@inproceedings{bb108400,
AUTHOR = "Yu, J.",
TITLE = "A Real-Time 3D Visual Singing Synthesis:
From Appearance to Internal Articulators",
BOOKTITLE = MMMod17,
YEAR = "2017",
PAGES = "I: 53-64",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105115"}
@inproceedings{bb108401,
AUTHOR = "Dawood, S. and Hicks, Y. and Marshall, D.",
TITLE = "Speech-Driven Facial Animation Using Manifold Relevance Determination",
BOOKTITLE = CVAVM16,
YEAR = "2016",
PAGES = "II: 869-882",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105116"}
@inproceedings{bb108402,
AUTHOR = "Malleson, C. and Bazin, J.C. and Wang, O. and Bradley, D. and Beeler, T. and Hilton, A. and Sorkine Hornung, A.",
TITLE = "FaceDirector: Continuous Control of Facial Performance in Video",
BOOKTITLE = ICCV15,
YEAR = "2015",
PAGES = "3979-3987",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105117"}
@inproceedings{bb108403,
AUTHOR = "Musti, U. and Zhou, Z.H. and Pietikainen, M.",
TITLE = "Facial 3D Shape Estimation from Images for Visual Speech Animation",
BOOKTITLE = ICPR14,
YEAR = "2014",
PAGES = "40-45",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105118"}
@inproceedings{bb108404,
AUTHOR = "Yu, J. and Li, A.",
TITLE = "3D visual pronunciation of Mandarine Chinese for language learning",
BOOKTITLE = ICIP14,
YEAR = "2014",
PAGES = "2036-2040",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105119"}
@inproceedings{bb108405,
AUTHOR = "Anderson, R. and Stenger, B. and Wan, V. and Cipolla, R.",
TITLE = "Expressive Visual Text-to-Speech Using Active Appearance Models",
BOOKTITLE = CVPR13,
YEAR = "2013",
PAGES = "3382-3389",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105120"}
@inproceedings{bb108406,
AUTHOR = "Manresa Yee, C. and Ponsa, P. and Arellano, D. and Larrea, M.",
TITLE = "An Avatar Acceptance Study for Home Automation Scenarios",
BOOKTITLE = AMDO12,
YEAR = "2012",
PAGES = "230-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105121"}
@inproceedings{bb108407,
AUTHOR = "Tang, Y.Q. and Fang, Y. and Huang, Q.H.",
TITLE = "Audio personalization using head related transfer function in 3DTV",
BOOKTITLE = "3DTV11",
YEAR = "2011",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105122"}
@inproceedings{bb108408,
AUTHOR = "Liu, K. and Ostermann, J.",
TITLE = "Realistic head motion synthesis for an image-based talking head",
BOOKTITLE = FG11,
YEAR = "2011",
PAGES = "125-130",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105123"}
@inproceedings{bb108409,
AUTHOR = "Ostermann, J. and Liu, K.",
TITLE = "Realistic head motion synthesis for an image-based talking head",
BOOKTITLE = FG11,
YEAR = "2011",
PAGES = "221-226",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105123"}
@inproceedings{bb108410,
AUTHOR = "Chaloupka, J. and Chaloupka, Z.",
TITLE = "Czech Artificial Computerized Talking Head George",
BOOKTITLE = COST08,
YEAR = "2008",
PAGES = "324-330",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105124"}
@inproceedings{bb108411,
AUTHOR = "Zhao, H. and Chen, Y.B. and Shen, Y.M. and Tang, C.J.",
TITLE = "Audio-Visual Speech Synthesis Based on Chinese Visual Triphone",
BOOKTITLE = CISP09,
YEAR = "2009",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105125"}
@inproceedings{bb108412,
AUTHOR = "Hu, Y.L. and Zhou, M.Q. and Wu, Z.K.",
TITLE = "An Automatic Dense Point Registration Method for 3D Face Animation",
BOOKTITLE = CISP09,
YEAR = "2009",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105126"}
@inproceedings{bb108413,
AUTHOR = "Berger, M.O. and Ponroy, J. and Wrobel Dautcourt, B.",
TITLE = "Realistic Face Animation for Audiovisual Speech Applications: A
Densification Approach Driven by Sparse Stereo Meshes",
BOOKTITLE = MIRAGE09,
YEAR = "2009",
PAGES = "297-307",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105127"}
@inproceedings{bb108414,
AUTHOR = "Verdet, F. and Hennebert, J.",
TITLE = "Impostures of Talking Face Systems Using Automatic Face Animation",
BOOKTITLE = BTAS08,
YEAR = "2008",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105128"}
@inproceedings{bb108415,
AUTHOR = "Gaur, U. and Jain, A. and Goel, S.",
TITLE = "Towards Real-Time Monocular Video-Based Avatar Animation",
BOOKTITLE = ISVC08,
YEAR = "2008",
PAGES = "II: 949-958",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105129"}
@inproceedings{bb108416,
AUTHOR = "Badin, P. and Elisei, F. and Bailly, G. and Tarabalka, Y.",
TITLE = "An Audiovisual Talking Head for Augmented Speech Generation: Models and
Animations Based on a Real Speaker's Articulatory Data",
BOOKTITLE = AMDO08,
YEAR = "2008",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105130"}
@inproceedings{bb108417,
AUTHOR = "Fanelli, G. and Fratarcangeli, M.",
TITLE = "A Non-Invasive Approach for Driving Virtual Talking Heads from Real
Facial Movements",
BOOKTITLE = "3DTV07",
YEAR = "2007",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105131"}
@inproceedings{bb108418,
AUTHOR = "Xiong, L. and Zheng, N.N. and You, Q. and Liu, J.Y.",
TITLE = "Facial Expression Sequence Synthesis Based on Shape and Texture Fusion
Model",
BOOKTITLE = ICIP07,
YEAR = "2007",
PAGES = "IV: 473-476",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105132"}
@inproceedings{bb108419,
AUTHOR = "Beaumesnil, B. and Luthon, F.",
TITLE = "Real Time Tracking for 3D Realistic Lip Animation",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "I: 219-222",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105133"}
@inproceedings{bb108420,
AUTHOR = "Ravindra de Silva, P. and Madurapperuma, A.P. and Marasinghe, A. and Osano, M.",
TITLE = "Integrating Animated Pedagogical Agent as Motivational Supporter into
Interactive System",
BOOKTITLE = CRV06,
YEAR = "2006",
PAGES = "34-34",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105134"}
@inproceedings{bb108421,
AUTHOR = "Pei, Y.R. and Zha, H.B.",
TITLE = "Vision Based Speech Animation Transferring with Underlying Anatomical
Structure",
BOOKTITLE = ACCV06,
YEAR = "2006",
PAGES = "I:591-600",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105135"}
@inproceedings{bb108422,
AUTHOR = "Liu, Y.H. and Xu, G.Y. and Tao, L.M.",
TITLE = "An Efficient Approach for Multi-view Face Animation Based on Quasi 3D
Model",
BOOKTITLE = ACCV06,
YEAR = "2006",
PAGES = "II:913-922",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105136"}
@inproceedings{bb108423,
AUTHOR = "Leszczynski, M. and Skarbek, W.",
TITLE = "Viseme Classification for Talking Head Application",
BOOKTITLE = CAIP05,
YEAR = "2005",
PAGES = "773",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105137"}
@inproceedings{bb108424,
AUTHOR = "Leszczynski, M. and Skarbek, W.",
TITLE = "Viseme recognition: A comparative study",
BOOKTITLE = AVSBS05,
YEAR = "2005",
PAGES = "287-292",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105138"}
@inproceedings{bb108425,
AUTHOR = "Leszczynski, M. and Skarbek, W. and Badura, S.",
TITLE = "Fast Viseme Recognition for Talking Head Application",
BOOKTITLE = ICIAR05,
YEAR = "2005",
PAGES = "516-523",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105139"}
@inproceedings{bb108426,
AUTHOR = "Gracia Roche, J.J. and Orrite, C. and Bernues, E. and Herrero, J.E.",
TITLE = "Color Distribution Tracking for Facial Analysis",
BOOKTITLE = IbPRIA05,
YEAR = "2005",
PAGES = "I:484",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105140"}
@inproceedings{bb108427,
AUTHOR = "Ypsilos, I.A. and Hilton, A. and Turkmani, A. and Jackson, P.J.B.",
TITLE = "Speech-driven face synthesis from 3D video",
BOOKTITLE = "3DPVT04",
YEAR = "2004",
PAGES = "58-65",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105141"}
@inproceedings{bb108428,
AUTHOR = "Saisan, P. and Bissacco, A. and Chiuso, A. and Soatto, S.",
TITLE = "Modeling and Synthesis of Facial Motion Driven by Speech",
BOOKTITLE = ECCV04,
YEAR = "2004",
PAGES = "Vol III: 456-467",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105142"}
@inproceedings{bb108429,
AUTHOR = "Malcangi, M. and de Tintis, R.",
TITLE = "Audio Based Real-Time Speech Animation of Embodied Conversational
Agents",
BOOKTITLE = GW03,
YEAR = "2003",
PAGES = "350-360",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105143"}
@inproceedings{bb108430,
AUTHOR = "Aleksic, P.S. and Katsaggelos, A.K.",
TITLE = "Speech-to-video synthesis using facial animation parameters",
BOOKTITLE = ICIP03,
YEAR = "2003",
PAGES = "III: 1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105144"}
@inproceedings{bb108431,
AUTHOR = "Hack, C.A. and Taylor, C.J.",
TITLE = "Modelling 'Talking Head' Behaviour",
BOOKTITLE = BMVC03,
YEAR = "2003",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105145"}
@inproceedings{bb108432,
AUTHOR = "Choi, K.H. and Hwang, J.N.",
TITLE = "Creating 3D speech-driven talking heads: a probabilistic network
approach",
BOOKTITLE = ICIP02,
YEAR = "2002",
PAGES = "I: 984-987",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105146"}
@inproceedings{bb108433,
AUTHOR = "Hong, P.Y. and Wen, Z. and Huang, T.S. and Shum, H.Y.",
TITLE = "Real-time speech-driven 3D face animation",
BOOKTITLE = "3DPVT02",
YEAR = "2002",
PAGES = "713-716",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105147"}
@inproceedings{bb108434,
AUTHOR = "Morishima, S. and Yotsukura, T.",
TITLE = "Hypermask: Talking Head Projected Onto Moving Surface",
BOOKTITLE = ICIP01,
YEAR = "2001",
PAGES = "III: 947-950",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105148"}
@inproceedings{bb108435,
AUTHOR = "Neumann, J. and Aloimonos, Y.",
TITLE = "Talking Heads: Introducing the tool of 3D motion fields in the study of
action",
BOOKTITLE = HUMO00,
YEAR = "2000",
PAGES = "25-32",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105149"}
@inproceedings{bb108436,
AUTHOR = "Chen, T.H. and Wang, Y. and Graf, H.P. and Swain, C.T.",
TITLE = "A new frame interpolation scheme for talking head sequences",
BOOKTITLE = ICIP95,
YEAR = "1995",
PAGES = "II: 591-594",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105150"}
@inproceedings{bb108437,
AUTHOR = "Shan, S.",
TITLE = "Individual 3d Face Synthesis Based on Orthogonal Photos and
Speech-driven Facial Animation",
BOOKTITLE = ICIP00,
YEAR = "2000",
PAGES = "Vol III: 238-241",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105151"}
@inproceedings{bb108438,
AUTHOR = "Noh, J.Y. and Neumann, U.",
TITLE = "Talking Face",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TA1",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105152"}
@inproceedings{bb108439,
AUTHOR = "Kakihara, K. and Nakamura, S. and Shikano, K.",
TITLE = "Speech-To-Face Movement Synthesis Based on HMMS",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "MP7",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105153"}
@inproceedings{bb108440,
AUTHOR = "Van Gool, L.J. and Tuytelaars, T. and Pollefeys, M.",
TITLE = "Adventurous Tourism for Couch Potatoes",
BOOKTITLE = CAIP99,
YEAR = "1999",
PAGES = "98-107",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105154"}
@inproceedings{bb108441,
AUTHOR = "Ishikawa, T. and Sera, H. and Morishima, S. and Terzopoulos, D.",
TITLE = "Facial Image Reconstruction by Estimated Muscle Parameter",
BOOKTITLE = AFGR98,
YEAR = "1998",
PAGES = "342-347",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105155"}
@inproceedings{bb108442,
AUTHOR = "Bothe, H.H.",
TITLE = "A visual speech model based on fuzzy-neuro methods",
BOOKTITLE = CIAP95,
YEAR = "1995",
PAGES = "152-158",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105156"}
@article{bb108443,
AUTHOR = "Lavagetto, F.",
TITLE = "Time-Delay Neural Networks for Estimating Lip Movements from
Speech Analysis:
A Useful Tool in Audio Video Synchronization",
JOURNAL = CirSysVideo,
VOLUME = "7",
YEAR = "1997",
NUMBER = "5",
MONTH = "October",
PAGES = "786-800",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105157"}
@inproceedings{bb108444,
AUTHOR = "Gasper, E. and Matthews, J.H. and Wesley, R.",
TITLE = "Advanced tools for speech synchronized animation",
BOOKTITLE = US_Patent,
YEAR = "1997",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105158"}
@inproceedings{bb108445,
AUTHOR = "Wesley, R. and Matthews, J.H. and Gasper, E.",
TITLE = "Advanced tools for speech synchronized animation",
BOOKTITLE = US_Patent,
YEAR = "1997",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105158"}
@inproceedings{bb108446,
AUTHOR = "Gasper, E. and Wesley, R.",
TITLE = "Advanced tools for speech synchronized animation",
BOOKTITLE = US_Patent,
YEAR = "1997",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105158"}
@article{bb108447,
AUTHOR = "Chien, J.T. and Lin, M.S.",
TITLE = "Frame-synchronous noise compensation for hands-free speech recognition
in car environments",
JOURNAL = VISP,
VOLUME = "147",
YEAR = "2000",
NUMBER = "6",
MONTH = "December",
PAGES = "508-515",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105159"}
@inproceedings{bb108448,
AUTHOR = "Rosenfeld, M.",
TITLE = "Method for automatically animating lip synchronization and
facial expression of animated characters",
BOOKTITLE = US_Patent,
YEAR = "2001",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105160"}
@inproceedings{bb108449,
AUTHOR = "Haisma, N. and Sinke, J.G. and Bergevoet, B.A.J. and van Gestel, H.A.W.",
TITLE = "Post-synchronizing an information stream including lip
objects replacement",
BOOKTITLE = US_Patent,
YEAR = "2006",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105161"}
@inproceedings{bb108450,
AUTHOR = "Huang, Y. and Lin, S.S.T. and Guo, B.N. and Shum, H.Y.",
TITLE = "System and method for real time lip synchronization",
BOOKTITLE = US_Patent,
YEAR = "2006",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105162"}
@article{bb108451,
AUTHOR = "Saenko, K. and Livescu, K. and Glass, J. and Darrell, T.J.",
TITLE = "Multistream Articulatory Feature-Based Models for Visual Speech
Recognition",
JOURNAL = PAMI,
VOLUME = "31",
YEAR = "2009",
NUMBER = "9",
MONTH = "September",
PAGES = "1700-1707",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105163"}
@inproceedings{bb108452,
AUTHOR = "Saenko, K. and Livescu, K. and Siracusa, M. and Wilson, K. and Glass, J. and Darrell, T.J.",
TITLE = "Visual Speech Recognition with Loosely Synchronized Feature Streams",
BOOKTITLE = ICCV05,
YEAR = "2005",
PAGES = "II: 1424-1431",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105164"}
@article{bb108453,
AUTHOR = "El Sallam, A.A. and Mian, A.S.",
TITLE = "Correlation based speech-video synchronization",
JOURNAL = PRL,
VOLUME = "32",
YEAR = "2011",
NUMBER = "6",
MONTH = "April",
PAGES = "780-786",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105165"}
@inproceedings{bb108454,
AUTHOR = "El Sallam, A.A. and Mian, A.S.",
TITLE = "Speech-Video Synchronization Using Lips Movements and Speech Envelope
Correlation",
BOOKTITLE = ICIAR09,
YEAR = "2009",
PAGES = "397-407",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105166"}
@article{bb108455,
AUTHOR = "Chen, Y.M. and Huang, F.C. and Guan, S.H. and Chen, B.Y.",
TITLE = "Animating Lip-Sync Characters With Dominated Animeme Models",
JOURNAL = CirSysVideo,
VOLUME = "22",
YEAR = "2012",
NUMBER = "9",
MONTH = "September",
PAGES = "1344-1353",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105167"}
@article{bb108456,
AUTHOR = "Srinivasan, V. and Bethel, C.L. and Murphy, R.R.",
TITLE = "Evaluation of Head Gaze Loosely Synchronized With Real-Time Synthetic
Speech for Social Robots",
JOURNAL = HMS,
VOLUME = "44",
YEAR = "2014",
NUMBER = "6",
MONTH = "December",
PAGES = "767-778",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105168"}
@article{bb108457,
AUTHOR = "Liu, N. and Zhou, T. and Ji, Y.F. and Zhao, Z.Y. and Wan, L.H.",
TITLE = "Synthesizing Talking Faces from Text and Audio: An Autoencoder and
Sequence-to-Sequence Convolutional Neural Network",
JOURNAL = PR,
VOLUME = "102",
YEAR = "2020",
PAGES = "107231",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105169"}
@article{bb108458,
AUTHOR = "Yu, L. and Yu, J. and Li, M. and Ling, Q.",
TITLE = "Multimodal Inputs Driven Talking Face Generation With
Spatial-Temporal Dependency",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "1",
MONTH = "January",
PAGES = "203-216",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105170"}
@article{bb108459,
AUTHOR = "Liu, L. and Feng, G. and Beautemps, D. and Zhang, X.P.",
TITLE = "Re-Synchronization Using the Hand Preceding Model for Multi-Modal
Fusion in Automatic Continuous Cued Speech Recognition",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "292-305",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105171"}
@article{bb108460,
AUTHOR = "Beyan, C. and Shahid, M. and Murino, V.",
TITLE = "RealVAD: A Real-World Dataset and A Method for Voice Activity
Detection by Body Motion Analysis",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "2071-2085",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105172"}
@article{bb108461,
AUTHOR = "Eskimez, S.E. and Zhang, Y. and Duan, Z.Y.",
TITLE = "Speech Driven Talking Face Generation From a Single Image and an
Emotion Condition",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "3480-3490",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105173"}
@article{bb108462,
AUTHOR = "Ghose, S. and Prevost, J.J.",
TITLE = "FoleyGAN: Visually Guided Generative Adversarial Network-Based
Synchronous Sound Generation in Silent Videos",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "4508-4519",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105174"}
@article{bb108463,
AUTHOR = "Zhou, J.X. and Guo, D. and Wang, M.",
TITLE = "Contrastive Positive Sample Propagation Along the Audio-Visual Event
Line",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "7239-7257",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105175"}
@inproceedings{bb108464,
AUTHOR = "Zhou, J.X. and Zheng, L. and Zhong, Y.R. and Hao, S.J. and Wang, M.",
TITLE = "Positive Sample Propagation along the Audio-Visual Event Line",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "8432-8440",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105176"}
@article{bb108465,
AUTHOR = "Wang, X.S. and Xie, Q. and Zhu, J. and Xie, L. and Scharenborg, O.",
TITLE = "AnyoneNet: Synchronized Speech and Talking Head Generation for
Arbitrary Persons",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "6717-6728",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105177"}
@article{bb108466,
AUTHOR = "Yang, D. and Huang, S. and Jiang, W. and Zou, J.",
TITLE = "Implicit Memory-Based Variational Motion Talking Face Generation",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "431-435",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105178"}
@article{bb108467,
AUTHOR = "Cheng, H. and Guo, Y.Y. and Yin, J.H. and Chen, H. and Wang, J. and Nie, L.Q.",
TITLE = "Audio-Driven Talking Video Frame Restoration",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "4110-4122",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105179"}
@article{bb108468,
AUTHOR = "Sheng, Z.C. and Nie, L.Q. and Zhang, M. and Chang, X.J. and Yan, Y.",
TITLE = "Stochastic Latent Talking Face Generation Toward Emotional
Expressions and Head Poses",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "4",
MONTH = "April",
PAGES = "2734-2748",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105180"}
@article{bb108469,
AUTHOR = "Liu, M. and Li, D. and Li, Y.Q. and Song, X.M. and Nie, L.Q.",
TITLE = "Audio-Semantic Enhanced Pose-Driven Talking Head Generation",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "11",
MONTH = "November",
PAGES = "11056-11069",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105181"}
@article{bb108470,
AUTHOR = "Ahn, Y. and Chae, J. and Shin, J.W.",
TITLE = "Text-to-Speech With Lip Synchronization Based on Speech-Assisted
Text-to-Video Alignment and Masked Unit Prediction",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "961-965",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105182"}
@article{bb108471,
AUTHOR = "Han, T.S. and Gui, S.N. and Huang, Y.Q. and Li, B.H. and Liu, L.J. and Zhou, B.J. and Jiang, N. and Lu, Q. and Zhi, R.C. and Liang, Y.Y. and Zhang, D. and Wan, J.",
TITLE = "PMMTalk: Speech-Driven 3D Facial Animation From Complementary
Pseudo Multi-Modal Features",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "2570-2581",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105183"}
@inproceedings{bb108472,
AUTHOR = "Sinha, S. and Bhowmick, B. and Tiwari, L. and Chanda, S.",
TITLE = "DisFlowEm: One-Shot Emotional Talking Head Generation Using
Disentangled Pose and Expression Flow-Guidance",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4841-4851",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105184"}
@inproceedings{bb108473,
AUTHOR = "Fan, X. and Gao, H. and Chen, Z. and Chang, P. and Han, M. and Hasegawa Johnson, M.",
TITLE = "SyncDiff: Diffusion-Based Talking Head Synthesis with Bottlenecked
Temporal Visual Prior for Improved Synchronization",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4554-4563",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105185"}
@inproceedings{bb108474,
AUTHOR = "Zhang, L. and Mo, S.T. and Zhang, Y.J. and Morgado, P.",
TITLE = "Audio-synchronized Visual Animation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLI: 1-18",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105186"}
@inproceedings{bb108475,
AUTHOR = "Guan, J.Z. and Xu, Z.L. and Zhou, H. and Wang, K.Y. and He, S.Y. and Zhang, Z.W. and Liang, B.R. and Feng, H.C. and Ding, E. and Liu, J.T. and Wang, J.D. and Zhao, Y.J. and Liu, Z.W.",
TITLE = "Resyncer: Rewiring Style-based Generator for Unified Audio-Visually
Synced Facial Performer",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLI: 348-367",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105187"}
@inproceedings{bb108476,
AUTHOR = "Yaman, D. and Eyiokur, F.I. and Barmann, L. and Ekenel, H.K. and Waibel, A.",
TITLE = "Audio-driven Talking Face Generation with Stabilized Synchronization
Loss",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIX: 417-435",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105188"}
@inproceedings{bb108477,
AUTHOR = "Kim, H.K. and Lee, S. and Kim, H.G.",
TITLE = "Analyzing Visible Articulatory Movements in Speech Production for
Speech-Driven 3D Facial Animation",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "3575-3579",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105189"}
@inproceedings{bb108478,
AUTHOR = "Fernandez Labrador, C. and Akcay, M. and Abecassis, E. and Massich, J. and Schroers, C.",
TITLE = "DiVAS: Video and Audio Synchronization with Dynamic Frame Rates",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26836-26844",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105190"}
@inproceedings{bb108479,
AUTHOR = "Peng, Z.Q. and Hu, W.T. and Shi, Y. and Zhu, X.Y. and Zhang, X.M. and Zhao, H. and He, J. and Liu, H.Y. and Fan, Z.X.",
TITLE = "SyncTalk: The Devil is in the Synchronization for Talking Head
Synthesis",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "666-676",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105191"}
@inproceedings{bb108480,
AUTHOR = "Zhang, C.X. and Wang, C. and Zhao, Y.F. and Cheng, S. and Luo, L.J. and Guo, X.H.",
TITLE = "DR2: Disentangled Recurrent Representation Learning for
Data-efficient Speech Video Synthesis",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6192-6202",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105192"}
@inproceedings{bb108481,
AUTHOR = "Gupta, H.",
TITLE = "Perceptual Synchronization Scoring of Dubbed Content using
Phoneme-Viseme Agreement",
BOOKTITLE = VAQuality24,
YEAR = "2024",
PAGES = "392-402",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105193"}
@inproceedings{bb108482,
AUTHOR = "Lee, D. and Kim, C. and Yu, S.J. and Yoo, J. and Park, G.M.",
TITLE = "RADIO: Reference-Agnostic Dubbing Video Synthesis",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4156-4166",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105194"}
@inproceedings{bb108483,
AUTHOR = "Sung Bin, K. and Hyun, L. and Hong, D.H. and Nam, S. and Ju, J. and Oh, T.H.",
TITLE = "LaughTalk: Expressive 3D Talking Head Generation with Laughter",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6392-6401",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105195"}
@inproceedings{bb108484,
AUTHOR = "Mukhopadhyay, S. and Suri, S. and Gadde, R.T. and Shrivastava, A.",
TITLE = "Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5280-5290",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105196"}
@inproceedings{bb108485,
AUTHOR = "Niu, Z. and Mak, B.",
TITLE = "On the Audio-visual Synchronization for Lip-to-Speech Synthesis",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7809-7818",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105197"}
@inproceedings{bb108486,
AUTHOR = "Ki, T. and Min, D.",
TITLE = "StyleLipSync: Style-based Personalized Lip-sync Video Generation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22784-22793",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105198"}
@inproceedings{bb108487,
AUTHOR = "Guan, J.Z. and Zhang, Z.W. and Zhou, H. and Hu, T.S. and Wang, K.Y. and He, D.L. and Feng, H.C. and Liu, J.T. and Ding, E. and Liu, Z.W. and Wang, J.D.",
TITLE = "StyleSync: High-Fidelity Generalized and Personalized Lip Sync in
Style-Based Generator",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1505-1515",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105199"}
@inproceedings{bb108488,
AUTHOR = "Chatziagapi, A. and Athar, S. and Jain, A. and MV, R. and Bhat, V. and Samaras, D.",
TITLE = "LipNeRF: What is the right feature space to lip-sync a NeRF?",
BOOKTITLE = FG23,
YEAR = "2023",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105200"}
@inproceedings{bb108489,
AUTHOR = "Gupta, A. and Mukhopadhyay, R. and Balachandra, S. and Khan, F.F. and Namboodiri, V.P. and Jawahar, C.V.",
TITLE = "Towards Generating Ultra-High Resolution Talking-Face Videos with Lip
synchronization",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "5198-5207",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105201"}
@inproceedings{bb108490,
AUTHOR = "Zheng, A. and Zhu, F.X. and Zhu, H. and Luo, M. and He, R.",
TITLE = "Talking Face Generation via Learning Semantic and Temporal
Synchronous Landmarks",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3682-3689",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105202"}
@inproceedings{bb108491,
AUTHOR = "Lee, J.Y. and Chung, S.W. and Kim, S. and Kang, H.G. and Sohn, K.H.",
TITLE = "Looking into Your Speech: Learning Cross-modal Affinity for
Audio-visual Speech Separation",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "1336-1345",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105203"}
@inproceedings{bb108492,
AUTHOR = "Zheng, R.B. and Zhu, Z. and Song, B. and Ji, C.J.",
TITLE = "A Neural Lip-Sync Framework for Synthesizing Photorealistic Virtual
News Anchors",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "5286-5293",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105204"}
@inproceedings{bb108493,
AUTHOR = "Kumar, N. and Goel, S. and Narang, A. and Hasan, M.",
TITLE = "Robust One Shot Audio to Video Generation",
BOOKTITLE = DeepVision20,
YEAR = "2020",
PAGES = "3334-3343",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105205"}
@inproceedings{bb108494,
AUTHOR = "Shalev, Y. and Wolf, L.B.",
TITLE = "End to End Lip Synchronization with a Temporal AutoEncoder",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "330-339",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105206"}
@inproceedings{bb108495,
AUTHOR = "Wang, J. and Fang, Z. and Zhao, H.",
TITLE = "AlignNet: A Unifying Approach to Audio-Visual Alignment",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "3298-3306",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105207"}
@inproceedings{bb108496,
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/describe500syncav1.html#TT105208"}
@inproceedings{bb108497,
AUTHOR = "Yu, J.",
TITLE = "Speech Synchronized Tongue Animation by Combining Physiology Modeling
and X-ray Image Fitting",
BOOKTITLE = MMMod17,
YEAR = "2017",
PAGES = "I: 726-737",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT105209"}
@inproceedings{bb108498,
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/describe500syncav1.html#TT105210"}
@inproceedings{bb108499,
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/describe500syncav1.html#TT105211"}
Last update:Nov 26, 2025 at 20:24:09