@inproceedings{bb193600,
        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#TT188858"}

@article{bb193601,
        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#TT188859"}

@article{bb193602,
        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#TT188860"}

@article{bb193603,
        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#TT188861"}

@inproceedings{bb193604,
        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#TT188862"}

@inproceedings{bb193605,
        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#TT188863"}

@article{bb193606,
        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#TT188864"}

@article{bb193607,
        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#TT188865"}

@article{bb193608,
        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#TT188866"}

@inproceedings{bb193609,
        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#TT188867"}

@inproceedings{bb193610,
        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#TT188868"}

@inproceedings{bb193611,
        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#TT188869"}

@inproceedings{bb193612,
        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#TT188870"}

@article{bb193613,
        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#TT188871"}

@article{bb193614,
        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#TT188872"}

@article{bb193615,
        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#TT188873"}

@article{bb193616,
        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#TT188874"}

@article{bb193617,
        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#TT188875"}

@article{bb193618,
        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#TT188876"}

@article{bb193619,
        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#TT188877"}

@article{bb193620,
        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#TT188878"}

@inproceedings{bb193621,
        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#TT188879"}

@article{bb193622,
        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#TT188880"}

@article{bb193623,
        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#TT188881"}

@article{bb193624,
        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#TT188882"}

@article{bb193625,
        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#TT188883"}

@article{bb193626,
        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#TT188884"}

@inproceedings{bb193627,
        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#TT188885"}

@inproceedings{bb193628,
        AUTHOR = "Wang, X. and Huang, Q. and Celikyilmaz, A. and Gao, J.F. and Shen, D. and Wang, Y.F. and Wang, W.Y. and Zhang, L.",
        TITLE = "Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning
for Vision-Language Navigation",
        BOOKTITLE = "CVPR19",
        YEAR = "2019",
        PAGES = "6622-6631",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT188886"}

@inproceedings{bb193629,
        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#TT188887"}

@inproceedings{bb193630,
        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#TT188888"}

@inproceedings{bb193631,
        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#TT188889"}

@inproceedings{bb193632,
        AUTHOR = "Liu, H. and Li, Y. 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#TT188890"}

@inproceedings{bb193633,
        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#TT188891"}

@inproceedings{bb193634,
        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#TT188892"}

@inproceedings{bb193635,
        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#TT188893"}

@inproceedings{bb193636,
        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#TT188894"}

@inproceedings{bb193637,
        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#TT188895"}

@inproceedings{bb193638,
        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#TT188896"}

@inproceedings{bb193639,
        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#TT188897"}

@inproceedings{bb193640,
        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#TT188898"}

@inproceedings{bb193641,
        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#TT188899"}

@inproceedings{bb193642,
        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#TT188900"}

@inproceedings{bb193643,
        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#TT188901"}

@inproceedings{bb193644,
        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#TT188902"}

@inproceedings{bb193645,
        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#TT188903"}

@inproceedings{bb193646,
        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#TT188904"}

@inproceedings{bb193647,
        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#TT188905"}

@inproceedings{bb193648,
        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#TT188906"}

@inproceedings{bb193649,
        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#TT188907"}

@inproceedings{bb193650,
        AUTHOR = "Ban, Y. 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#TT188908"}

@inproceedings{bb193651,
        AUTHOR = "Le, N. and Heili, A. and Wu, D. and Odobez, J.M.",
        TITLE = "Temporally subsampled detection for accurate and efficient face
tracking and diarization",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "1792-1797",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT188909"}

@inproceedings{bb193652,
        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#TT188910"}

@inproceedings{bb193653,
        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#TT188911"}

@inproceedings{bb193654,
        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#TT188912"}

@inproceedings{bb193655,
        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#TT188913"}

@inproceedings{bb193656,
        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#TT188914"}

@inproceedings{bb193657,
        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#TT188915"}

@inproceedings{bb193658,
        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#TT188916"}

@inproceedings{bb193659,
        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#TT188917"}

@inproceedings{bb193660,
        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#TT188918"}

@inproceedings{bb193661,
        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#TT188919"}

@inproceedings{bb193662,
        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#TT188920"}

@inproceedings{bb193663,
        AUTHOR = "Saeed, A. and Al Hamadi, A. and Heuer, M.",
        TITLE = "Speaker Tracking Using Multi-modal Fusion Framework",
        BOOKTITLE = ICISP12,
        YEAR = "2012",
        PAGES = "539-546",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT188921"}

@inproceedings{bb193664,
        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#TT188922"}

@inproceedings{bb193665,
        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#TT188923"}

@inproceedings{bb193666,
        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#TT188924"}

@inproceedings{bb193667,
        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#TT188925"}

@inproceedings{bb193668,
        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#TT188926"}

@inproceedings{bb193669,
        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#TT188927"}

@inproceedings{bb193670,
        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#TT188928"}

@inproceedings{bb193671,
        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#TT188929"}

@inproceedings{bb193672,
        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#TT188930"}

@inproceedings{bb193673,
        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#TT188931"}

@inproceedings{bb193674,
        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#TT188932"}

@inproceedings{bb193675,
        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#TT188933"}

@inproceedings{bb193676,
        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#TT188934"}

@inproceedings{bb193677,
        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#TT188935"}

@inproceedings{bb193678,
        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#TT188936"}

@inproceedings{bb193679,
        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#TT188937"}

@inproceedings{bb193680,
        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#TT188938"}

@inproceedings{bb193681,
        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#TT188939"}

@inproceedings{bb193682,
        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#TT188940"}

@inproceedings{bb193683,
        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#TT188941"}

@inproceedings{bb193684,
        AUTHOR = "Eisenstein, J.",
        TITLE = "Gesture in Automatic Discourse Processing",
        BOOKTITLE = CSAIL,
        YEAR = "2008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT188942"}

@inproceedings{bb193685,
        AUTHOR = "Eisenstein, J.",
        TITLE = "Gesture in Automatic Discourse Processing",
        BOOKTITLE = Ph.D.,
        YEAR = "2008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT188942"}

@inproceedings{bb193686,
        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#TT188943"}

@inproceedings{bb193687,
        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#TT188944"}

@inproceedings{bb193688,
        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#TT188945"}

@inproceedings{bb193689,
        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#TT188946"}

@inproceedings{bb193690,
        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#TT188947"}

@inproceedings{bb193691,
        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#TT188948"}

@inproceedings{bb193692,
        AUTHOR = "Liu, 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#TT188949"}

@inproceedings{bb193693,
        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#TT188950"}

@inproceedings{bb193694,
        AUTHOR = "Katsarakis, N. and Talantzis, F. and Pnevmatikakis, A. and Polymenakos, L.",
        TITLE = "The AIT 3D Audio / Visual Person Tracker for CLEAR 2007",
        BOOKTITLE = MTPH07,
        YEAR = "2007",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT188951"}

@inproceedings{bb193695,
        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#TT188952"}

@inproceedings{bb193696,
        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#TT188953"}

@inproceedings{bb193697,
        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#TT188954"}

@inproceedings{bb193698,
        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#TT188955"}

@inproceedings{bb193699,
        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#TT188956"}

Last update:Apr 6, 2020 at 18:30:45