@article{bb274200,
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#TT268917"}
@inproceedings{bb274201,
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#TT268918"}
@article{bb274202,
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#TT268919"}
@article{bb274203,
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#TT268920"}
@inproceedings{bb274204,
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#TT268921"}
@inproceedings{bb274205,
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#TT268922"}
@article{bb274206,
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#TT268923"}
@article{bb274207,
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#TT268924"}
@article{bb274208,
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#TT268925"}
@inproceedings{bb274209,
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#TT268926"}
@article{bb274210,
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#TT268927"}
@article{bb274211,
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#TT268928"}
@inproceedings{bb274212,
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#TT268929"}
@inproceedings{bb274213,
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#TT268930"}
@inproceedings{bb274214,
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#TT268931"}
@article{bb274215,
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#TT268932"}
@article{bb274216,
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#TT268933"}
@article{bb274217,
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#TT268934"}
@article{bb274218,
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#TT268935"}
@inproceedings{bb274219,
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#TT268936"}
@article{bb274220,
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#TT268937"}
@inproceedings{bb274221,
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#TT268938"}
@inproceedings{bb274222,
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#TT268939"}
@article{bb274223,
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#TT268940"}
@inproceedings{bb274224,
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#TT268941"}
@article{bb274225,
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#TT268942"}
@article{bb274226,
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#TT268943"}
@article{bb274227,
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#TT268944"}
@inproceedings{bb274228,
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#TT268945"}
@article{bb274229,
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#TT268946"}
@inproceedings{bb274230,
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#TT268947"}
@article{bb274231,
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#TT268948"}
@article{bb274232,
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#TT268949"}
@inproceedings{bb274233,
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#TT268950"}
@inproceedings{bb274234,
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#TT268951"}
@article{bb274235,
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#TT268952"}
@article{bb274236,
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#TT268953"}
@article{bb274237,
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#TT268954"}
@article{bb274238,
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#TT268955"}
@article{bb274239,
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#TT268956"}
@article{bb274240,
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#TT268957"}
@inproceedings{bb274241,
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#TT268958"}
@article{bb274242,
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#TT268959"}
@article{bb274243,
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#TT268960"}
@article{bb274244,
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#TT268961"}
@inproceedings{bb274245,
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#TT268961"}
@inproceedings{bb274246,
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#TT268962"}
@article{bb274247,
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#TT268963"}
@inproceedings{bb274248,
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#TT268964"}
@article{bb274249,
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#TT268965"}
@inproceedings{bb274250,
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#TT268966"}
@article{bb274251,
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#TT268967"}
@article{bb274252,
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#TT268968"}
@article{bb274253,
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#TT268969"}
@inproceedings{bb274254,
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#TT268970"}
@inproceedings{bb274255,
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#TT268971"}
@article{bb274256,
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#TT268972"}
@article{bb274257,
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#TT268973"}
@article{bb274258,
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#TT268974"}
@inproceedings{bb274259,
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#TT268975"}
@inproceedings{bb274260,
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#TT268976"}
@inproceedings{bb274261,
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#TT268977"}
@inproceedings{bb274262,
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#TT268978"}
@article{bb274263,
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#TT268979"}
@article{bb274264,
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#TT268980"}
@article{bb274265,
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#TT268981"}
@article{bb274266,
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#TT268982"}
@article{bb274267,
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#TT268983"}
@article{bb274268,
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#TT268984"}
@article{bb274269,
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#TT268985"}
@article{bb274270,
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#TT268986"}
@inproceedings{bb274271,
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#TT268987"}
@article{bb274272,
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#TT268988"}
@article{bb274273,
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#TT268989"}
@article{bb274274,
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#TT268990"}
@article{bb274275,
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#TT268991"}
@inproceedings{bb274276,
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#TT268992"}
@article{bb274277,
AUTHOR = "Pu, J. and Panagakis, Y. and Pantic, M.",
TITLE = "Active Speaker Detection and Localization in Videos Using Low-Rank
and Kernelized Sparsity",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "865-869",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT268993"}
@article{bb274278,
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#TT268994"}
@article{bb274279,
AUTHOR = "Liu, L. and Feng, G. and Beautemps, D. and Zhang, X.P.",
TITLE = "Re-Synchronization Using the Hand Preceding Model for Multi-Modal
Fusion in Automatic Continuous Cued Speech Recognition",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "292-305",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT268995"}
@article{bb274280,
AUTHOR = "Beyan, C. and Shahid, M. and Murino, V.",
TITLE = "RealVAD: A Real-World Dataset and A Method for Voice Activity
Detection by Body Motion Analysis",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "2071-2085",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT268996"}
@article{bb274281,
AUTHOR = "Qian, X.Y. and Liu, Q. and Wang, J.D. and Li, H.Z.",
TITLE = "Three-Dimensional Speaker Localization: Audio-Refined Visual Scaling
Factor Estimation",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1405-1409",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT268997"}
@article{bb274282,
AUTHOR = "Zheng, A. and Hu, M. and Jiang, B. and Huang, Y. and Yan, Y. and Luo, B.",
TITLE = "Adversarial-Metric Learning for Audio-Visual Cross-Modal Matching",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "338-351",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT268998"}
@article{bb274283,
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#TT268999"}
@article{bb274284,
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#TT269000"}
@inproceedings{bb274285,
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#TT269001"}
@article{bb274286,
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#TT269002"}
@article{bb274287,
AUTHOR = "Gong, Y. and Liu, A.H. and Rouditchenko, A. and Glass, J.",
TITLE = "UAVM: Towards Unifying Audio and Visual Models",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2437-2441",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269003"}
@inproceedings{bb274288,
AUTHOR = "Oya, T. and Iwase, S. and Morishima, S.",
TITLE = "The Sound of Bounding-Boxes",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "9-15",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269004"}
@article{bb274289,
AUTHOR = "Zhou, J.X. and Guo, D. and Wang, M.",
TITLE = "Contrastive Positive Sample Propagation Along the Audio-Visual Event
Line",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "7239-7257",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269005"}
@inproceedings{bb274290,
AUTHOR = "Zhou, J.X. and Zheng, L. and Zhong, Y. and Hao, S.J. and Wang, M.",
TITLE = "Positive Sample Propagation along the Audio-Visual Event Line",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "8432-8440",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269006"}
@article{bb274291,
AUTHOR = "Sen, T.K. and Naven, G. and Gerstner, L. and Bagley, D. and Baten, R.A. and Rahman, W. and Hasan, M.K. and Haut, K. and Mamun, A.A. and Samrose, S. and Solbu, A. and Barnes, R.E. and Frank, M.G. and Hoque, E.",
TITLE = "DBATES: Dataset for Discerning Benefits of Audio, Textual, and Facial
Expression Features in Competitive Debate Speeches",
JOURNAL = AffCom,
VOLUME = "14",
YEAR = "2023",
NUMBER = "2",
MONTH = "April",
PAGES = "1028-1043",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269007"}
@article{bb274292,
AUTHOR = "Sharma, G. and Dhall, A. and Cai, J.F.",
TITLE = "Audio-Visual Automatic Group Affect Analysis",
JOURNAL = AffCom,
VOLUME = "14",
YEAR = "2023",
NUMBER = "2",
MONTH = "April",
PAGES = "1056-1069",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269008"}
@article{bb274293,
AUTHOR = "Cheng, W.L. and Tang, W. and Huang, Y. and Luo, Y.W. and Wang, L.",
TITLE = "A Reconstruction-Based Visual-Acoustic-Semantic Embedding Method for
Speech-Image Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "4067-4080",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269009"}
@article{bb274294,
AUTHOR = "Kefalas, T. and Fotiadou, E. and Georgopoulos, M. and Panagakis, Y. and Ma, P.C. and Petridis, S. and Stafylakis, T. and Pantic, M.",
TITLE = "KAN-AV dataset for audio-visual face and speech analysis in the wild",
JOURNAL = IVC,
VOLUME = "140",
YEAR = "2023",
PAGES = "104839",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269010"}
@article{bb274295,
AUTHOR = "Wang, X.M. and Mi, J.C. and Li, B.Q. and Zhao, Y.X. and Meng, J.X.",
TITLE = "CATNet: Cross-modal fusion for audio-visual speech recognition",
JOURNAL = PRL,
VOLUME = "178",
YEAR = "2024",
PAGES = "216-222",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269011"}
@article{bb274296,
AUTHOR = "Zhu, D.D. and Zhang, K.W. and Zhang, N. and Zhou, Q.Q. and Min, X.K. and Zhai, G.T. and Yang, X.K.",
TITLE = "Unified Audio-Visual Saliency Model for Omnidirectional Videos With
Spatial Audio",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "764-775",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269012"}
@article{bb274297,
AUTHOR = "Qian, X.Y. and Xue, W. and Zhang, Q. and Tao, R.J. and Li, H.Z.",
TITLE = "Deep Cross-Modal Retrieval Between Spatial Image and Acoustic Speech",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "4480-4489",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269013"}
@article{bb274298,
AUTHOR = "Xie, J.W. and Liu, Z. and Li, G.Y. and Song, Y.J.",
TITLE = "Audio-visual saliency prediction with multisensory perception and
integration",
JOURNAL = IVC,
VOLUME = "143",
YEAR = "2024",
PAGES = "104955",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269014"}
@article{bb274299,
AUTHOR = "Sun, X. and Wang, X. and Liu, Q. and Zhou, X.",
TITLE = "Multi-Level Signal Fusion for Enhanced Weakly-Supervised Audio-Visual
Video Parsing",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1149-1153",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT269015"}
Last update:Apr 23, 2025 at 18:43:10