@inproceedings{bb287600,
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#TT282236"}
@inproceedings{bb287601,
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#TT282237"}
@article{bb287602,
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#TT282238"}
@article{bb287603,
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#TT282239"}
@article{bb287604,
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#TT282240"}
@article{bb287605,
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#TT282241"}
@inproceedings{bb287606,
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#TT282242"}
@article{bb287607,
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#TT282243"}
@article{bb287608,
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#TT282244"}
@inproceedings{bb287609,
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#TT282245"}
@article{bb287610,
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#TT282246"}
@article{bb287611,
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#TT282247"}
@inproceedings{bb287612,
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#TT282248"}
@article{bb287613,
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#TT282249"}
@article{bb287614,
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#TT282250"}
@article{bb287615,
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#TT282251"}
@inproceedings{bb287616,
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#TT282252"}
@article{bb287617,
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#TT282253"}
@inproceedings{bb287618,
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#TT282254"}
@article{bb287619,
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#TT282255"}
@article{bb287620,
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#TT282256"}
@article{bb287621,
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#TT282257"}
@article{bb287622,
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#TT282258"}
@article{bb287623,
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#TT282259"}
@article{bb287624,
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#TT282260"}
@inproceedings{bb287625,
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#TT282261"}
@inproceedings{bb287626,
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#TT282262"}
@inproceedings{bb287627,
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#TT282263"}
@article{bb287628,
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#TT282264"}
@inproceedings{bb287629,
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#TT282265"}
@article{bb287630,
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#TT282266"}
@article{bb287631,
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#TT282267"}
@inproceedings{bb287632,
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#TT282268"}
@inproceedings{bb287633,
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#TT282269"}
@article{bb287634,
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#TT282270"}
@article{bb287635,
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#TT282271"}
@article{bb287636,
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#TT282272"}
@article{bb287637,
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#TT282273"}
@inproceedings{bb287638,
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#TT282274"}
@inproceedings{bb287639,
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#TT282275"}
@inproceedings{bb287640,
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#TT282276"}
@article{bb287641,
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#TT282277"}
@article{bb287642,
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#TT282278"}
@article{bb287643,
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#TT282279"}
@article{bb287644,
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#TT282280"}
@inproceedings{bb287645,
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#TT282281"}
@inproceedings{bb287646,
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#TT282282"}
@article{bb287647,
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#TT282283"}
@inproceedings{bb287648,
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#TT282284"}
@article{bb287649,
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#TT282285"}
@article{bb287650,
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#TT282286"}
@article{bb287651,
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#TT282287"}
@inproceedings{bb287652,
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#TT282288"}
@article{bb287653,
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#TT282289"}
@article{bb287654,
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#TT282290"}
@inproceedings{bb287655,
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#TT282291"}
@inproceedings{bb287656,
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#TT282292"}
@article{bb287657,
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#TT282293"}
@article{bb287658,
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#TT282294"}
@article{bb287659,
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#TT282295"}
@article{bb287660,
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#TT282296"}
@article{bb287661,
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#TT282297"}
@article{bb287662,
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#TT282298"}
@inproceedings{bb287663,
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#TT282298"}
@inproceedings{bb287664,
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#TT282299"}
@article{bb287665,
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#TT282300"}
@inproceedings{bb287666,
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#TT282301"}
@article{bb287667,
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#TT282302"}
@inproceedings{bb287668,
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#TT282303"}
@article{bb287669,
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#TT282304"}
@article{bb287670,
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#TT282305"}
@article{bb287671,
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#TT282306"}
@inproceedings{bb287672,
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#TT282307"}
@inproceedings{bb287673,
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#TT282308"}
@article{bb287674,
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#TT282309"}
@article{bb287675,
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#TT282310"}
@article{bb287676,
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#TT282311"}
@inproceedings{bb287677,
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#TT282312"}
@inproceedings{bb287678,
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#TT282313"}
@inproceedings{bb287679,
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#TT282314"}
@inproceedings{bb287680,
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#TT282315"}
@article{bb287681,
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#TT282316"}
@article{bb287682,
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#TT282317"}
@article{bb287683,
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#TT282318"}
@article{bb287684,
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#TT282319"}
@article{bb287685,
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#TT282320"}
@article{bb287686,
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#TT282321"}
@article{bb287687,
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#TT282322"}
@article{bb287688,
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#TT282323"}
@inproceedings{bb287689,
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#TT282324"}
@article{bb287690,
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#TT282325"}
@article{bb287691,
AUTHOR = "Tsiami, A. and Koutras, P. and Katsamanis, A. and Vatakis, A. and Maragos, P.",
TITLE = "A behaviorally inspired fusion approach for computational audiovisual
saliency modeling",
JOURNAL = SP:IC,
VOLUME = "76",
YEAR = "2019",
PAGES = "186-200",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282326"}
@article{bb287692,
AUTHOR = "Hsiao, S. and Sun, H. and Hsieh, M. and Tsai, M. and Tsao, Y. and Lee, C.",
TITLE = "Toward Automating Oral Presentation Scoring During Principal
Certification Program Using Audio-Video Low-Level Behavior Profiles",
JOURNAL = AffCom,
VOLUME = "10",
YEAR = "2019",
NUMBER = "4",
MONTH = "October",
PAGES = "552-567",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282327"}
@article{bb287693,
AUTHOR = "Ma, Y. and Hong, H. and Li, H. and Zhao, H. and Li, Y.S. and Sun, L. and Gu, C. and Zhu, X.H.",
TITLE = "Non-Contact Speech Recovery Technology Using a 24 GHz Portable
Auditory Radar and Webcam",
JOURNAL = RS,
VOLUME = "12",
YEAR = "2020",
NUMBER = "4",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282328"}
@inproceedings{bb287694,
AUTHOR = "Xu, B. and Wang, J. and Lu, C. and Guo, Y.",
TITLE = "Watch to Listen Clearly: Visual Speech Enhancement Driven
Multi-modality Speech Recognition",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "1626-1635",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282329"}
@article{bb287695,
AUTHOR = "Tao, F. and Busso, C.",
TITLE = "End-to-End Audiovisual Speech Recognition System With Multitask
Learning",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "1-11",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282330"}
@article{bb287696,
AUTHOR = "Xu, J.H. and Zhang, B. and Wang, Z.Y. and Wang, Y. and Chen, F. and Gao, J.B. and Feng, D.D.",
TITLE = "Affective Audio Annotation of Public Speeches with Convolutional
Clustering Neural Network",
JOURNAL = AffCom,
VOLUME = "13",
YEAR = "2022",
NUMBER = "1",
MONTH = "January",
PAGES = "238-249",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282331"}
@article{bb287697,
AUTHOR = "Afouras, T. and Chung, J.S. and Senior, A. and Vinyals, O. and Zisserman, A.",
TITLE = "Deep Audio-Visual Speech Recognition",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "8717-8727",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282332"}
@inproceedings{bb287698,
AUTHOR = "Rahimi, A. and Afouras, T. and Zisserman, A.",
TITLE = "Reading to Listen at the Cocktail Party:
Multi-Modal Speech Separation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10483-10492",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282333"}
@article{bb287699,
AUTHOR = "Narain, J. and Johnson, K.T. and Quatieri, T.F. and Picard, R.W. and Maes, P.",
TITLE = "Modeling Real-World Affective and Communicative Nonverbal
Vocalizations From Minimally Speaking Individuals",
JOURNAL = AffCom,
VOLUME = "13",
YEAR = "2022",
NUMBER = "4",
MONTH = "October",
PAGES = "2238-2253",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282334"}
Last update:Feb 17, 2026 at 20:06:16