@inproceedings{bb214600,
        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#TT209682"}

@inproceedings{bb214601,
        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#TT209683"}

@article{bb214602,
        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#TT209684"}

@inproceedings{bb214603,
        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#TT209685"}

@article{bb214604,
        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#TT209686"}

@article{bb214605,
        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#TT209687"}

@article{bb214606,
        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#TT209688"}

@inproceedings{bb214607,
        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#TT209689"}

@article{bb214608,
        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#TT209690"}

@inproceedings{bb214609,
        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#TT209691"}

@article{bb214610,
        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#TT209692"}

@article{bb214611,
        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#TT209693"}

@inproceedings{bb214612,
        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#TT209694"}

@inproceedings{bb214613,
        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#TT209695"}

@article{bb214614,
        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#TT209696"}

@article{bb214615,
        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#TT209697"}

@article{bb214616,
        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#TT209698"}

@article{bb214617,
        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#TT209699"}

@article{bb214618,
        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#TT209700"}

@article{bb214619,
        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#TT209701"}

@inproceedings{bb214620,
        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#TT209702"}

@article{bb214621,
        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#TT209703"}

@article{bb214622,
        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#TT209704"}

@article{bb214623,
        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#TT209705"}

@inproceedings{bb214624,
        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#TT209705"}

@inproceedings{bb214625,
        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#TT209706"}

@article{bb214626,
        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#TT209707"}

@inproceedings{bb214627,
        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#TT209708"}

@article{bb214628,
        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#TT209709"}

@inproceedings{bb214629,
        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#TT209710"}

@article{bb214630,
        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#TT209711"}

@article{bb214631,
        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#TT209712"}

@article{bb214632,
        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#TT209713"}

@inproceedings{bb214633,
        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#TT209714"}

@inproceedings{bb214634,
        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#TT209715"}

@article{bb214635,
        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#TT209716"}

@article{bb214636,
        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#TT209717"}

@article{bb214637,
        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#TT209718"}

@inproceedings{bb214638,
        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#TT209719"}

@inproceedings{bb214639,
        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#TT209720"}

@inproceedings{bb214640,
        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#TT209721"}

@inproceedings{bb214641,
        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#TT209722"}

@article{bb214642,
        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#TT209723"}

@article{bb214643,
        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#TT209724"}

@article{bb214644,
        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#TT209725"}

@article{bb214645,
        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#TT209726"}

@article{bb214646,
        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#TT209727"}

@article{bb214647,
        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#TT209728"}

@article{bb214648,
        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#TT209729"}

@article{bb214649,
        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#TT209730"}

@inproceedings{bb214650,
        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#TT209731"}

@article{bb214651,
        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#TT209732"}

@article{bb214652,
        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#TT209733"}

@article{bb214653,
        AUTHOR = "Qian, X. and Brutti, A. and Lanz, O. and Omologo, M. and Cavallaro, A.",
        TITLE = "Multi-Speaker Tracking From an Audio-Visual Sensing Device",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2576-2588",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209734"}

@article{bb214654,
        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#TT209735"}

@article{bb214655,
        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#TT209736"}

@inproceedings{bb214656,
        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#TT209737"}

@article{bb214657,
        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#TT209738"}

@article{bb214658,
        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#TT209739"}

@article{bb214659,
        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#TT209740"}

@article{bb214660,
        AUTHOR = "Ban, Y.T. and Alameda Pineda, X. and Girin, L. and Horaud, R.",
        TITLE = "Variational Bayesian Inference for Audio-Visual Tracking of Multiple
Speakers",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1761-1776",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209741"}

@inproceedings{bb214661,
        AUTHOR = "Ban, Y.T. and Girin, L. and Alameda Pineda, X. and Horaud, R.",
        TITLE = "Exploiting the Complementarity of Audio and Visual Data in
Multi-speaker Tracking",
        BOOKTITLE = CVAVM17,
        YEAR = "2017",
        PAGES = "446-454",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209742"}

@article{bb214662,
        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#TT209743"}

@article{bb214663,
        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#TT209744"}

@inproceedings{bb214664,
        AUTHOR = "Mazumder, P. and Sing, P. and Parida, K.K. and Namboodiri, V.P.",
        TITLE = "AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by
Reconstructing Label Features from Multi-Modal Embeddings",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "3089-3098",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209745"}

@inproceedings{bb214665,
        AUTHOR = "Ishikawa, R. and Hachiuma, R. and Kurobe, A. and Saito, H.",
        TITLE = "Single-modal Incremental Terrain Clustering from Self-Supervised
Audio-Visual Feature Learning",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "9399-9406",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209746"}

@inproceedings{bb214666,
        AUTHOR = "Madrigal, F. and Lerasle, F. and Pibre, L. and Ferrane, I.",
        TITLE = "Audio-Video detection of the active speaker in meetings",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "2536-2543",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209747"}

@inproceedings{bb214667,
        AUTHOR = "Tellamekala, M.K. and Valstar, M. and Pound, M. and Giesbrecht, T.",
        TITLE = "Audio-Visual Predictive Coding for Self-Supervised Visual
Representation Learning",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "9912-9919",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209748"}

@inproceedings{bb214668,
        AUTHOR = "Liu, H. and Wang, Y. and Yang, B.",
        TITLE = "Mutual Alignment between Audiovisual Features for End-to-End
Audiovisual Speech Recognition",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "5348-5353",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209749"}

@inproceedings{bb214669,
        AUTHOR = "Liu, H. and Xu, W.L. and Yang, B.",
        TITLE = "Audio-Visual Speech Recognition Using A Two-Step Feature Fusion
Strategy",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "1896-1903",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209750"}

@inproceedings{bb214670,
        AUTHOR = "Liu, H. and Li, W.H. and Yang, B.",
        TITLE = "Robust Audio-Visual Speech Recognition Based on Hybrid Fusion",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "7580-7586",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209751"}

@inproceedings{bb214671,
        AUTHOR = "Chao, F.Y. and Ozcinar, C. and Zhang, L. and Hamidouche, W. and Deforges, O. and Smolic, A.",
        TITLE = "Towards Audio-Visual Saliency Prediction for Omnidirectional Video
with Spatial Audio",
        BOOKTITLE = VCIP20,
        YEAR = "2020",
        PAGES = "355-358",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209752"}

@inproceedings{bb214672,
        AUTHOR = "Zhou, H. and Xu, X.D. and Lin, D. and Wang, X.G. and Liu, Z.",
        TITLE = "Sep-stereo: Visually Guided Stereophonic Audio Generation by
Associating Source Separation",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XII: 52-69",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209753"}

@inproceedings{bb214673,
        AUTHOR = "Tian, Y.P. and Li, D.Z. and Xu, C.L.",
        TITLE = "Unified Multisensory Perception: Weakly-supervised Audio-visual Video
Parsing",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "III:436-454",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209754"}

@inproceedings{bb214674,
        AUTHOR = "Salman, A.N. and Busso, C.",
        TITLE = "Dynamic versus Static Facial Expressions in the Presence of Speech",
        BOOKTITLE = FG20,
        YEAR = "2020",
        PAGES = "436-443",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209755"}

@inproceedings{bb214675,
        AUTHOR = "Salman, A.N. and Busso, C. and Salman, A.N. and Busso, C.",
        TITLE = "Style Extractor For Facial Expression Recognition in the Presence of
Speech",
        BOOKTITLE = ICIP20,
        YEAR = "2020",
        PAGES = "1806-1810",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209756"}

@inproceedings{bb214676,
        AUTHOR = "Liu, Y.F. and Qiao, M.L. and Xu, M. and Li, B. and Hu, W.M. and Borji, A.",
        TITLE = "Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XX:413-429",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209757"}

@inproceedings{bb214677,
        AUTHOR = "Yang, K. and Russell, B. and Salamon, J.",
        TITLE = "Telling Left From Right:
Learning Spatial Correspondence of Sight and Sound",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "9929-9938",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209758"}

@inproceedings{bb214678,
        AUTHOR = "Gao, R. and Oh, T. and Grauman, K. and Torresani, L.",
        TITLE = "Listen to Look: Action Recognition by Previewing Audio",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10454-10464",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209759"}

@inproceedings{bb214679,
        AUTHOR = "Zhang, X. and Wu, X. and Zhai, X. and Ben, X. and Tu, C.",
        TITLE = "DAVD-Net: Deep Audio-Aided Video Decompression of Talking Heads",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "12332-12341",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209760"}

@inproceedings{bb214680,
        AUTHOR = "Vaezi Joze, H.R. and Shaban, A. and Iuzzolino, M.L. and Koishida, K.",
        TITLE = "MMTM: Multimodal Transfer Module for CNN Fusion",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "13286-13296",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209761"}

@inproceedings{bb214681,
        AUTHOR = "Alcazar, J.L. and Caba, F. and Mai, L. and Perazzi, F. and Lee, J. and Arbelaez, P. and Ghanem, B.",
        TITLE = "Active Speakers in Context",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "12462-12471",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209762"}

@inproceedings{bb214682,
        AUTHOR = "Huang, C. and Koishida, K.",
        TITLE = "Improved Active Speaker Detection based on Optical Flow",
        BOOKTITLE = MULWS20,
        YEAR = "2020",
        PAGES = "4084-4090",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209763"}

@inproceedings{bb214683,
        AUTHOR = "Ma, X.J. and Wu, C.C. and Li, Y.Y. and Zhong, Q.Y.",
        TITLE = "Speaker Identification System Based on Lip-Motion Feature",
        BOOKTITLE = CVS17,
        YEAR = "2017",
        PAGES = "289-299",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209764"}

@inproceedings{bb214684,
        AUTHOR = "Xu, B. and Lu, C. and Guo, Y. and Wang, J.",
        TITLE = "Discriminative Multi-Modality Speech Recognition",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "14421-14430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209765"}

@inproceedings{bb214685,
        AUTHOR = "Wang, J. and Fang, Z. and Zhao, H.",
        TITLE = "AlignNet: A Unifying Approach to Audio-Visual Alignment",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "3298-3306",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209766"}

@inproceedings{bb214686,
        AUTHOR = "Duan, B. and Tang, H. and Wang, W. and Zong, Z.L. and Yang, G.W. and Yan, Y.",
        TITLE = "Audio-Visual Event Localization via Recursive Fusion by Joint
Co-Attention",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "4012-4021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209767"}

@inproceedings{bb214687,
        AUTHOR = "Wu, Y. and Zhu, L.C. and Yan, Y. and Yang, Y.",
        TITLE = "Dual Attention Matching for Audio-Visual Event Localization",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "6291-6299",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209768"}

@inproceedings{bb214688,
        AUTHOR = "Subedar, M. and Krishnan, R. and Meyer, P.L. and Tickoo, O. and Huang, J.",
        TITLE = "Uncertainty-Aware Audiovisual Activity Recognition Using Deep
Bayesian Variational Inference",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "6300-6309",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209769"}

@inproceedings{bb214689,
        AUTHOR = "Alamri, H. and Cartillier, V. and Das, A. and Wang, J. and Cherian, A. and Essa, I. and Batra, D. and Marks, T.K. and Hori, C. and Anderson, P. and Lee, S. and Parikh, D.",
        TITLE = "Audio Visual Scene-Aware Dialog",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "7550-7559",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209770"}

@inproceedings{bb214690,
        AUTHOR = "Niu, Y.L. and Zhang, H.W. and Zhang, M.L. and Zhang, J.H. and Lu, Z.W. and Wen, J.R.",
        TITLE = "Recursive Visual Attention in Visual Dialog",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6672-6681",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209771"}

@inproceedings{bb214691,
        AUTHOR = "Schwartz, I. and Schwing, A.G. and Hazan, T.",
        TITLE = "A Simple Baseline for Audio-Visual Scene-Aware Dialog",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "12540-12550",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209772"}

@inproceedings{bb214692,
        AUTHOR = "Lu, Y. and Lee, H. and Tseng, H. and Yang, M.",
        TITLE = "Self-Supervised Audio Spatialization with Correspondence Classifier",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "3347-3351",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209773"}

@inproceedings{bb214693,
        AUTHOR = "Liu, H. and Sun, Y.H. and Li, Y.D. and Yang, B.",
        TITLE = "3D Audio-Visual Speaker Tracking with A Novel Particle Filter",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "7343-7348",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209774"}

@inproceedings{bb214694,
        AUTHOR = "Liu, H. and Li, Y.D. and Yang, B.",
        TITLE = "3D Audio-Visual Speaker Tracking with A Two-Layer Particle Filter",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "1955-1959",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209775"}

@inproceedings{bb214695,
        AUTHOR = "Saidi, I. and Zhang, L. and Barriac, V. and Deforges, O.",
        TITLE = "Laboratory and Crowdsourcing Studies of Lip Sync Effect on the
Audio-Video Quality Assessment for Videoconferencing Application",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "3207-3211",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209776"}

@inproceedings{bb214696,
        AUTHOR = "Meng, D. and Peng, X. and Wang, K. and Qiao, Y.",
        TITLE = "Frame Attention Networks for Facial Expression Recognition in Videos",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "3866-3870",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209777"}

@inproceedings{bb214697,
        AUTHOR = "Shahid, M. and Beyan, C. and Murino, V.",
        TITLE = "Comparisons of Visual Activity Primitives for Voice Activity Detection",
        BOOKTITLE = CIAP19,
        YEAR = "2019",
        PAGES = "I:48-59",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209778"}

@inproceedings{bb214698,
        AUTHOR = "Kim, C.I. and Shin, H.J.V. and Oh, T.H. and Kaspar, A. and Elgharib, M. and Matusik, W.",
        TITLE = "On Learning Associations of Faces and Voices",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "V:276-292",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT209779"}

@inproceedings{bb214699,
        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#TT209780"}

Last update:Oct 20, 2021 at 09:45:26