@article{bb181300,
        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#TT176685"}

@inproceedings{bb181301,
        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#TT176686"}

@article{bb181302,
        AUTHOR = "Garg, A. and Pavlovic, V. and Rehg, J.M.",
        TITLE = "Boosted learning in dynamic Bayesian networks for multimodal speaker
detection",
        JOURNAL = PIEEE,
        VOLUME = "91",
        YEAR = "2003",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "1355-1369",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176687"}

@inproceedings{bb181303,
        AUTHOR = "Garg, A. and Pavlovic, V. and Rehg, J.M.",
        TITLE = "Audio-visual speaker detection using dynamic Bayesian networks",
        BOOKTITLE = AFGR00,
        YEAR = "2000",
        PAGES = "384-390",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176688"}

@inproceedings{bb181304,
        AUTHOR = "Pavlovic, V. and Garg, A. and Rehg, J.M. and Huang, T.S.",
        TITLE = "Multimodal Speaker Detection using Error Feedback Dynamic Bayesian
Networks",
        BOOKTITLE = CVPR00,
        YEAR = "2000",
        PAGES = "II: 34-41",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176689"}

@inproceedings{bb181305,
        AUTHOR = "Pavlovic, V. and Berry, G. and Huang, T.S.",
        TITLE = "Integration of Audio/Visual Information for Use in
Human-Computer Intelligent Interaction",
        BOOKTITLE = ICIP97,
        YEAR = "1997",
        PAGES = "I: 121-124",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176690"}

@inproceedings{bb181306,
        AUTHOR = "Choudhury, T. and Rehg, J.M. and Pavlovic, V. and Pentland, A.P.",
        TITLE = "Boosting and structure learning in dynamic Bayesian networks for
audio-visual speaker detection",
        BOOKTITLE = ICPR02,
        YEAR = "2002",
        PAGES = "III: 789-794",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176691"}

@inproceedings{bb181307,
        AUTHOR = "Pavlovic, V.",
        TITLE = "Multimodal tracking and classification of audio-visual features",
        BOOKTITLE = ICIP98,
        YEAR = "1998",
        PAGES = "I: 343-347",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176692"}

@inproceedings{bb181308,
        AUTHOR = "Rehg, J.M. and Murphy, K.P. and Fieguth, P.W.",
        TITLE = "Vision-Based Speaker Detection Using Bayesian Networks",
        BOOKTITLE = CVPR99,
        YEAR = "1999",
        PAGES = "II: 110-116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176693"}

@article{bb181309,
        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#TT176694"}

@article{bb181310,
        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#TT176695"}

@article{bb181311,
        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#TT176696"}

@article{bb181312,
        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#TT176697"}

@article{bb181313,
        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#TT176698"}

@article{bb181314,
        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#TT176699"}

@inproceedings{bb181315,
        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#TT176700"}

@inproceedings{bb181316,
        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#TT176701"}

@inproceedings{bb181317,
        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#TT176702"}

@article{bb181318,
        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#TT176703"}

@inproceedings{bb181319,
        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#TT176704"}

@article{bb181320,
        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#TT176705"}

@article{bb181321,
        AUTHOR = "Talantzis, F. and Pnevmatikakis, A. and Constantinides, A.G.",
        TITLE = "Audio-Visual Active Speaker Tracking in Cluttered Indoors Environments",
        JOURNAL = SMC-B,
        VOLUME = "39",
        YEAR = "2009",
        NUMBER = "1",
        MONTH = "February",
        PAGES = "7-15",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176706"}

@article{bb181322,
        AUTHOR = "Constantinides, A.G. and Pnevmatikakis, A. and Talantzis, F.",
        TITLE = "Audio-Visual Active Speaker Tracking in Cluttered Indoors Environments",
        JOURNAL = SMC-B,
        VOLUME = "38",
        YEAR = "2008",
        NUMBER = "3",
        MONTH = "June",
        PAGES = "799-807",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176706"}

@article{bb181323,
        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#TT176707"}

@inproceedings{bb181324,
        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#TT176708"}

@inproceedings{bb181325,
        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#TT176709"}

@article{bb181326,
        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#TT176710"}

@article{bb181327,
        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#TT176711"}

@article{bb181328,
        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#TT176712"}

@inproceedings{bb181329,
        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#TT176713"}

@article{bb181330,
        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#TT176714"}

@article{bb181331,
        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#TT176715"}

@inproceedings{bb181332,
        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#TT176716"}

@inproceedings{bb181333,
        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#TT176717"}

@inproceedings{bb181334,
        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#TT176718"}

@article{bb181335,
        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#TT176719"}

@article{bb181336,
        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#TT176720"}

@article{bb181337,
        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#TT176721"}

@article{bb181338,
        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#TT176722"}

@inproceedings{bb181339,
        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#TT176723"}

@article{bb181340,
        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#TT176724"}

@inproceedings{bb181341,
        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#TT176725"}

@inproceedings{bb181342,
        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#TT176726"}

@article{bb181343,
        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#TT176727"}

@inproceedings{bb181344,
        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#TT176728"}

@article{bb181345,
        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#TT176729"}

@article{bb181346,
        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#TT176730"}

@article{bb181347,
        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#TT176731"}

@inproceedings{bb181348,
        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#TT176732"}

@article{bb181349,
        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#TT176733"}

@inproceedings{bb181350,
        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#TT176734"}

@article{bb181351,
        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#TT176735"}

@article{bb181352,
        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#TT176736"}

@inproceedings{bb181353,
        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#TT176737"}

@inproceedings{bb181354,
        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#TT176738"}

@article{bb181355,
        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#TT176739"}

@article{bb181356,
        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#TT176740"}

@article{bb181357,
        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#TT176741"}

@article{bb181358,
        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#TT176742"}

@article{bb181359,
        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#TT176743"}

@article{bb181360,
        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#TT176744"}

@inproceedings{bb181361,
        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#TT176745"}

@article{bb181362,
        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#TT176746"}

@article{bb181363,
        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#TT176747"}

@article{bb181364,
        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#TT176748"}

@inproceedings{bb181365,
        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#TT176748"}

@inproceedings{bb181366,
        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#TT176749"}

@article{bb181367,
        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#TT176750"}

@inproceedings{bb181368,
        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#TT176751"}

@article{bb181369,
        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#TT176752"}

@inproceedings{bb181370,
        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#TT176753"}

@article{bb181371,
        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#TT176754"}

@article{bb181372,
        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#TT176755"}

@article{bb181373,
        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#TT176756"}

@inproceedings{bb181374,
        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#TT176757"}

@inproceedings{bb181375,
        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#TT176758"}

@article{bb181376,
        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#TT176759"}

@article{bb181377,
        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#TT176760"}

@article{bb181378,
        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#TT176761"}

@inproceedings{bb181379,
        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#TT176762"}

@inproceedings{bb181380,
        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#TT176763"}

@inproceedings{bb181381,
        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#TT176764"}

@inproceedings{bb181382,
        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#TT176765"}

@article{bb181383,
        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#TT176766"}

@article{bb181384,
        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#TT176767"}

@article{bb181385,
        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#TT176768"}

@article{bb181386,
        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#TT176769"}

@article{bb181387,
        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#TT176770"}

@article{bb181388,
        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#TT176771"}

@article{bb181389,
        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#TT176772"}

@article{bb181390,
        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#TT176773"}

@inproceedings{bb181391,
        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#TT176774"}

@article{bb181392,
        AUTHOR = "Liu, X. and Geng, J.J. and Ling, H.B. and Cheung, Y.M.",
        TITLE = "Attention guided deep audio-face fusion for efficient speaker naming",
        JOURNAL = PR,
        VOLUME = "88",
        YEAR = "2019",
        PAGES = "557-568",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176775"}

@inproceedings{bb181393,
        AUTHOR = "Schindler, A. and Boyer, M. and Lindley, A. and Schreiber, D. and Philipp, T.",
        TITLE = "Large Scale Audio-Visual Video Analytics Platform for Forensic
Investigations of Terroristic Attacks",
        BOOKTITLE = "MMMod19",
        YEAR = "2019",
        PAGES = "II:106-119",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176776"}

@inproceedings{bb181394,
        AUTHOR = "Oliveira, D.A.B. and Mattos, A.B. and da Silva Morais, E.",
        TITLE = "Improving Viseme Recognition Using GAN-Based Frontal View Mapping",
        BOOKTITLE = AMFG18,
        YEAR = "2018",
        PAGES = "2229-22297",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176777"}

@inproceedings{bb181395,
        AUTHOR = "Yang, X. and Molchanov, P. and Kautz, J.",
        TITLE = "Making Convolutional Networks Recurrent for Visual Sequence Learning",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6469-6478",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176778"}

@inproceedings{bb181396,
        AUTHOR = "Zhang, J. and Richmond, K. and Fisher, R.B.",
        TITLE = "Dual-modality Talking-metrics: 3D Visual-Audio Integrated
Behaviometric Cues from Speakers",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3144-3149",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176779"}

@inproceedings{bb181397,
        AUTHOR = "Chowdhury, A. and Atoum, Y. and Tran, L. and Liu, X. and Ross, A.",
        TITLE = "MSU-AVIS dataset: Fusing Face and Voice Modalities for Biometric
Recognition in Indoor Surveillance Videos",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3567-3573",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176780"}

@inproceedings{bb181398,
        AUTHOR = "Nagrani, A. and Albanie, S. and Zisserman, A.",
        TITLE = "Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "8427-8436",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176781"}

@inproceedings{bb181399,
        AUTHOR = "Saitoh, T. and Kubokawa, M.",
        TITLE = "SSSD: Speech Scene database by Smart Device for Visual Speech
Recognition",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3228-3232",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT176782"}

Last update:Jan 25, 2019 at 17:55:53