@article{bb241300,
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#TT236211"}
@article{bb241301,
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#TT236212"}
@article{bb241302,
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#TT236213"}
@article{bb241303,
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#TT236214"}
@inproceedings{bb241304,
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#TT236215"}
@article{bb241305,
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#TT236216"}
@inproceedings{bb241306,
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#TT236217"}
@inproceedings{bb241307,
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#TT236218"}
@article{bb241308,
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#TT236219"}
@inproceedings{bb241309,
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#TT236220"}
@article{bb241310,
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#TT236221"}
@article{bb241311,
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#TT236222"}
@article{bb241312,
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#TT236223"}
@inproceedings{bb241313,
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#TT236224"}
@article{bb241314,
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#TT236225"}
@inproceedings{bb241315,
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#TT236226"}
@article{bb241316,
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#TT236227"}
@article{bb241317,
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#TT236228"}
@inproceedings{bb241318,
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#TT236229"}
@inproceedings{bb241319,
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#TT236230"}
@article{bb241320,
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#TT236231"}
@article{bb241321,
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#TT236232"}
@article{bb241322,
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#TT236233"}
@article{bb241323,
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#TT236234"}
@article{bb241324,
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#TT236235"}
@article{bb241325,
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#TT236236"}
@inproceedings{bb241326,
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#TT236237"}
@article{bb241327,
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#TT236238"}
@article{bb241328,
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#TT236239"}
@article{bb241329,
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#TT236240"}
@inproceedings{bb241330,
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#TT236240"}
@inproceedings{bb241331,
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#TT236241"}
@article{bb241332,
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#TT236242"}
@inproceedings{bb241333,
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#TT236243"}
@article{bb241334,
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#TT236244"}
@inproceedings{bb241335,
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#TT236245"}
@article{bb241336,
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#TT236246"}
@article{bb241337,
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#TT236247"}
@article{bb241338,
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#TT236248"}
@inproceedings{bb241339,
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#TT236249"}
@inproceedings{bb241340,
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#TT236250"}
@article{bb241341,
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#TT236251"}
@article{bb241342,
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#TT236252"}
@article{bb241343,
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#TT236253"}
@inproceedings{bb241344,
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#TT236254"}
@inproceedings{bb241345,
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#TT236255"}
@inproceedings{bb241346,
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#TT236256"}
@inproceedings{bb241347,
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#TT236257"}
@article{bb241348,
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#TT236258"}
@article{bb241349,
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#TT236259"}
@article{bb241350,
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#TT236260"}
@article{bb241351,
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#TT236261"}
@article{bb241352,
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#TT236262"}
@article{bb241353,
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#TT236263"}
@article{bb241354,
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#TT236264"}
@article{bb241355,
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#TT236265"}
@inproceedings{bb241356,
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#TT236266"}
@article{bb241357,
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#TT236267"}
@article{bb241358,
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#TT236268"}
@article{bb241359,
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#TT236269"}
@article{bb241360,
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#TT236270"}
@inproceedings{bb241361,
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#TT236271"}
@article{bb241362,
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#TT236272"}
@article{bb241363,
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#TT236273"}
@article{bb241364,
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#TT236274"}
@article{bb241365,
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#TT236275"}
@article{bb241366,
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#TT236276"}
@article{bb241367,
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#TT236277"}
@article{bb241368,
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#TT236278"}
@article{bb241369,
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#TT236279"}
@inproceedings{bb241370,
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#TT236280"}
@article{bb241371,
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#TT236281"}
@article{bb241372,
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#TT236282"}
@inproceedings{bb241373,
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#TT236283"}
@article{bb241374,
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#TT236284"}
@inproceedings{bb241375,
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#TT236285"}
@inproceedings{bb241376,
AUTHOR = "Feng, D. and Yang, S. and Shan, S.G. and Chen, X.L.",
TITLE = "Audio-Driven Deformation Flow for Effective Lip Reading",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "274-280",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236286"}
@inproceedings{bb241377,
AUTHOR = "Varshney, M. and Yadav, R. and Namboodiri, V.P. and Hegde, R.M.",
TITLE = "Learning Speaker-specific Lip-to-Speech Generation",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "491-498",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236287"}
@inproceedings{bb241378,
AUTHOR = "Shi, C. and Yang, S.",
TITLE = "Spatial and Visual Perspective-Taking via View Rotation and Relation
Reasoning for Embodied Reference Understanding",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:201-218",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236288"}
@inproceedings{bb241379,
AUTHOR = "Hayes, T. and Zhang, S. and Yin, X. and Pang, G. and Sheng, S. and Yang, H. and Ge, S. and Hu, Q.Y. and Parikh, D.",
TITLE = "MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and
GENeration",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "VIII:431-449",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236289"}
@inproceedings{bb241380,
AUTHOR = "van Horn, G. and Qian, R. and Wilber, K. and Adam, H. and Aodha, O.M. and Belongie, S.",
TITLE = "Exploring Fine-Grained Audiovisual Categorization with the SSW60
Dataset",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "VIII:271-289",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236290"}
@inproceedings{bb241381,
AUTHOR = "Yu, S. and Wu, P. and Liang, P.P. and Salakhutdinov, R. and Morency, L.P.",
TITLE = "PACS: A Dataset for Physical Audiovisual CommonSense Reasoning",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:292-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236291"}
@inproceedings{bb241382,
AUTHOR = "Cheng, H.Y. and Liu, Z.Y. and Zhou, H. and Qian, C. and Wu, W. and Wang, L.M.",
TITLE = "Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video
Parsing",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXIV:431-448",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236292"}
@inproceedings{bb241383,
AUTHOR = "Zhang, Z.Q. and Zhang, J. and Zhang, J.S. and Wu, M.H. and Fang, X. and Dai, L.R.",
TITLE = "Learning Contextually Fused Audio-Visual Representations for
Audio-Visual Speech Recognition",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "1346-1350",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236293"}
@inproceedings{bb241384,
AUTHOR = "Mo, S.T. and Morgado, P.",
TITLE = "Localizing Visual Sounds the Easy Way",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:218-234",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236294"}
@inproceedings{bb241385,
AUTHOR = "Montesinos, J.F. and Kadandale, V.S. and Haro, G.",
TITLE = "VoViT: Low Latency Graph-Based Audio-Visual Voice Separation
Transformer",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:310-326",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236295"}
@inproceedings{bb241386,
AUTHOR = "Tzinis, E. and Wisdom, S. and Remez, T. and Hershey, J.R.",
TITLE = "AudioScopeV2: Audio-Visual Attention Architectures for Calibrated
Open-Domain On-Screen Sound Separation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:368-385",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236296"}
@inproceedings{bb241387,
AUTHOR = "Zhou, J.X. and Wang, J. and Zhang, J.Y. and Sun, W. and Zhang, J. and Birchfield, S. and Guo, D. and Kong, L. and Wang, M. and Zhong, Y.",
TITLE = "Audio-Visual Segmentation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:386-403",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236297"}
@inproceedings{bb241388,
AUTHOR = "Alcazar, J.L. and Cordes, M. and Zhao, C. and Ghanem, B.",
TITLE = "End-to-End Active Speaker Detection",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:126-143",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236298"}
@inproceedings{bb241389,
AUTHOR = "Chen, C.G. and Gao, R.H. and Calamia, P. and Grauman, K.",
TITLE = "Visual Acoustic Matching",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18836-18846",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236299"}
@inproceedings{bb241390,
AUTHOR = "Lee, S. and Kim, H.I. and Ro, Y.M.",
TITLE = "Weakly Paired Associative Learning for Sound and Image
Representations via Bimodal Associative Memory",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10524-10533",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236300"}
@inproceedings{bb241391,
AUTHOR = "Vasudevan, A.B. and Dai, D.X. and Van Gool, L.J.",
TITLE = "Sound and Visual Representation Learning with Multiple Pretraining
Tasks",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "14596-14606",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236301"}
@inproceedings{bb241392,
AUTHOR = "Xia, Y. and Zhao, Z.",
TITLE = "Cross-modal Background Suppression for Audio-Visual Event
Localization",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19957-19966",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236302"}
@inproceedings{bb241393,
AUTHOR = "Jiang, H. and Murdock, C. and Ithapu, V.K.",
TITLE = "Egocentric Deep Multi-Channel Audio-Visual Active Speaker
Localization",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10534-10542",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236303"}
@inproceedings{bb241394,
AUTHOR = "Ng, E. and Joo, H. and Hu, L.W. and Li, H. and Darrell, T.J. and Kanazawa, A. and Ginosar, S.",
TITLE = "Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "20363-20373",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236304"}
@inproceedings{bb241395,
AUTHOR = "Mercea, O.B. and Hummel, T. and Koepke, A.S. and Akata, Z.",
TITLE = "Temporal and Cross-modal Attention for Audio-Visual Zero-Shot Learning",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XX:488-505",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236305"}
@inproceedings{bb241396,
AUTHOR = "Mercea, O.B. and Riesch, L. and Koepke, A.S. and Akata, Z.",
TITLE = "Audiovisual Generalised Zero-shot Learning with Cross-modal Attention
and Language",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10543-10553",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236306"}
@inproceedings{bb241397,
AUTHOR = "Karas, V. and Tellamekala, M.K. and Mallol Ragolta, A. and Valstar, M. and Schuller, B.W.",
TITLE = "Time-Continuous Audiovisual Fusion with Recurrence vs Attention for
In-The-Wild Affect Recognition",
BOOKTITLE = ABAW22,
YEAR = "2022",
PAGES = "2381-2390",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236307"}
@inproceedings{bb241398,
AUTHOR = "Yang, K. and Markovic, D. and Krenn, S. and Agrawal, V. and Richard, A.",
TITLE = "Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech
Enhancement by Re-Synthesis",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "8217-8227",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236308"}
@inproceedings{bb241399,
AUTHOR = "Kim, M. and Hong, J. and Park, S.J. and Ro, Y.M.",
TITLE = "Multi-modality Associative Bridging through Memory:
Speech Sound Recollected from Face Video",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "296-306",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236309"}
Last update: