@book{bb259700,
AUTHOR = "Sharma, P. and Reilly, R.B.",
TITLE = "The UCD Colour Face Image Database for Face Detection",
PUBLISHER = "Online",
YEAR = "1998",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254491"}
@inproceedings{bb259701,
AUTHOR = "Fox, N.A. and O'Mullane, B.A. and Reilly, R.B.",
TITLE = "Audio-Visual Speaker Identification via Adaptive Fusion Using
Reliability Estimates of Both Modalities",
BOOKTITLE = AVBPA05,
YEAR = "2005",
PAGES = "787",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254492"}
@inproceedings{bb259702,
AUTHOR = "Zhang, D. and Ghobakhlou, A. and Kasabov, N.",
TITLE = "An adaptive model of person identification combining speech and image
information",
BOOKTITLE = ICARCV04,
YEAR = "2004",
PAGES = "I: 413-418",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254493"}
@inproceedings{bb259703,
AUTHOR = "Kratt, J. and Metze, F. and Stiefelhagen, R. and Waibel, A.",
TITLE = "Large Vocabulary Audio-Visual Speech Recognition Using the Janus Speech
Recognition Toolkit",
BOOKTITLE = DAGM04,
YEAR = "2004",
PAGES = "488-495",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254494"}
@inproceedings{bb259704,
AUTHOR = "Hanafiah, Z.M. and Yamazaki, C. and Nakamura, A. and Kuno, Y.",
TITLE = "Understanding inexplicit utterances using vision for helper robots",
BOOKTITLE = ICPR04,
YEAR = "2004",
PAGES = "IV: 925-928",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254495"}
@inproceedings{bb259705,
AUTHOR = "Hermann, T. and Henning, T. and Ritter, H.",
TITLE = "Gesture Desk an Integrated Multi-modal Gestural Workplace
for Sonification",
BOOKTITLE = GW03,
YEAR = "2003",
PAGES = "369-379",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254496"}
@inproceedings{bb259706,
AUTHOR = "Merola, G.",
TITLE = "The Effects of the Gesture Viewpoint on the Students' Memory of Words
and Stories",
BOOKTITLE = GW07,
YEAR = "2007",
PAGES = "272-281",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254497"}
@inproceedings{bb259707,
AUTHOR = "Merola, G. and Poggi, I.",
TITLE = "Multimodality and Gestures in the Teacher's Communication",
BOOKTITLE = GW03,
YEAR = "2003",
PAGES = "101-111",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254498"}
@inproceedings{bb259708,
AUTHOR = "Kranstedt, A. and Kuhnlein, P. and Wachsmuth, I.",
TITLE = "Deixis in Multimodal Human Computer Interaction:
An Interdisciplinary Approach",
BOOKTITLE = GW03,
YEAR = "2003",
PAGES = "112-123",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254499"}
@inproceedings{bb259709,
AUTHOR = "Saeed, K. and Kozlowski, M.",
TITLE = "An Image-Based System for Spoken-Letter Recognition",
BOOKTITLE = CAIP03,
YEAR = "2003",
PAGES = "494-502",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254500"}
@inproceedings{bb259710,
AUTHOR = "Ho, P. and Armington, J.",
TITLE = "A Dual-Factor Authentication System Featuring Speaker Verification and
Token Technology",
BOOKTITLE = AVBPA03,
YEAR = "2003",
PAGES = "128-136",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254501"}
@inproceedings{bb259711,
AUTHOR = "Fox, N.A. and Reilly, R.B.",
TITLE = "Audio-Visual Speaker Identification Based on the Use of Dynamic Audio
and Visual Features",
BOOKTITLE = AVBPA03,
YEAR = "2003",
PAGES = "743-751",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254502"}
@inproceedings{bb259712,
AUTHOR = "Czyz, J. and Bengio, S. and Marcel, C. and Vandendorpe, L.",
TITLE = "Scalability Analysis of Audio-Visual Person Identity Verification",
BOOKTITLE = AVBPA03,
YEAR = "2003",
PAGES = "752-760",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254503"}
@inproceedings{bb259713,
AUTHOR = "Bengio, S.",
TITLE = "Multimodal Authentication Using Asynchronous HMMs",
BOOKTITLE = AVBPA03,
YEAR = "2003",
PAGES = "770-777",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254504"}
@inproceedings{bb259714,
AUTHOR = "Lucey, S. and Chen, T.H.",
TITLE = "Improved Audio-Visual Speaker Recognition via the Use of a Hybrid
Combination Strategy",
BOOKTITLE = AVBPA03,
YEAR = "2003",
PAGES = "929-936",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254505"}
@inproceedings{bb259715,
AUTHOR = "Krahnstoever, N. and Schapira, E. and Kettebeko, S. and Sharma, R.",
TITLE = "Multimodal human-computer interaction for crisis management systems",
BOOKTITLE = WACV02,
YEAR = "2002",
PAGES = "203-207",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254506"}
@inproceedings{bb259716,
AUTHOR = "Kettebekov, S. and Yeasin, M. and Sharma, R.",
TITLE = "Improving continuous gesture recognition with spoken prosody",
BOOKTITLE = CVPR03,
YEAR = "2003",
PAGES = "I: 565-570",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254507"}
@inproceedings{bb259717,
AUTHOR = "Poh, N. and Korczak, J.",
TITLE = "Hybrid Biometric Person Authentication Using Face and Voice Features",
BOOKTITLE = AVBPA01,
YEAR = "2001",
PAGES = "348",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254508"}
@inproceedings{bb259718,
AUTHOR = "Nakamura, S.",
TITLE = "Fusion of Audio-Visual Information for Integrated Speech Processing",
BOOKTITLE = AVBPA01,
YEAR = "2001",
PAGES = "127",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254509"}
@inproceedings{bb259719,
AUTHOR = "Sullivan, K.P.H. and Pelecanos, J.",
TITLE = "Revisiting Carl Bildt's Impostor: Would a Speaker Verification System
Foil Him?",
BOOKTITLE = AVBPA01,
YEAR = "2001",
PAGES = "144",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254510"}
@inproceedings{bb259720,
AUTHOR = "Geiger, G. and Ezzat, T. and Poggio, T.",
TITLE = "Perceptual Evaluation of Video-Realistic Speech",
BOOKTITLE = "MIT AIM",
YEAR = "2003",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254511"}
@inproceedings{bb259721,
AUTHOR = "Zhang, X.Z. and Merserratt, R.M. and Clements, M.",
TITLE = "Bimodal fusion in audio-visual speech recognition",
BOOKTITLE = ICIP02,
YEAR = "2002",
PAGES = "I: 964-967",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254512"}
@inproceedings{bb259722,
AUTHOR = "Graf, H.P. and Cosatto, E. and Strom, V. and Huang, F.J.",
TITLE = "Visual prosody: facial movements accompanying speech",
BOOKTITLE = AFGR02,
YEAR = "2002",
PAGES = "381-386",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254513"}
@inproceedings{bb259723,
AUTHOR = "Qi, Y.",
TITLE = "Learning Algorithms for Audio and Video Processing:
Independent Component Analysis and Support Vector Machine Based Approaches",
BOOKTITLE = UMD,
YEAR = "2000",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254514"}
@inproceedings{bb259724,
AUTHOR = "Nankaku, Y. and Tokuda, K. and Kitamura, T.",
TITLE = "Normalized Training for HMM-based Visual Speech Recognition",
BOOKTITLE = ICIP00,
YEAR = "2000",
PAGES = "Vol III: 234-237",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254515"}
@inproceedings{bb259725,
AUTHOR = "Zhang, Y. and Levinson, S. and Huang, T.S.",
TITLE = "Speaker Independent Audio-Visual Speech Recognition",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP8",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254516"}
@inproceedings{bb259726,
AUTHOR = "Pan, H. and Huang, T.S.",
TITLE = "A New Approach to Integrate Audio and Visual Features of Speech",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP8",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254517"}
@inproceedings{bb259727,
AUTHOR = "Potamianos, G. and Verma, A. and Neti, C. and Iyengar, G. and Basu, S.",
TITLE = "A Cascade Image Transform for Speaker Independent Automatic Speech
Reading",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP8",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254518"}
@inproceedings{bb259728,
AUTHOR = "Pan, H. and Liang, Z.P. and Huang, T.S.",
TITLE = "Fusing Audio and Visual Features of Speech",
BOOKTITLE = ICIP00,
YEAR = "2000",
PAGES = "Vol III: 214-217",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254519"}
@inproceedings{bb259729,
AUTHOR = "Faruquie, T.A. and Majumdar, A. and Rajput, N. and Subramaniam, L.V.",
TITLE = "Large Vocabulary Audio-visual Speech Recognition Using Active Shape
Models",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol III: 106-109",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254520"}
@inproceedings{bb259730,
AUTHOR = "Yu, K. and Jiang, X. and Bunke, H.",
TITLE = "Combining Acoustic and Visual Classifiers for the Recognition of Spoken
Sentences",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol II: 491-494",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254521"}
@inproceedings{bb259731,
AUTHOR = "Nam, J. and Alghoniemy, M. and Tewfik, A.H.",
TITLE = "Audio-visual content-based violent scene characterization",
BOOKTITLE = ICIP98,
YEAR = "1998",
PAGES = "I: 353-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254522"}
@inproceedings{bb259732,
AUTHOR = "Luettin, J. and Dupont, S.",
TITLE = "Continuous Audio-Visual Speech Recognition",
BOOKTITLE = ECCV98,
YEAR = "1998",
PAGES = "II: 657",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254523"}
@inproceedings{bb259733,
AUTHOR = "Yang, J. and Xiao, J. and Ritter, M.",
TITLE = "Automatic Selection of Visemes for Image-based Visual Speech Synthesis",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP8",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254524"}
@inproceedings{bb259734,
AUTHOR = "Sharma, R. and Cai, J.Y. and Chakravarthy, S. and Poddar, I. and Sethi, Y.",
TITLE = "Exploiting Speech/Gesture Co-occurrence for Improving Continuous
Gesture Recognition in Weather Narration",
BOOKTITLE = AFGR00,
YEAR = "2000",
PAGES = "422-427",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254525"}
@inproceedings{bb259735,
AUTHOR = "Yamamoto, E. and Nakamura, S. and Shikano, K.",
TITLE = "Lip Movement Synthesis from Speech Based on Hidden Markov Models",
BOOKTITLE = AFGR98,
YEAR = "1998",
PAGES = "154-159",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254526"}
@inproceedings{bb259736,
AUTHOR = "Roy, D. and Pentland, A.P.",
TITLE = "Automatic spoken affect classification and analysis",
BOOKTITLE = AFGR96,
YEAR = "1996",
PAGES = "363-367",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254527"}
@inproceedings{bb259737,
AUTHOR = "Petajan, E.D.",
TITLE = "An Architecture for Automatic Lipreading to Enhance Speech Recognition",
BOOKTITLE = CVPR85,
YEAR = "1985",
PAGES = "40-47",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT254528"}
@article{bb259738,
AUTHOR = "Zotkin, D.N. and Duraiswami, R. and Davis, L.S.",
TITLE = "Joint Audio-Visual Tracking Using Particle Filters",
JOURNAL = JASP,
VOLUME = "2002",
YEAR = "2002",
NUMBER = "11",
MONTH = "November",
PAGES = "1154",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254529"}
@article{bb259739,
AUTHOR = "Garg, A. and Pavlovic, V. and Rehg, J.M.",
TITLE = "Boosted learning in dynamic Bayesian networks for multimodal speaker
detection",
JOURNAL = PIEEE,
VOLUME = "91",
YEAR = "2003",
NUMBER = "9",
MONTH = "September",
PAGES = "1355-1369",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254530"}
@inproceedings{bb259740,
AUTHOR = "Garg, A. and Pavlovic, V. and Rehg, J.M.",
TITLE = "Audio-visual speaker detection using dynamic Bayesian networks",
BOOKTITLE = AFGR00,
YEAR = "2000",
PAGES = "384-390",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254531"}
@inproceedings{bb259741,
AUTHOR = "Pavlovic, V. and Garg, A. and Rehg, J.M. and Huang, T.S.",
TITLE = "Multimodal Speaker Detection using Error Feedback Dynamic Bayesian
Networks",
BOOKTITLE = CVPR00,
YEAR = "2000",
PAGES = "II: 34-41",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254532"}
@inproceedings{bb259742,
AUTHOR = "Pavlovic, V. and Berry, G. and Huang, T.S.",
TITLE = "Integration of Audio/Visual Information for Use in
Human-Computer Intelligent Interaction",
BOOKTITLE = ICIP97,
YEAR = "1997",
PAGES = "I: 121-124",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254533"}
@inproceedings{bb259743,
AUTHOR = "Choudhury, T. and Rehg, J.M. and Pavlovic, V. and Pentland, A.P.",
TITLE = "Boosting and structure learning in dynamic Bayesian networks for
audio-visual speaker detection",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "III: 789-794",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254534"}
@inproceedings{bb259744,
AUTHOR = "Pavlovic, V.",
TITLE = "Multimodal tracking and classification of audio-visual features",
BOOKTITLE = ICIP98,
YEAR = "1998",
PAGES = "I: 343-347",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254535"}
@inproceedings{bb259745,
AUTHOR = "Rehg, J.M. and Murphy, K.P. and Fieguth, P.W.",
TITLE = "Vision-Based Speaker Detection Using Bayesian Networks",
BOOKTITLE = CVPR99,
YEAR = "1999",
PAGES = "II: 110-116",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254536"}
@article{bb259746,
AUTHOR = "Talantzis, F. and Pnevmatikakis, A. and Constantinides, A.G.",
TITLE = "Audio-Visual Active Speaker Tracking in Cluttered Indoors Environments",
JOURNAL = SMC-B,
VOLUME = "39",
YEAR = "2009",
NUMBER = "1",
MONTH = "February",
PAGES = "7-15",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254537"}
@article{bb259747,
AUTHOR = "Constantinides, A.G. and Pnevmatikakis, A. and Talantzis, F.",
TITLE = "Audio-Visual Active Speaker Tracking in Cluttered Indoors Environments",
JOURNAL = SMC-B,
VOLUME = "38",
YEAR = "2008",
NUMBER = "3",
MONTH = "June",
PAGES = "799-807",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254537"}
@article{bb259748,
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/people917avt1.html#TT254538"}
@article{bb259749,
AUTHOR = "Ban, Y.T. and Alameda Pineda, X. and Girin, L. and Horaud, R.",
TITLE = "Variational Bayesian Inference for Audio-Visual Tracking of Multiple
Speakers",
JOURNAL = PAMI,
VOLUME = "43",
YEAR = "2021",
NUMBER = "5",
MONTH = "May",
PAGES = "1761-1776",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254539"}
@inproceedings{bb259750,
AUTHOR = "Ban, Y.T. and Girin, L. and Alameda Pineda, X. and Horaud, R.",
TITLE = "Exploiting the Complementarity of Audio and Visual Data in
Multi-speaker Tracking",
BOOKTITLE = CVAVM17,
YEAR = "2017",
PAGES = "446-454",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254540"}
@article{bb259751,
AUTHOR = "Qian, X.Y. and Brutti, A. and Lanz, O. and Omologo, M. and Cavallaro, A.",
TITLE = "Audio-Visual Tracking of Concurrent Speakers",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "942-954",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254541"}
@article{bb259752,
AUTHOR = "Hu, D. and Wei, Y. and Qian, R. and Lin, W.Y. and Song, R.H. and Wen, J.R.",
TITLE = "Class-Aware Sounding Objects Localization via Audiovisual
Correspondence",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "9844-9859",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254542"}
@article{bb259753,
AUTHOR = "Wang, H. and Zha, Z.J. and Li, L. and Chen, X.J. and Luo, J.B.",
TITLE = "Semantic and Relation Modulation for Audio-Visual Event Localization",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "7711-7725",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254543"}
@article{bb259754,
AUTHOR = "Garg, R. and Gao, R.H. and Grauman, K.",
TITLE = "Visually-Guided Audio Spatialization in Video with Geometry-Aware
Multi-task Learning",
JOURNAL = IJCV,
VOLUME = "131",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "2723-2737",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254544"}
@article{bb259755,
AUTHOR = "Wang, J.X. and Li, C.L. and Zheng, A. and Tang, J. and Luo, B.",
TITLE = "Looking and Hearing Into Details:
Dual-Enhanced Siamese Adversarial Network for Audio-Visual Matching",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "7505-7516",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254545"}
@inproceedings{bb259756,
AUTHOR = "Nugroho, M.A. and Woo, S. and Lee, S. and Kim, C.",
TITLE = "Audio-Visual Glance Network for Efficient Video Recognition",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10116-10125",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254546"}
@inproceedings{bb259757,
AUTHOR = "Liu, Y. and Tan, Y. and Lan, H.Y.",
TITLE = "Self-Supervised Contrastive Learning for Audio-Visual Action
Recognition",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1000-1004",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254547"}
@inproceedings{bb259758,
AUTHOR = "Min, K. and Roy, S. and Tripathi, S. and Guha, T. and Majumdar, S.",
TITLE = "Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXV:371-387",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254548"}
@inproceedings{bb259759,
AUTHOR = "Majumder, S. and Al Halah, Z. and Grauman, K.",
TITLE = "Move2Hear: Active Audio-Visual Source Separation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "275-285",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254549"}
@inproceedings{bb259760,
AUTHOR = "Majumder, S. and Grauman, K.",
TITLE = "Active Audio-Visual Separation of Dynamic Sound Sources",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:551-569",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254550"}
@inproceedings{bb259761,
AUTHOR = "Alcazar, J.L. and Heilbron, F.C. and Thabet, A.K. and Ghanem, B.",
TITLE = "MAAS: Multi-modal Assignation for Active Speaker Detection",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "265-274",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254551"}
@inproceedings{bb259762,
AUTHOR = "Kopuklu, O. and Taseska, M. and Rigoll, G.",
TITLE = "How to Design a Three-Stage Architecture for Audio-Visual Active
Speaker Detection in the Wild",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1173-1183",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254552"}
@inproceedings{bb259763,
AUTHOR = "Wu, Y. and Yang, Y.",
TITLE = "Exploring Heterogeneous Clues for Weakly-Supervised Audio-Visual
Video Parsing",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "1326-1335",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254553"}
@inproceedings{bb259764,
AUTHOR = "Liu, H. and Sun, Y.H. and Li, Y.D. and Yang, B.",
TITLE = "3D Audio-Visual Speaker Tracking with A Novel Particle Filter",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "7343-7348",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254554"}
@inproceedings{bb259765,
AUTHOR = "Liu, H. and Li, Y.D. and Yang, B.",
TITLE = "3D Audio-Visual Speaker Tracking with A Two-Layer Particle Filter",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "1955-1959",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254555"}
@inproceedings{bb259766,
AUTHOR = "He, G. and Liu, X. and Fan, F. and You, J.",
TITLE = "Image2Audio: Facilitating Semi-supervised Audio Emotion Recognition
with Facial Expression Image",
BOOKTITLE = VL3W20,
YEAR = "2020",
PAGES = "3978-3983",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254556"}
@inproceedings{bb259767,
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/people917avt1.html#TT254557"}
@inproceedings{bb259768,
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/people917avt1.html#TT254558"}
@inproceedings{bb259769,
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/people917avt1.html#TT254559"}
@inproceedings{bb259770,
AUTHOR = "Megherbi, N. and Ambellouis, S. and Colot, O. and Cabestaing, F.",
TITLE = "Data Association in Multi-Target Tracking Using Belief Theory:
Handling Target Emergence and Disappearance Issue",
BOOKTITLE = AVSBS05,
YEAR = "2005",
PAGES = "517-521",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254560"}
@inproceedings{bb259771,
AUTHOR = "Megherbi, N. and Ambellouis, S. and Colot, O. and Cabestaing, F.",
TITLE = "Joint audio-video people tracking using belief theory",
BOOKTITLE = AVSBS05,
YEAR = "2005",
PAGES = "135-140",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254561"}
@inproceedings{bb259772,
AUTHOR = "Li, X. and Sun, L. and Tao, L.M. and Xu, G.Y. and Jia, Y.",
TITLE = "A Speaker Tracking Algorithm Based on Audio and Visual Information
Fusion Using Particle Filter",
BOOKTITLE = ICIAR04,
YEAR = "2004",
PAGES = "II: 572-580",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254562"}
@inproceedings{bb259773,
AUTHOR = "Lange, C. and Hermann, T. and Ritter, H.",
TITLE = "Holistic Body Tracking for Gestural Interfaces",
BOOKTITLE = GW03,
YEAR = "2003",
PAGES = "132-139",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254563"}
@inproceedings{bb259774,
AUTHOR = "Blake, A. and Gangnet, M. and Perez, P. and Vermaak, J.",
TITLE = "Integrated tracking with vision and sound",
BOOKTITLE = CIAP01,
YEAR = "2001",
PAGES = "354-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT254564"}
@article{bb259775,
AUTHOR = "Mirhosseini, A.R. and Yan, H. and Lam, K.M.",
TITLE = "Adaptive Deformable Model for Mouth Boundary Detection",
JOURNAL = OptEng,
VOLUME = "37",
YEAR = "1998",
NUMBER = "3",
MONTH = "March",
PAGES = "869-875",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254565"}
@inproceedings{bb259776,
AUTHOR = "Mirhosseini, A.R. and Lam, K.M. and Yan, H.",
TITLE = "An adaptive deformable template for mouth boundary modeling",
BOOKTITLE = CIAP97,
YEAR = "1997",
PAGES = "I: 559-566",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254566"}
@inproceedings{bb259777,
AUTHOR = "Mirhosseini, A.R. and Yan, H. and Lam, K.M. and Chen, C.",
TITLE = "A Hierarchical and Adaptive Deformable Model for
Mouth Boundary Detection",
BOOKTITLE = ICIP97,
YEAR = "1997",
PAGES = "II: 756-759",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254567"}
@article{bb259778,
AUTHOR = "Li, C.H. and Yuen, P.C.",
TITLE = "Regularized color clustering in medical image database",
JOURNAL = MedImg,
VOLUME = "19",
YEAR = "2000",
NUMBER = "11",
MONTH = "November",
PAGES = "1150-1155",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254568"}
@inproceedings{bb259779,
AUTHOR = "Li, C.H. and Yuen, P.C.",
TITLE = "Normalized sampling for color clustering in medical diagnosis",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "III: 819-822",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254569"}
@article{bb259780,
AUTHOR = "Sadeghi, M.T. and Kittler, J.V. and Messer, K.",
TITLE = "Modelling and segmentation of lip area in face images",
JOURNAL = VISP,
VOLUME = "149",
YEAR = "2002",
NUMBER = "3",
MONTH = "June",
PAGES = "179-184",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254570"}
@inproceedings{bb259781,
AUTHOR = "Sadeghi, M.T. and Kittler, J.V. and Messer, K.",
TITLE = "Spatial clustering of pixels in the mouth area of face images",
BOOKTITLE = CIAP01,
YEAR = "2001",
PAGES = "36-41",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254571"}
@inproceedings{bb259782,
AUTHOR = "Sadeghi, M.T. and Kittler, J.V. and Messer, K.",
TITLE = "Segmentation of Lip Pixels for Lip Tracker Initialisation",
BOOKTITLE = ICIP01,
YEAR = "2001",
PAGES = "I: 50-53",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254572"}
@inproceedings{bb259783,
AUTHOR = "Sadeghi, M.T. and Kittler, J.V. and Messer, K.",
TITLE = "Real Time Segmentation of Lip Pixels for Lip Tracker Initialization",
BOOKTITLE = CAIP01,
YEAR = "2001",
PAGES = "317 ff.",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254573"}
@article{bb259784,
AUTHOR = "Lucey, S. and Sridharan, S. and Chandran, V.",
TITLE = "Adaptive mouth segmentation using chromatic features",
JOURNAL = PRL,
VOLUME = "23",
YEAR = "2002",
NUMBER = "11",
MONTH = "September",
PAGES = "1293-1302",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254574"}
@inproceedings{bb259785,
AUTHOR = "Lucey, S. and Sridharan, S. and Chandran, V.",
TITLE = "A Suitability Metric for Mouth Tracking Through Chromatic Segmentation",
BOOKTITLE = ICIP01,
YEAR = "2001",
PAGES = "III: 258-261",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254575"}
@inproceedings{bb259786,
AUTHOR = "Lucey, S. and Sridharan, S. and Chandran, V.",
TITLE = "Initialised Eigenlip Estimator for Fast Lip Tracking Using Linear
Regression",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol III: 178-181",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254576"}
@article{bb259787,
AUTHOR = "Liew, A.W.C. and Leung, S.H. and Lau, W.H.",
TITLE = "Lip contour extraction from color images using a deformable model",
JOURNAL = PR,
VOLUME = "35",
YEAR = "2002",
NUMBER = "12",
MONTH = "December",
PAGES = "2949-2962",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254577"}
@inproceedings{bb259788,
AUTHOR = "Liew, A.W.C. and Leung, S.H. and Lau, W.H.",
TITLE = "Lip Contour Extraction Using a Deformable Model",
BOOKTITLE = ICIP00,
YEAR = "2000",
PAGES = "Vol II: 255-258",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254578"}
@article{bb259789,
AUTHOR = "Leung, S.H. and Wang, S.L. and Lau, W.H.",
TITLE = "Lip Image Segmentation Using Fuzzy Clustering Incorporating an Elliptic
Shape Function",
JOURNAL = IP,
VOLUME = "13",
YEAR = "2004",
NUMBER = "1",
MONTH = "January",
PAGES = "51-62",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254579"}
@article{bb259790,
AUTHOR = "Wang, S.L. and Lau, W.H. and Leung, S.H.",
TITLE = "Automatic lip contour extraction from color images",
JOURNAL = PR,
VOLUME = "37",
YEAR = "2004",
NUMBER = "12",
MONTH = "December",
PAGES = "2375-2387",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254580"}
@inproceedings{bb259791,
AUTHOR = "Mihara, I. and Yamauchi, Y. and Morishita, A. and Doi, M.",
TITLE = "Image recognition method and apparatus",
BOOKTITLE = US_Patent,
YEAR = "2008",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254581"}
@inproceedings{bb259792,
AUTHOR = "Doi, M. and Morishita, A. and Yamauchi, Y. and Mihara, I.",
TITLE = "Image recognition method and apparatus",
BOOKTITLE = US_Patent,
YEAR = "2008",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254581"}
@inproceedings{bb259793,
AUTHOR = "Mihara, I. and Doi, M.",
TITLE = "Image recognition method and apparatus",
BOOKTITLE = US_Patent,
YEAR = "2003",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254581"}
@inproceedings{bb259794,
AUTHOR = "Doi, M. and Morishita, A. and Yamauchi, Y. and Mihara, I.",
TITLE = "Image recognition method and apparatus",
BOOKTITLE = US_Patent,
YEAR = "2004",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254581"}
@article{bb259795,
AUTHOR = "Eveno, N. and Caplier, A. and Coulon, P.Y.",
TITLE = "Accurate and quasi-automatic lip tracking",
JOURNAL = CirSysVideo,
VOLUME = "14",
YEAR = "2004",
NUMBER = "5",
MONTH = "May",
PAGES = "706-715",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254582"}
@inproceedings{bb259796,
AUTHOR = "Eveno, N. and Caplier, A. and Coulon, P.Y.",
TITLE = "Jumping snakes and parametric model for lip segmentation",
BOOKTITLE = ICIP03,
YEAR = "2003",
PAGES = "II: 867-870",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254583"}
@inproceedings{bb259797,
AUTHOR = "Bouvier, C. and Coulon, P.Y. and Maldague, X.",
TITLE = "Unsupervised Lips Segmentation Based on ROI Optimisation and Parametric
Model",
BOOKTITLE = ICIP07,
YEAR = "2007",
PAGES = "IV: 301-304",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254584"}
@article{bb259798,
AUTHOR = "Aharon, M. and Kimmel, R.",
TITLE = "Representation Analysis and Synthesis of Lip Images Using
Dimensionality Reduction",
JOURNAL = IJCV,
VOLUME = "67",
YEAR = "2006",
NUMBER = "3",
MONTH = "May",
PAGES = "297-312",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254585"}
@article{bb259799,
AUTHOR = "Nguyen, D. and Halupka, D. and Aarabi, P. and Sheikholeslami, A.",
TITLE = "Real-Time Face Detection and Lip Feature Extraction Using
Field-Programmable Gate Arrays",
JOURNAL = SMC-B,
VOLUME = "36",
YEAR = "2006",
NUMBER = "4",
MONTH = "August",
PAGES = "902-912",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT254586"}
Last update:Jul 18, 2024 at 20:50:34