bb259420, 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#TT254213"} @article{bb259421, 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#TT254214"} @article{bb259422, 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#TT254215"} @article{bb259423, 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#TT254216"} @article{bb259424, 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#TT254217"} @inproceedings{bb259425, 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#TT254218"} @inproceedings{bb259426, 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#TT254219"} @inproceedings{bb259427, 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#TT254220"} @article{bb259428, 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#TT254221"} @inproceedings{bb259429, 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#TT254222"} @article{bb259430, 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#TT254223"} @article{bb259431, 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#TT254224"} @inproceedings{bb259432, 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#TT254225"} @inproceedings{bb259433, 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#TT254226"} @article{bb259434, 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#TT254227"} @article{bb259435, 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#TT254228"} @article{bb259436, 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#TT254229"} @inproceedings{bb259437, 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#TT254230"} @article{bb259438, 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#TT254231"} @article{bb259439, 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#TT254232"} @inproceedings{bb259440, 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#TT254233"} @inproceedings{bb259441, 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#TT254234"} @inproceedings{bb259442, 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#TT254235"} @article{bb259443, 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#TT254236"} @article{bb259444, 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#TT254237"} @article{bb259445, 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#TT254238"} @article{bb259446, 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#TT254239"} @inproceedings{bb259447, 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#TT254240"} @article{bb259448, 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#TT254241"} @inproceedings{bb259449, 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#TT254242"} @inproceedings{bb259450, 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#TT254243"} @article{bb259451, 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#TT254244"} @inproceedings{bb259452, 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#TT254245"} @article{bb259453, 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#TT254246"} @article{bb259454, 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#TT254247"} @article{bb259455, 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#TT254248"} @inproceedings{bb259456, 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#TT254249"} @article{bb259457, 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#TT254250"} @inproceedings{bb259458, 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#TT254251"} @article{bb259459, 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#TT254252"} @article{bb259460, 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#TT254253"} @inproceedings{bb259461, 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#TT254254"} @inproceedings{bb259462, 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#TT254255"} @article{bb259463, 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#TT254256"} @article{bb259464, 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#TT254257"} @article{bb259465, 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#TT254258"} @article{bb259466, 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#TT254259"} @article{bb259467, 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#TT254260"} @article{bb259468, 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#TT254261"} @inproceedings{bb259469, 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#TT254262"} @article{bb259470, 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#TT254263"} @article{bb259471, 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#TT254264"} @article{bb259472, 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#TT254265"} @inproceedings{bb259473, 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#TT254265"} @inproceedings{bb259474, 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#TT254266"} @article{bb259475, 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#TT254267"} @inproceedings{bb259476, 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#TT254268"} @article{bb259477, AUTHOR = "Nicolaou, M.A. and Pavlovic, V. and Pantic, M.", TITLE = "Dynamic Probabilistic CCA for Analysis of Affective Behavior and Fusion of Continuous Annotations", JOURNAL = PAMI, VOLUME = "36", YEAR = "2014", NUMBER = "7", MONTH = "July", PAGES = "1299-1311", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254269"} @inproceedings{bb259478, AUTHOR = "Nicolaou, M.A. and Pavlovic, V. and Pantic, M.", TITLE = "Dynamic Probabilistic CCA for Analysis of Affective Behaviour", BOOKTITLE = ECCV12, YEAR = "2012", PAGES = "VII: 98-111", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254270"} @article{bb259479, AUTHOR = "Wang, L.J. and Qian, Y. and Scott, M.R. and Chen, G. and Soong, F.K.", TITLE = "Computer-Assisted Audiovisual Language Learning", JOURNAL = Computer, VOLUME = "45", YEAR = "2012", NUMBER = "6", MONTH = "June", PAGES = "38-47", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254271"} @article{bb259480, AUTHOR = "Wu, Q.X. and Wang, Z.Y. and Deng, F.Q. and Chi, Z. and Feng, D.D.", TITLE = "Realistic Human Action Recognition with Multimodal Feature Selection and Fusion", JOURNAL = SMCS, VOLUME = "43", YEAR = "2013", NUMBER = "4", PAGES = "875-885", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254272"} @article{bb259481, AUTHOR = "Wu, Q.X. and Wang, Z.Y. and Deng, F.Q. and Xia, Y. and Kang, W.X. and Feng, D.D.", TITLE = "Discriminative two-level feature selection for realistic human action recognition", JOURNAL = JVCIR, VOLUME = "24", YEAR = "2013", NUMBER = "7", PAGES = "1064-1074", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254273"} @inproceedings{bb259482, AUTHOR = "Wu, Q.X. and Wang, Z.Y. and Deng, F.Q. and Feng, D.D.", TITLE = "Realistic Human Action Recognition with Audio Context", BOOKTITLE = DICTA10, YEAR = "2010", PAGES = "288-293", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254274"} @inproceedings{bb259483, AUTHOR = "Wu, Q.X. and Lu, S.Y. and Wang, Z.Y. and Deng, F.Q. and Kang, W.X. and Feng, D.D.", TITLE = "Structure Context of Local Features in Realistic Human Action Recognition", BOOKTITLE = VECTaR11, YEAR = "2011", PAGES = "1496-1501", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254275"} @article{bb259484, AUTHOR = "Mirzaei, M.R. and Ghorshi, S. and Mortazavi, M.", TITLE = "Audio-visual speech recognition techniques in augmented reality environments", JOURNAL = VC, VOLUME = "30", YEAR = "2014", NUMBER = "3", MONTH = "March", PAGES = "245-257", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254276"} @article{bb259485, AUTHOR = "Bredin, H. and Roy, A. and Le, V.B. and Barras, C.", TITLE = "Person instance graphs for mono-, cross- and multi-modal person recognition in multimedia data: application to speaker identification in TV broadcast", JOURNAL = MultInfoRetr, VOLUME = "3", YEAR = "2014", NUMBER = "3", MONTH = "September", PAGES = "161-175", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254277"} @article{bb259486, AUTHOR = "Ozasa, Y. and Nakano, M. and Ariki, Y. and Iwahashi, N.", TITLE = "Discriminating Unknown Objects from Known Objects Using Image and Speech Information", JOURNAL = IEICE, VOLUME = "E98-D", YEAR = "2015", NUMBER = "3", MONTH = "March", PAGES = "704-711", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254278"} @inproceedings{bb259487, AUTHOR = "Ozasa, Y. and Ariki, Y. and Nakano, M. and Iwahashi, N.", TITLE = "Disambiguation in Unknown Object Detection by Integrating Image and Speech Recognition Confidences", BOOKTITLE = ACCV12, YEAR = "2012", PAGES = "I:85-96", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254279"} @inproceedings{bb259488, AUTHOR = "Nishimura, H. and Ozasa, Y. and Ariki, Y. and Nakano, M.", TITLE = "Selection of Unknown Objects Specified by Speech Using Models Constructed from Web Images", BOOKTITLE = ICPR14, YEAR = "2014", PAGES = "477-482", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254280"} @inproceedings{bb259489, AUTHOR = "Nishimura, H. and Ozasa, Y. and Ariki, Y. and Nakano, M.", TITLE = "Object Recognition by Integrated Information Using Web Images", BOOKTITLE = ACPR13, YEAR = "2013", PAGES = "657-661", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254281"} @inproceedings{bb259490, AUTHOR = "Ozasa, Y. and Enami, N. and Ariki, Y.", TITLE = "Color saliency for object identification", BOOKTITLE = FCV15, YEAR = "2015", PAGES = "1-5", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254282"} @article{bb259491, AUTHOR = "Harte, N. and Gillen, E.", TITLE = "TCD-TIMIT: An Audio-Visual Corpus of Continuous Speech", JOURNAL = MultMed, VOLUME = "17", YEAR = "2015", NUMBER = "5", MONTH = "May", PAGES = "603-615", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254283"} @article{bb259492, AUTHOR = "Katsaggelos, A.K. and Bahaadini, S. and Molina, R.", TITLE = "Audiovisual Fusion: Challenges and New Approaches", JOURNAL = PIEEE, VOLUME = "103", YEAR = "2015", NUMBER = "9", MONTH = "September", PAGES = "1635-1653", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254284"} @article{bb259493, AUTHOR = "Mezai, L. and Hachouf, F.", TITLE = "Score-Level Fusion of Face and Voice Using Particle Swarm Optimization and Belief Functions", JOURNAL = HMS, VOLUME = "45", YEAR = "2015", NUMBER = "6", MONTH = "December", PAGES = "761-772", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254285"} @article{bb259494, AUTHOR = "Wu, P. and Liu, H. and Li, X. and Fan, T. and Zhang, X.", TITLE = "A Novel Lip Descriptor for Audio-Visual Keyword Spotting Based on Adaptive Decision Fusion", JOURNAL = MultMed, VOLUME = "18", YEAR = "2016", NUMBER = "3", MONTH = "March", PAGES = "326-338", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254286"} @article{bb259495, AUTHOR = "Dilpazir, H. and Muhammad, Z. and Minhas, Q. and Ahmed, F. and Malik, H. and Mahmood, H.", TITLE = "Multivariate mutual information for audio video fusion", JOURNAL = SIViP, VOLUME = "10", YEAR = "2016", NUMBER = "7", MONTH = "October", PAGES = "1265-1272", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254287"} @article{bb259496, AUTHOR = "Beyan, C. and Capozzi, F. and Becchio, C. and Murino, V.", TITLE = "Prediction of the Leadership Style of an Emergent Leader Using Audio and Visual Nonverbal Features", JOURNAL = MultMed, VOLUME = "20", YEAR = "2018", NUMBER = "2", MONTH = "February", PAGES = "441-456", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254288"} @article{bb259497, AUTHOR = "Fernandez Lopez, A. and Sukno, F.M.", TITLE = "Survey on automatic lip-reading in the era of deep learning", JOURNAL = IVC, VOLUME = "78", YEAR = "2018", PAGES = "53-72", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254289"} @article{bb259498, AUTHOR = "Stafylakis, T. and Khan, M.H. and Tzimiropoulos, G.", TITLE = "Pushing the boundaries of audiovisual word recognition using Residual Networks and LSTMs", JOURNAL = CVIU, VOLUME = "176-177", YEAR = "2018", PAGES = "22-32", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254290"} @inproceedings{bb259499, AUTHOR = "Stafylakis, T. and Tzimiropoulos, G.", TITLE = "Zero-Shot Keyword Spotting for Visual Speech Recognition In-the-wild", BOOKTITLE = ECCV18, YEAR = "2018", PAGES = "II: 536-552", BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254291"}