@inproceedings{bb256400,
        AUTHOR = "Chen, Y.B. and Xian, Y.Q. and Koepke, A.S. and Shan, Y. and Akata, Z.",
        TITLE = "Distilling Audio-Visual Knowledge by Compositional Contrastive
Learning",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "7012-7021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251210"}

@inproceedings{bb256401,
        AUTHOR = "Zhang, Z.M. and Li, L.C. and Ding, Y. and Fan, C.J.",
        TITLE = "Flow-guided One-shot Talking Face Generation with a High-resolution
Audio-visual Dataset",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "3660-3669",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251211"}

@inproceedings{bb256402,
        AUTHOR = "Gao, R. and Grauman, K.",
        TITLE = "VisualVoice: Audio-Visual Speech Separation with Cross-Modal
Consistency",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "15490-15500",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251212"}

@inproceedings{bb256403,
        AUTHOR = "Lee, J.Y. and Chung, S.W. and Kim, S. and Kang, H.G. and Sohn, K.H.",
        TITLE = "Looking into Your Speech: Learning Cross-modal Affinity for
Audio-visual Speech Separation",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "1336-1345",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251213"}

@inproceedings{bb256404,
        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#TT251214"}

@inproceedings{bb256405,
        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#TT251215"}

@inproceedings{bb256406,
        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#TT251216"}

@inproceedings{bb256407,
        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#TT251217"}

@inproceedings{bb256408,
        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#TT251218"}

@inproceedings{bb256409,
        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#TT251219"}

@inproceedings{bb256410,
        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#TT251220"}

@inproceedings{bb256411,
        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#TT251221"}

@inproceedings{bb256412,
        AUTHOR = "Zhou, H. and Xu, X.D. and Lin, D. and Wang, X.G. and Liu, Z.W.",
        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#TT251222"}

@inproceedings{bb256413,
        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#TT251223"}

@inproceedings{bb256414,
        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#TT251224"}

@inproceedings{bb256415,
        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#TT251225"}

@inproceedings{bb256416,
        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#TT251226"}

@inproceedings{bb256417,
        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#TT251227"}

@inproceedings{bb256418,
        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#TT251228"}

@inproceedings{bb256419,
        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#TT251229"}

@inproceedings{bb256420,
        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#TT251230"}

@inproceedings{bb256421,
        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#TT251231"}

@inproceedings{bb256422,
        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#TT251232"}

@inproceedings{bb256423,
        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#TT251233"}

@inproceedings{bb256424,
        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#TT251234"}

@inproceedings{bb256425,
        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#TT251235"}

@inproceedings{bb256426,
        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#TT251236"}

@inproceedings{bb256427,
        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#TT251237"}

@inproceedings{bb256428,
        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#TT251238"}

@inproceedings{bb256429,
        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#TT251239"}

@inproceedings{bb256430,
        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#TT251240"}

@inproceedings{bb256431,
        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#TT251241"}

@inproceedings{bb256432,
        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#TT251242"}

@inproceedings{bb256433,
        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#TT251243"}

@inproceedings{bb256434,
        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#TT251244"}

@inproceedings{bb256435,
        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#TT251245"}

@inproceedings{bb256436,
        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#TT251246"}

@inproceedings{bb256437,
        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#TT251247"}

@inproceedings{bb256438,
        AUTHOR = "Oliveira, D.A.B. and Mattos, A.B. and da Silva Morais, E.",
        TITLE = "Improving Viseme Recognition Using GAN-Based Frontal View Mapping",
        BOOKTITLE = AMFG18,
        YEAR = "2018",
        PAGES = "2229-22297",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251248"}

@inproceedings{bb256439,
        AUTHOR = "Yang, X. and Molchanov, P. and Kautz, J.",
        TITLE = "Making Convolutional Networks Recurrent for Visual Sequence Learning",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6469-6478",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251249"}

@inproceedings{bb256440,
        AUTHOR = "Zhang, J. and Richmond, K. and Fisher, R.B.",
        TITLE = "Dual-modality Talking-metrics: 3D Visual-Audio Integrated
Behaviometric Cues from Speakers",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3144-3149",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251250"}

@inproceedings{bb256441,
        AUTHOR = "Chowdhury, A. and Atoum, Y. and Tran, L. and Liu, X. and Ross, A.",
        TITLE = "MSU-AVIS dataset: Fusing Face and Voice Modalities for Biometric
Recognition in Indoor Surveillance Videos",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3567-3573",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251251"}

@inproceedings{bb256442,
        AUTHOR = "Nagrani, A. and Albanie, S. and Zisserman, A.",
        TITLE = "Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "8427-8436",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251252"}

@inproceedings{bb256443,
        AUTHOR = "Saitoh, T. and Kubokawa, M.",
        TITLE = "SSSD: Speech Scene database by Smart Device for Visual Speech
Recognition",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3228-3232",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251253"}

@inproceedings{bb256444,
        AUTHOR = "Owens, A. and Efros, A.A.",
        TITLE = "Audio-Visual Scene Analysis with Self-Supervised Multisensory Features",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VI: 639-658",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251254"}

@inproceedings{bb256445,
        AUTHOR = "Berlin, A.A. and Surati, R.",
        TITLE = "Video Deconfounding: Hearing-Aid Inspired Video Enhancement",
        BOOKTITLE = IVMSP18,
        YEAR = "2018",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251255"}

@inproceedings{bb256446,
        AUTHOR = "Ding, R. and Pang, C. and Liu, H.",
        TITLE = "Audio-Visual Keyword Spotting Based on Multidimensional Convolutional
Neural Network",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "4138-4142",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251256"}

@inproceedings{bb256447,
        AUTHOR = "Liao, J. and Wang, S. and Zhang, X. and Liu, G.",
        TITLE = "3D Convolutional Neural Networks Based Speaker Identification and
Authentication",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "2042-2046",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251257"}

@inproceedings{bb256448,
        AUTHOR = "Savran, A. and Tavarone, R. and Higy, B. and Badino, L. and Bartolozzi, C.",
        TITLE = "Energy and Computation Efficient Audio-Visual Voice Activity
Detection Driven by Event-Cameras",
        BOOKTITLE = FG18,
        YEAR = "2018",
        PAGES = "333-340",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251258"}

@inproceedings{bb256449,
        AUTHOR = "Ephrat, A. and Halperin, T. and Peleg, S.",
        TITLE = "Improved Speech Reconstruction from Silent Video",
        BOOKTITLE = CVAVM17,
        YEAR = "2017",
        PAGES = "455-462",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251259"}

@inproceedings{bb256450,
        AUTHOR = "Ahn, J. and Kim, Y.J. and Kim, D.J.",
        TITLE = "Patch-based visual microphone for improving quality of sound",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "3927-3932",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251260"}

@inproceedings{bb256451,
        AUTHOR = "Chung, J.S. and Zisserman, A.",
        TITLE = "Out of Time: Automated Lip Sync in the Wild",
        BOOKTITLE = LipRead16,
        YEAR = "2016",
        PAGES = "II: 251-263",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251261"}

@inproceedings{bb256452,
        AUTHOR = "Miao, C.L. and Feng, J.W. and Ding, Y. and Yang, Y. and Chen, X.G. and Ji, X.Y.",
        TITLE = "Unsupervised person clustering in videos with cross-modal
communication",
        BOOKTITLE = VCIP16,
        YEAR = "2016",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251262"}

@inproceedings{bb256453,
        AUTHOR = "Hu, D. and Li, X.L. and Lu, X.Q.",
        TITLE = "Temporal Multimodal Learning in Audiovisual Speech Recognition",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "3574-3582",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251263"}

@inproceedings{bb256454,
        AUTHOR = "Liu, H. and Fan, T. and Wu, P.P.",
        TITLE = "Audio-visual Keyword Spotting for Mandarin Based on Discriminative
Local Spatial-Temporal Descriptors",
        BOOKTITLE = ICPR14,
        YEAR = "2014",
        PAGES = "785-790",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251264"}

@inproceedings{bb256455,
        AUTHOR = "Ringeval, F. and Sonderegger, A. and Sauer, J. and Lalanne, D.",
        TITLE = "Introducing the RECOLA multimodal corpus of remote collaborative and
affective interactions",
        BOOKTITLE = FG13,
        YEAR = "2013",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251265"}

@inproceedings{bb256456,
        AUTHOR = "Aubrey, A.J. and Cunningham, D.W. and Marshall, D. and Rosin, P.L. and Shin, A.",
        TITLE = "The Face Speaks:
Contextual and Temporal Sensitivity to Backchannel Responses",
        BOOKTITLE = FaceCVHum12,
        YEAR = "2012",
        PAGES = "II:248-259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251266"}

@inproceedings{bb256457,
        AUTHOR = "Tawari, A. and Trivedi, M.",
        TITLE = "Audio-visual data association for face expression analysis",
        BOOKTITLE = ICPR12,
        YEAR = "2012",
        PAGES = "1120-1123",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251267"}

@inproceedings{bb256458,
        AUTHOR = "Taj, M. and Cavallaro, A.",
        TITLE = "Interaction recognition in wide areas using audiovisual sensors",
        BOOKTITLE = ICIP12,
        YEAR = "2012",
        PAGES = "1113-1116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251268"}

@inproceedings{bb256459,
        AUTHOR = "Giorgolo, G.",
        TITLE = "Integration of Gesture and Verbal Language: A Formal Semantics Approach",
        BOOKTITLE = GW11,
        YEAR = "2011",
        PAGES = "216-227",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251269"}

@inproceedings{bb256460,
        AUTHOR = "Le, Q.A. and Pelachaud, C.",
        TITLE = "Generating Co-speech Gestures for the Humanoid Robot NAO through BML",
        BOOKTITLE = GW11,
        YEAR = "2011",
        PAGES = "228-237",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251270"}

@inproceedings{bb256461,
        AUTHOR = "Navarathna, R. and Dean, D. and Sridharan, S. and Fookes, C. and Lucey, P.",
        TITLE = "Visual Voice Activity Detection Using Frontal versus Profile Views",
        BOOKTITLE = DICTA11,
        YEAR = "2011",
        PAGES = "134-139",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251271"}

@inproceedings{bb256462,
        AUTHOR = "Komai, Y. and Ariki, Y. and Takiguchi, T.",
        TITLE = "Audio-Visual Speech Recognition Based on AAM Parameter and Phoneme
Analysis of Visual Feature",
        BOOKTITLE = PSIVT11,
        YEAR = "2011",
        PAGES = "I: 97-108",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251272"}

@inproceedings{bb256463,
        AUTHOR = "Zheng, H.M. and Wang, M. and Li, Z.",
        TITLE = "Audio-visual speaker identification with multi-view distance metric
learning",
        BOOKTITLE = ICIP10,
        YEAR = "2010",
        PAGES = "4561-4564",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251273"}

@inproceedings{bb256464,
        AUTHOR = "Krishnan, R.K. and Sarkar, S.",
        TITLE = "Similarity Measure between Two Gestures Using Triplets",
        BOOKTITLE = HAU3D13,
        YEAR = "2013",
        PAGES = "506-513",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251274"}

@inproceedings{bb256465,
        AUTHOR = "Krishnan, R.K. and Sarkar, S.",
        TITLE = "Detecting Group Turn Patterns in Conversations Using Audio-Video Change
Scale-Space",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "137-140",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251275"}

@inproceedings{bb256466,
        AUTHOR = "Aran, O. and Gatica Perez, D.",
        TITLE = "Fusing Audio-Visual Nonverbal Cues to Detect Dominant People in Group
Conversations",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "3687-3690",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251276"}

@inproceedings{bb256467,
        AUTHOR = "Niese, R. and Al Hamadi, A. and Michaelis, B.",
        TITLE = "A New Multi-camera Based Facial Expression Analysis Concept",
        BOOKTITLE = ICIAR12,
        YEAR = "2012",
        PAGES = "II: 64-71",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251277"}

@inproceedings{bb256468,
        AUTHOR = "Steer, M.A. and Al Hamadi, A. and Michaelis, B.",
        TITLE = "Audio-Visual Data Fusion Using a Particle Filter in the Application of
Face Recognition",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "4392-4395",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251278"}

@inproceedings{bb256469,
        AUTHOR = "Roy, A. and Marcel, S.",
        TITLE = "Crossmodal Matching of Speakers Using Lip and Voice Features in
Temporally Non-overlapping Audio and Video Streams",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "4504-4507",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251279"}

@inproceedings{bb256470,
        AUTHOR = "Cour, T. and Sapp, B. and Nagle, A. and Taskar, B.",
        TITLE = "Talking pictures:
Temporal grouping and dialog-supervised person recognition",
        BOOKTITLE = CVPR10,
        YEAR = "2010",
        PAGES = "1014-1021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251280"}

@inproceedings{bb256471,
        AUTHOR = "Wu, G.Y. and Zhu, J. and Xu, H.H.",
        TITLE = "A hybrid visual feature extraction method for audio-visual speech
recognition",
        BOOKTITLE = ICIP09,
        YEAR = "2009",
        PAGES = "1829-1832",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251281"}

@inproceedings{bb256472,
        AUTHOR = "Ceballos, A. and Gomez, J. and Prieto, F. and Redarce, T.",
        TITLE = "Robot Command Interface Using an Audio-Visual Speech Recognition System",
        BOOKTITLE = CIARP09,
        YEAR = "2009",
        PAGES = "869-876",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251282"}

@inproceedings{bb256473,
        AUTHOR = "Cifani, S. and Abel, A. and Hussain, A. and Squartini, S. and Piazza, F.",
        TITLE = "An Investigation into Audiovisual Speech Correlation in Reverberant
Noisy Environments",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "331-343",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251283"}

@inproceedings{bb256474,
        AUTHOR = "Fanelli, G. and Gall, J. and Van Gool, L.J.",
        TITLE = "Hough transform-based mouth localization for audio-visual speech
recognition",
        BOOKTITLE = BMVC09,
        YEAR = "2009",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251284"}

@inproceedings{bb256475,
        AUTHOR = "Cadavid, S. and Abdel Mottaleb, M. and Messinger, D.S. and Mahoor, M.H. and Bahrick, L.E.",
        TITLE = "Detecting local audio-visual synchrony in monologues utilizing vocal
pitch and facial landmark trajectories",
        BOOKTITLE = BMVC09,
        YEAR = "2009",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251285"}

@inproceedings{bb256476,
        AUTHOR = "Lee, J.S. and Ebrahimi, T.",
        TITLE = "Two-Level Bimodal Association for Audio-Visual Speech Recognition",
        BOOKTITLE = ACIVS09,
        YEAR = "2009",
        PAGES = "133-144",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251286"}

@inproceedings{bb256477,
        AUTHOR = "Marchegiani, M.L. and Pirri, F. and Pizzoli, M.",
        TITLE = "Multimodal Speaker Recognition in a Conversation Scenario",
        BOOKTITLE = CVS09,
        YEAR = "2009",
        PAGES = "11-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251287"}

@inproceedings{bb256478,
        AUTHOR = "Kumar, K. and Navratil, J. and Marcheret, E. and Libal, V. and Ramaswamy, G. and Potamianos, G.",
        TITLE = "Audio-visual speech synchronization detection using a bimodal linear
prediction model",
        BOOKTITLE = Biometrics09,
        YEAR = "2009",
        PAGES = "53-59",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251288"}

@inproceedings{bb256479,
        AUTHOR = "Karam, W. and Mokbel, C. and Greige, H. and Chollet, G.",
        TITLE = "Audio-Visual Identity Verification and Robustness to Imposture",
        BOOKTITLE = ICB09,
        YEAR = "2009",
        PAGES = "796-805",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251289"}

@inproceedings{bb256480,
        AUTHOR = "Rebillat, M. and Katz, B.F.G. and Corteel, E.",
        TITLE = "SMART-I2: Spatial Multi-user Audio-visual Real-time interactive
interface, A broadcast application context",
        BOOKTITLE = "3DTV09",
        YEAR = "2009",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251290"}

@inproceedings{bb256481,
        AUTHOR = "Eisenstein, J.",
        TITLE = "Gesture in Automatic Discourse Processing",
        BOOKTITLE = CSAIL,
        YEAR = "2008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251291"}

@inproceedings{bb256482,
        AUTHOR = "Eisenstein, J.",
        TITLE = "Gesture in Automatic Discourse Processing",
        BOOKTITLE = Ph.D.,
        YEAR = "2008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251291"}

@inproceedings{bb256483,
        AUTHOR = "Das, A. and Manyam, O.K. and Tapaswi, M.",
        TITLE = "Audio-Visual Person Authentication with Multiple Visualized-Speech
Features and Multiple Face Profiles",
        BOOKTITLE = ICCVGIP08,
        YEAR = "2008",
        PAGES = "39-46",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251292"}

@inproceedings{bb256484,
        AUTHOR = "Cao, Y. and Baang, S. and Liu, S.H. and Li, M. and Hu, S.Q.",
        TITLE = "Audio-visual event classification via spatial-temporal-audio words",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251293"}

@inproceedings{bb256485,
        AUTHOR = "Terry, L.H. and Shiell, D.J. and Katsaggelos, A.K.",
        TITLE = "Feature space video stream consistency estimation for dynamic stream
weighting in audio-visual speech recognition",
        BOOKTITLE = ICIP08,
        YEAR = "2008",
        PAGES = "1316-1319",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251294"}

@inproceedings{bb256486,
        AUTHOR = "Naseem, I. and Mian, A.S.",
        TITLE = "User Verification by Combining Speech and Face Biometrics in Video",
        BOOKTITLE = ISVC08,
        YEAR = "2008",
        PAGES = "II: 482-492",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251295"}

@inproceedings{bb256487,
        AUTHOR = "Ettinger, E. and Freund, Y.",
        TITLE = "Coordinate-free calibration of an acoustically driven camera pointing
system",
        BOOKTITLE = ICDSC08,
        YEAR = "2008",
        PAGES = "1-9",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251296"}

@inproceedings{bb256488,
        AUTHOR = "Hung, H. and Friedland, G.",
        TITLE = "Towards Audio-Visual On-line Diarization Of Participants In Group
Meetings",
        BOOKTITLE = M2SFA208,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251297"}

@inproceedings{bb256489,
        AUTHOR = "Liu, Y.Y. and Sato, Y.",
        TITLE = "Finding Speaker Face Region by Audiovisual Correlation",
        BOOKTITLE = M2SFA208,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251298"}

@inproceedings{bb256490,
        AUTHOR = "Kelly, D. and Pitie, F. and Kokaram, A. and Boland, F.",
        TITLE = "A Comparative Error Analysis of Audio-Visual Source Localization",
        BOOKTITLE = M2SFA208,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251299"}

@inproceedings{bb256491,
        AUTHOR = "Pachoud, S. and Gong, S. and Cavallaro, A.",
        TITLE = "Video Augmentation for Improving Audio Speech Recognition under Noise",
        BOOKTITLE = BMVC08,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251300"}

@inproceedings{bb256492,
        AUTHOR = "Horii, Y. and Kawashima, H. and Matsuyama, T.",
        TITLE = "Speaker detection using the timing structure of lip motion and sound",
        BOOKTITLE = CVPR4HB08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251301"}

@inproceedings{bb256493,
        AUTHOR = "Rua, E.A. and Castro, J.L.A. and Mateo, C.G.",
        TITLE = "Quality-Based Score Normalization for Audiovisual Person Authentication",
        BOOKTITLE = ICIAR08,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251302"}

@inproceedings{bb256494,
        AUTHOR = "Wang, L. and Tjondrongoro, D. and Liu, Y.",
        TITLE = "Clustering and Visualizing Audio-Visual Dataset on Mobile Devices in a
Topic-Oriented Manner",
        BOOKTITLE = Visual07,
        YEAR = "2007",
        PAGES = "310-321",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251303"}

@inproceedings{bb256495,
        AUTHOR = "Zajdel, W. and Krijnders, J.D. and Andringa, T. and Gavrila, D.M.",
        TITLE = "CASSANDRA: audio-video sensor fusion for aggression detection",
        BOOKTITLE = AVSBS07,
        YEAR = "2007",
        PAGES = "200-205",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251304"}

@inproceedings{bb256496,
        AUTHOR = "Stodle, D. and Bjorndalen, J.M. and Anshus, O.J.",
        TITLE = "A System for Hybrid Vision- and Sound-Based Interaction with Distal and
Proximal Targets on Wall-Sized, High-Resolution Tiled Displays",
        BOOKTITLE = CVHCI07,
        YEAR = "2007",
        PAGES = "59-68",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251305"}

@inproceedings{bb256497,
        AUTHOR = "van Hengel, P.W.J. and Andringa, T.C.",
        TITLE = "Verbal aggression detection in complex social environments",
        BOOKTITLE = AVSBS07,
        YEAR = "2007",
        PAGES = "15-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251306"}

@inproceedings{bb256498,
        AUTHOR = "Ikeda, O.",
        TITLE = "Detection of a Speaker in Video by Combined Analysis of Speech Sound
and Mouth Movement",
        BOOKTITLE = ISVC07,
        YEAR = "2007",
        PAGES = "II: 602-610",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251307"}

@inproceedings{bb256499,
        AUTHOR = "Das, A.",
        TITLE = "Audio Visual Person Authentication by Multiple Nearest Neighbor
Classifiers",
        BOOKTITLE = ICB07,
        YEAR = "2007",
        PAGES = "1114-1123",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT251308"}