@inproceedings{bb289800,
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#TT284433"}
@inproceedings{bb289801,
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#TT284434"}
@inproceedings{bb289802,
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#TT284435"}
@inproceedings{bb289803,
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#TT284436"}
@article{bb289804,
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#TT284437"}
@article{bb289805,
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#TT284438"}
@inproceedings{bb289806,
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#TT284439"}
@inproceedings{bb289807,
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#TT284440"}
@inproceedings{bb289808,
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#TT284441"}
@inproceedings{bb289809,
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#TT284442"}
@inproceedings{bb289810,
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#TT284443"}
@inproceedings{bb289811,
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#TT284444"}
@article{bb289812,
AUTHOR = "Vajaria, H. and Sankar, R. and Kasturi, R.",
TITLE = "Exploring Co-Occurence Between Speech and Body Movement for
Audio-Guided Video Localization",
JOURNAL = CirSysVideo,
VOLUME = "18",
YEAR = "2008",
NUMBER = "11",
MONTH = "November",
PAGES = "1608-1617",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284445"}
@inproceedings{bb289813,
AUTHOR = "Vajaria, H. and Islam, T. and Sarkar, S. and Sankar, R. and Kasturi, R.",
TITLE = "Audio Segmentation and Speaker Localization in Meeting Videos",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "II: 1150-1153",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284446"}
@article{bb289814,
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#TT284447"}
@article{bb289815,
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#TT284447"}
@article{bb289816,
AUTHOR = "Lee, J.S. and de Simone, F. and Ebrahimi, T.",
TITLE = "Efficient video coding based on audio-visual focus of attention",
JOURNAL = JVCIR,
VOLUME = "22",
YEAR = "2011",
NUMBER = "8",
MONTH = "November",
PAGES = "704-711",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284448"}
@article{bb289817,
AUTHOR = "Blauth, D.A. and Minotto, V.P. and Jung, C.R. and Lee, B. and Kalker, T.",
TITLE = "Voice activity detection and speaker localization using audiovisual
cues",
JOURNAL = PRL,
VOLUME = "33",
YEAR = "2012",
NUMBER = "4",
MONTH = "March",
PAGES = "373-380",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284449"}
@inproceedings{bb289818,
AUTHOR = "Montazzolli, S. and Jung, C.R. and Gelb, D.",
TITLE = "Audiovisual voice activity detection using off-the-shelf cameras",
BOOKTITLE = ICIP15,
YEAR = "2015",
PAGES = "3886-3890",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284450"}
@article{bb289819,
AUTHOR = "Minotto, V.P. and Jung, C.R. and Lee, B.",
TITLE = "Simultaneous-Speaker Voice Activity Detection and Localization Using
Mid-Fusion of SVM and HMMs",
JOURNAL = MultMed,
VOLUME = "16",
YEAR = "2014",
NUMBER = "4",
MONTH = "June",
PAGES = "1032-1044",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284451"}
@article{bb289820,
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#TT284452"}
@article{bb289821,
AUTHOR = "Pu, J. and Panagakis, Y. and Pantic, M.",
TITLE = "Active Speaker Detection and Localization in Videos Using Low-Rank
and Kernelized Sparsity",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "865-869",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284453"}
@article{bb289822,
AUTHOR = "Qian, X.Y. and Liu, Q. and Wang, J.D. and Li, H.Z.",
TITLE = "Three-Dimensional Speaker Localization: Audio-Refined Visual Scaling
Factor Estimation",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1405-1409",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284454"}
@article{bb289823,
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#TT284455"}
@inproceedings{bb289824,
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#TT284456"}
@article{bb289825,
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#TT284457"}
@article{bb289826,
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#TT284458"}
@article{bb289827,
AUTHOR = "Zheng, A. and Hu, M. and Jiang, B. and Huang, Y. and Yan, Y. and Luo, B.",
TITLE = "Adversarial-Metric Learning for Audio-Visual Cross-Modal Matching",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "338-351",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284459"}
@article{bb289828,
AUTHOR = "Wang, Y. and Qian, X.H. and Zhou, W.",
TITLE = "Transformer-Prompted Network: Efficient Audio-Visual Segmentation via
Transformer and Prompt Learning",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "516-520",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284460"}
@article{bb289829,
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#TT284461"}
@article{bb289830,
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#TT284462"}
@article{bb289831,
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#TT284463"}
@article{bb289832,
AUTHOR = "Liu, C. and Li, P. and Zhang, H. and Li, L.C. and Huang, Z. and Wang, D.D. and Yu, X.",
TITLE = "BAVS: Bootstrapping Audio-Visual Segmentation by Integrating
Foundation Knowledge",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "10015-10028",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284464"}
@inproceedings{bb289833,
AUTHOR = "Liu, C. and Li, P. and Yang, L.Y. and Wang, D.D. and Li, L.C. and Yu, X.",
TITLE = "Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent
Alignment",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28922-28931",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284465"}
@inproceedings{bb289834,
AUTHOR = "Liu, C. and Li, P.P. and Yu, Q. and Sheng, H.W. and Wang, D.D. and Li, L.C. and Yu, X.",
TITLE = "Benchmarking Audio Visual Segmentation for Long-Untrimmed Videos",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22712-22722",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284466"}
@article{bb289835,
AUTHOR = "Traa, J. and Smaragdis, P.",
TITLE = "A Wrapped Kalman Filter for Azimuthal Speaker Tracking",
JOURNAL = SPLetters,
VOLUME = "20",
YEAR = "2013",
NUMBER = "12",
PAGES = "1257-1260",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284467"}
@article{bb289836,
AUTHOR = "Li, Y. and Liu, H. and Yang, B.",
TITLE = "STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "1835-1847",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284468"}
@article{bb289837,
AUTHOR = "Shi, Z.F. and Wu, Q.B. and Meng, F.M. and Xu, L.F. and Li, H.L.",
TITLE = "Cross-Modal Cognitive Consensus Guided Audio-Visual Segmentation",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "209-223",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284469"}
@article{bb289838,
AUTHOR = "Senocak, A. and Ryu, H. and Kim, J. and Oh, T.H. and Pfister, H. and Chung, J.S.",
TITLE = "Toward Interactive Sound Source Localization:
Better Align Sight and Sound!",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "9",
MONTH = "September",
PAGES = "7643-7659",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284470"}
@article{bb289839,
AUTHOR = "Jiang, Z.Y. and Chen, X. and Wang, S. and Qian, X.Y. and Li, H.Z.",
TITLE = "TPEech: Target Speaker Extraction and Noise Suppression With
Historical Dialogue Text Cues",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "351-355",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284471"}
@article{bb289840,
AUTHOR = "Yang, W.H. and Wei, J.G. and Lu, W.H. and Song, X.Y. and Yue, X.",
TITLE = "Listening for 'You': Enhancing Speech Image Retrieval via Target
Speaker Extraction",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "201-205",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284472"}
@inproceedings{bb289841,
AUTHOR = "Um, S.J. and Kim, D.J. and Lee, S. and Kim, J.U.",
TITLE = "Object-aware Sound Source Localization via Audio-Visual Scene
Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8342-8351",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284473"}
@inproceedings{bb289842,
AUTHOR = "Kim, I.H. and Song, Y. and Park, J. and Kim, W.H. and Kwak, S.",
TITLE = "Improving Sound Source Localization with Joint Slot Attention on
Image and Audio",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3121-3130",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284474"}
@inproceedings{bb289843,
AUTHOR = "Liu, C. and Yang, L.Y. and Li, P. and Wang, D.D. and Li, L. and Yu, X.",
TITLE = "Dynamic Derivation and Elimination: Audio Visual Segmentation with
Enhanced Audio Semantics",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3131-3141",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284475"}
@inproceedings{bb289844,
AUTHOR = "Ryu, H. and Kim, S. and Chung, J.S. and Senocak, A.",
TITLE = "Seeing Speech and Sound: Distinguishing and Locating Audio Sources in
Visual Scenes",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13540-13549",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284476"}
@inproceedings{bb289845,
AUTHOR = "Wang, X.Z. and Cheng, F. and Bertasius, G.",
TITLE = "LoCoNet: Long-Short Context Network for Active Speaker Detection",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18462-18472",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284477"}
@inproceedings{bb289846,
AUTHOR = "Huang, C. and Tian, Y.P. and Kumar, A. and Xu, C.L.",
TITLE = "Egocentric Audio-Visual Object Localization",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22910-22921",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284478"}
@inproceedings{bb289847,
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#TT284479"}
@inproceedings{bb289848,
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#TT284480"}
@inproceedings{bb289849,
AUTHOR = "Mo, S.T. and Morgado, P.",
TITLE = "Localizing Visual Sounds the Easy Way",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:218-234",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284481"}
@inproceedings{bb289850,
AUTHOR = "Xia, Y. and Zhao, Z.",
TITLE = "Cross-modal Background Suppression for Audio-Visual Event
Localization",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19957-19966",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284482"}
@inproceedings{bb289851,
AUTHOR = "Jiang, H. and Murdock, C. and Ithapu, V.K.",
TITLE = "Egocentric Deep Multi-Channel Audio-Visual Active Speaker
Localization",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10534-10542",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284483"}
@inproceedings{bb289852,
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#TT284484"}
@inproceedings{bb289853,
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/people917avt1.html#TT284485"}
@inproceedings{bb289854,
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/people917avt1.html#TT284486"}
@inproceedings{bb289855,
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#TT284487"}
@inproceedings{bb289856,
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#TT284488"}
@inproceedings{bb289857,
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#TT284489"}
@inproceedings{bb289858,
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#TT284490"}
@inproceedings{bb289859,
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#TT284491"}
@inproceedings{bb289860,
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#TT284492"}
@inproceedings{bb289861,
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#TT284493"}
@inproceedings{bb289862,
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#TT284494"}
@inproceedings{bb289863,
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#TT284495"}
@inproceedings{bb289864,
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#TT284496"}
@inproceedings{bb289865,
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/people917avt1.html#TT284497"}
@inproceedings{bb289866,
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#TT284498"}
@inproceedings{bb289867,
AUTHOR = "Kushal, A. and Rahurkar, M. and Fei Fei, L. and Ponce, J. and Huang, T.",
TITLE = "Audio-Visual Speaker Localization Using Graphical Models",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "I: 291-294",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284499"}
@inproceedings{bb289868,
AUTHOR = "Tsuji, T. and Yamamoto, K. and Ishii, I.",
TITLE = "Real-time Sound Source Localization Based on Audiovisual Frequency
Integration",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "IV: 322-325",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917avt1.html#TT284500"}
@inproceedings{bb289869,
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#TT284501"}
@inproceedings{bb289870,
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#TT284502"}
@inproceedings{bb289871,
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#TT284503"}
@inproceedings{bb289872,
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#TT284504"}
@inproceedings{bb289873,
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#TT284505"}
@article{bb289874,
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#TT284506"}
@inproceedings{bb289875,
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#TT284507"}
@inproceedings{bb289876,
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#TT284508"}
@article{bb289877,
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#TT284509"}
@inproceedings{bb289878,
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#TT284510"}
@article{bb289879,
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#TT284511"}
@inproceedings{bb289880,
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#TT284512"}
@inproceedings{bb289881,
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#TT284513"}
@inproceedings{bb289882,
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#TT284514"}
@article{bb289883,
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#TT284515"}
@inproceedings{bb289884,
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#TT284516"}
@inproceedings{bb289885,
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#TT284517"}
@article{bb289886,
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#TT284518"}
@inproceedings{bb289887,
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#TT284519"}
@article{bb289888,
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#TT284520"}
@article{bb289889,
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#TT284521"}
@inproceedings{bb289890,
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#TT284522"}
@inproceedings{bb289891,
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#TT284522"}
@inproceedings{bb289892,
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#TT284522"}
@inproceedings{bb289893,
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#TT284522"}
@article{bb289894,
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#TT284523"}
@inproceedings{bb289895,
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#TT284524"}
@inproceedings{bb289896,
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#TT284525"}
@article{bb289897,
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#TT284526"}
@article{bb289898,
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#TT284527"}
@article{bb289899,
AUTHOR = "Chang, W.Y. and Chen, C.S. and Jian, Y.D.",
TITLE = "Visual Tracking in High-Dimensional State Space by Appearance-Guided
Particle Filtering",
JOURNAL = IP,
VOLUME = "17",
YEAR = "2008",
NUMBER = "7",
MONTH = "July",
PAGES = "1154-1167",
BIBSOURCE = "http://www.visionbib.com/bibliography/people917.html#TT284528"}
Last update:Apr 6, 2026 at 11:28:57