@inproceedings{bb110600,
AUTHOR = "Zakharov, E. and Ivakhnenko, A. and Shysheya, A. and Lempitsky, V.",
TITLE = "Fast Bi-layer Neural Synthesis of One-shot Realistic Head Avatars",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XII: 524-540",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107272"}
@inproceedings{bb110601,
AUTHOR = "Chu, H. and Ma, S.G. and de la Torre, F. and Fidler, S. and Sheikh, Y.",
TITLE = "Expressive Telepresence via Modular Codec Avatars",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XII: 330-345",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107273"}
@inproceedings{bb110602,
AUTHOR = "Thies, J. and Elgharib, M. and Tewari, A. and Theobalt, C. and Nießner, M.",
TITLE = "Neural Voice Puppetry: Audio-driven Facial Reenactment",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XVI: 716-731",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107274"}
@inproceedings{bb110603,
AUTHOR = "Pang, W. and Wang, X.J.",
TITLE = "Guessing State Tracking for Visual Dialogue",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XVI: 683-698",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107275"}
@inproceedings{bb110604,
AUTHOR = "Das, D. and Biswas, S. and Sinha, S. and Bhowmick, B.",
TITLE = "Speech-driven Facial Animation Using Cascaded Gans for Learning of
Motion and Texture",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XXX: 408-424",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107276"}
@inproceedings{bb110605,
AUTHOR = "Shalev, Y. and Wolf, L.B.",
TITLE = "Image Animation with Perturbed Masks",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3637-3646",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107277"}
@inproceedings{bb110606,
AUTHOR = "Mittal, G. and Wang, B.",
TITLE = "Animating Face using Disentangled Audio Representations",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "3279-3287",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107278"}
@inproceedings{bb110607,
AUTHOR = "Chen, Z. and Liu, Z. and Hu, H. and Bai, J. and Lian, S. and Shi, F. and Wang, K.",
TITLE = "A Realistic Face-to-Face Conversation System Based on Deep Neural
Networks",
BOOKTITLE = ACVR19,
YEAR = "2019",
PAGES = "2575-2583",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107279"}
@inproceedings{bb110608,
AUTHOR = "Zakharov, E. and Shysheya, A. and Burkov, E. and Lempitsky, V.",
TITLE = "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "9458-9467",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107280"}
@inproceedings{bb110609,
AUTHOR = "Cudeiro, D. and Bolkart, T. and Laidlaw, C. and Ranjan, A. and Black, M.J.",
TITLE = "Capture, Learning, and Synthesis of 3D Speaking Styles",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "10093-10103",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107281"}
@inproceedings{bb110610,
AUTHOR = "Chen, L. and Maddox, R.K. and Duan, Z.Y. and Xu, C.L.",
TITLE = "Hierarchical Cross-Modal Talking Face Generation With Dynamic
Pixel-Wise Loss",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "7824-7833",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107282"}
@inproceedings{bb110611,
AUTHOR = "Chu, H. and Li, D.Q. and Fidler, S.",
TITLE = "A Face-to-Face Neural Conversation Model",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7113-7121",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107283"}
@inproceedings{bb110612,
AUTHOR = "Afouras, T. and Asano, Y.M. and Fagan, F. and Vedaldi, A. and Metze, F.",
TITLE = "Self-supervised object detection from audio-visual correspondence",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10565-10576",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107284"}
@inproceedings{bb110613,
AUTHOR = "Feng, C. and Chen, Z.Y. and Owens, A.",
TITLE = "Self-Supervised Video Forensics by Audio-Visual Anomaly Detection",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10491-10503",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107285"}
@inproceedings{bb110614,
AUTHOR = "Afouras, T. and Owens, A. and Chung, J.S. and Zisserman, A.",
TITLE = "Self-supervised Learning of Audio-visual Objects from Video",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XVIII:208-224",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107286"}
@inproceedings{bb110615,
AUTHOR = "Wiles, O. and Koepke, A.S. and Zisserman, A.",
TITLE = "Self-Supervised Learning of Class Embeddings from Video",
BOOKTITLE = CEFRL19,
YEAR = "2019",
PAGES = "3019-3027",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107287"}
@inproceedings{bb110616,
AUTHOR = "Wiles, O. and Koepke, A.S. and Zisserman, A.",
TITLE = "X2Face: A Network for Controlling Face Generation Using Images, Audio,
and Pose Codes",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XIII: 690-706",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107288"}
@inproceedings{bb110617,
AUTHOR = "Modrzejewski, M. and Rokita, P.",
TITLE = "Graphical Interface Design for Chatbots for the Needs of Artificial
Intelligence Support in Web and Mobile Applications",
BOOKTITLE = ICCVG18,
YEAR = "2018",
PAGES = "48-56",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107289"}
@inproceedings{bb110618,
AUTHOR = "Nakatani, S. and Saiki, S. and Nakamura, M. and Yasuda, K.",
TITLE = "Generating Personalized Virtual Agent in Speech Dialogue System for
People with Dementia",
BOOKTITLE = DHM18,
YEAR = "2018",
PAGES = "326-337",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107290"}
@inproceedings{bb110619,
AUTHOR = "Huber, B. and McDuff, D.",
TITLE = "Facial Expression Grounded Conversational Dialogue Generation",
BOOKTITLE = FG18,
YEAR = "2018",
PAGES = "365-372",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107291"}
@inproceedings{bb110620,
AUTHOR = "Luo, C. and Yu, J. and Li, X. and Zhang, L.",
TITLE = "HMM based speech-driven 3D tongue animation",
BOOKTITLE = ICIP17,
YEAR = "2017",
PAGES = "4377-4381",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107292"}
@inproceedings{bb110621,
AUTHOR = "Filntisis, P.P. and Katsamanis, A. and Maragos, P.",
TITLE = "Photorealistic adaptation and interpolation of facial expressions
using HMMS and AAMS for audio-visual speech synthesis",
BOOKTITLE = ICIP17,
YEAR = "2017",
PAGES = "2941-2945",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107293"}
@inproceedings{bb110622,
AUTHOR = "Filntisis, P.P. and Katsamanis, A. and Maragos, P.",
TITLE = "Demonstration of an HMM-based photorealistic expressive audio-visual
speech synthesis system",
BOOKTITLE = ICIP17,
YEAR = "2017",
PAGES = "4588-4588",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107294"}
@inproceedings{bb110623,
AUTHOR = "Wang, Y.B. and Khoo, E.T.",
TITLE = "Real-time stereoscopic rendering of realistic avatar for interactive
3D telepresence system",
BOOKTITLE = ICIVC17,
YEAR = "2017",
PAGES = "577-581",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107295"}
@inproceedings{bb110624,
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#TT107296"}
@inproceedings{bb110625,
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#TT107297"}
@inproceedings{bb110626,
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#TT107298"}
@inproceedings{bb110627,
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#TT107299"}
@inproceedings{bb110628,
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#TT107300"}
@inproceedings{bb110629,
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#TT107301"}
@inproceedings{bb110630,
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#TT107302"}
@inproceedings{bb110631,
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#TT107303"}
@inproceedings{bb110632,
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#TT107304"}
@inproceedings{bb110633,
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#TT107304"}
@inproceedings{bb110634,
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#TT107305"}
@inproceedings{bb110635,
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#TT107306"}
@inproceedings{bb110636,
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#TT107307"}
@inproceedings{bb110637,
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#TT107308"}
@inproceedings{bb110638,
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#TT107309"}
@inproceedings{bb110639,
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#TT107310"}
@inproceedings{bb110640,
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#TT107311"}
@inproceedings{bb110641,
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#TT107312"}
@inproceedings{bb110642,
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#TT107313"}
@inproceedings{bb110643,
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#TT107314"}
@inproceedings{bb110644,
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#TT107315"}
@inproceedings{bb110645,
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#TT107316"}
@inproceedings{bb110646,
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#TT107317"}
@inproceedings{bb110647,
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#TT107318"}
@inproceedings{bb110648,
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#TT107319"}
@inproceedings{bb110649,
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#TT107320"}
@inproceedings{bb110650,
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#TT107321"}
@inproceedings{bb110651,
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#TT107322"}
@inproceedings{bb110652,
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#TT107323"}
@inproceedings{bb110653,
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#TT107324"}
@inproceedings{bb110654,
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#TT107325"}
@inproceedings{bb110655,
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#TT107326"}
@inproceedings{bb110656,
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#TT107327"}
@inproceedings{bb110657,
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#TT107328"}
@inproceedings{bb110658,
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#TT107329"}
@inproceedings{bb110659,
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#TT107330"}
@inproceedings{bb110660,
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#TT107331"}
@inproceedings{bb110661,
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#TT107332"}
@inproceedings{bb110662,
AUTHOR = "Noh, J.Y. and Neumann, U.",
TITLE = "Talking Face",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TA1",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT107333"}
@inproceedings{bb110663,
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#TT107334"}
@inproceedings{bb110664,
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#TT107335"}
@inproceedings{bb110665,
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#TT107336"}
@inproceedings{bb110666,
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#TT107337"}
@article{bb110667,
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#TT107338"}
@inproceedings{bb110668,
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#TT107339"}
@inproceedings{bb110669,
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#TT107339"}
@inproceedings{bb110670,
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#TT107339"}
@article{bb110671,
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#TT107340"}
@inproceedings{bb110672,
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#TT107341"}
@inproceedings{bb110673,
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#TT107342"}
@inproceedings{bb110674,
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#TT107343"}
@article{bb110675,
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#TT107344"}
@inproceedings{bb110676,
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#TT107345"}
@article{bb110677,
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#TT107346"}
@inproceedings{bb110678,
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#TT107347"}
@article{bb110679,
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#TT107348"}
@article{bb110680,
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#TT107349"}
@article{bb110681,
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#TT107350"}
@article{bb110682,
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#TT107351"}
@article{bb110683,
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#TT107352"}
@article{bb110684,
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#TT107353"}
@article{bb110685,
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#TT107354"}
@article{bb110686,
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#TT107355"}
@article{bb110687,
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#TT107356"}
@inproceedings{bb110688,
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#TT107357"}
@article{bb110689,
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#TT107358"}
@article{bb110690,
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#TT107359"}
@article{bb110691,
AUTHOR = "Cheng, H. and Guo, Y.Y. and Yin, J.H. and Chen, H.N. 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#TT107360"}
@article{bb110692,
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#TT107361"}
@article{bb110693,
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#TT107362"}
@article{bb110694,
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#TT107363"}
@article{bb110695,
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#TT107364"}
@article{bb110696,
AUTHOR = "Peng, W.S. and Zhang, K.P.",
TITLE = "HarmoniDPO: Video-guided Audio Generation via Preference-Optimized
Diffusion",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "77",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT107365"}
@article{bb110697,
AUTHOR = "Ghosh, S. and Zalkow, F. and Jana, N.D.",
TITLE = "Enhanced Audio-Visual Speech Synthesis via Multi-Discriminative
Learning",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "1966-1975",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT107366"}
@article{bb110698,
AUTHOR = "Kim, J.Y. and Yun, H. and Kim, G.",
TITLE = "Towards Scene-Aware Video-to-Spatial Audio Generation",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "4",
MONTH = "April",
PAGES = "184",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT107367"}
@article{bb110699,
AUTHOR = "Zhong, W.Z. and Lin, J. and Chen, P.X. and Gao, F. and Lin, L. and Li, G.B.",
TITLE = "High-Fidelity and Lip-Synced Talking Face Synthesis via
Landmark-Based Diffusion Model",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "3369-3380",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT107368"}
Last update:May 24, 2026 at 14:46:09