@inproceedings{bb108300,
AUTHOR = "Wu, X.Z. and Sun, Y.T. and Chen, H. and Zhou, H. and Wang, J.D. and Liu, Z.Z. and Qi, X.J.",
TITLE = "3D-Aware Text-Driven Talking Avatar Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXVIII: 416-433",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105015"}
@inproceedings{bb108301,
AUTHOR = "Zhang, W.X. and Zhu, C.G. and Gao, J.N. and Yan, Y.C. and Zhai, G.T. and Yang, X.K.",
TITLE = "A Comparative Study of Perceptual Quality Metrics For Audio-Driven
Talking Head Videos",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "1218-1224",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105016"}
@inproceedings{bb108302,
AUTHOR = "Lei, H. and Bie, Z. and Jing, Z. and Bie, H.X.",
TITLE = "Talking-Head Video Compression With Motion Semantic Enhancement Model",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "1980-1986",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105017"}
@inproceedings{bb108303,
AUTHOR = "Xing, Y.Z. and He, Y.Q. and Tian, Z. and Wang, X.T. and Chen, Q.F.",
TITLE = "Seeing and Hearing: Open-domain Visual-Audio Generation with
Diffusion Latent Aligners",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7151-7161",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105018"}
@inproceedings{bb108304,
AUTHOR = "Mughal, M.H. and Dabral, R. and Habibie, I. and Donatelli, L. and Habermann, M. and Theobalt, C.",
TITLE = "ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech
Gesture Synthesis",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "1388-1398",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105019"}
@inproceedings{bb108305,
AUTHOR = "Mehta, S. and Deichler, A. and O'Regan, J. and Moell, B. and Beskow, J. and Henter, G.E. and Alexanderson, S.",
TITLE = "Fake it to make it: Using synthetic data to remedy the data shortage
in joint multi-modal speech-and-gesture synthesis",
BOOKTITLE = HUMOGen24,
YEAR = "2024",
PAGES = "1952-1964",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105020"}
@inproceedings{bb108306,
AUTHOR = "Zhang, Q. and Xiao, T. and Habeeb, H. and Laich, L. and Bouaziz, S. and Snape, P. and Zhang, W.J. and Cioffi, M. and Zhang, P.Z. and Pidlypenskyi, P. and Lin, W. and Ma, L. and Wang, M.J. and Li, K. and Long, C.J. and Song, S. and Prazak, M. and Sjoholm, A. and Deogade, A. and Lee, J. and Mangas, J.D. and Aubel, A.",
TITLE = "REFA: Real-time Egocentric Facial Animations for Virtual Reality",
BOOKTITLE = ABAW24,
YEAR = "2024",
PAGES = "4793-4802",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105021"}
@inproceedings{bb108307,
AUTHOR = "Yang, K.D. and Ranjan, A. and Chang, J.H.R. and Vemulapalli, R. and Tuzel, O.",
TITLE = "Probabilistic Speech-Driven 3D Facial Motion Synthesis: New
Benchmarks, Methods, and Applications",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27284-27293",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105022"}
@inproceedings{bb108308,
AUTHOR = "Liu, Y.F. and Cao, Q. and Wen, Y.D. and Jiang, H. and Ding, C.X.",
TITLE = "Towards Variable and Coordinated Holistic Co-Speech Motion Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "1566-1576",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105023"}
@inproceedings{bb108309,
AUTHOR = "Ng, E. and Romero, J. and Bagautdinov, T. and Bai, S.J. and Darrell, T.J. and Kanazawa, A. and Richard, A.",
TITLE = "From Audio to Photoreal Embodiment:
Synthesizing Humans in Conversations",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "1001-1010",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105024"}
@inproceedings{bb108310,
AUTHOR = "Zhang, Z.C. and Zheng, R. and Li, B. and Han, C.Y. and Li, T.Q. and Wang, M. and Guo, T.D. and Chen, J.D. and Liu, Z.W. and Yang, M.",
TITLE = "Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "5209-5219",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105025"}
@inproceedings{bb108311,
AUTHOR = "Jang, Y.J. and Kim, J.H. and Ahn, J. and Kwak, D. and Yang, H.S. and Ju, Y.C. and Kim, I.H. and Kim, B.Y. and Chung, J.S.",
TITLE = "Faces that Speak: Jointly Synthesising Talking Face and Speech from
Text",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8818-8828",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105026"}
@inproceedings{bb108312,
AUTHOR = "Aneja, S. and Thies, J. and Dai, A. and Niessner, M.",
TITLE = "FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head
Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "21263-21273",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105027"}
@inproceedings{bb108313,
AUTHOR = "Hogue, S. and Zhang, C.X. and Daruger, H. and Tian, Y.P. and Guo, X.H.",
TITLE = "DiffTED: One-shot Audio-driven TED Talk Video Generation with
Diffusion-based Co-speech Gestures",
BOOKTITLE = HUMOGen24,
YEAR = "2024",
PAGES = "1922-1931",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105028"}
@inproceedings{bb108314,
AUTHOR = "Yaman, D. and Eyiokur, F.I. and Barmann, L. and Akti, S. and Ekenel, H.K. and Waibel, A.",
TITLE = "Audio-Visual Speech Representation Expert for Enhanced Talking Face
Video Generation and Evaluation",
BOOKTITLE = NTIRE24,
YEAR = "2024",
PAGES = "6003-6013",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105029"}
@inproceedings{bb108315,
AUTHOR = "Pham, T.T. and Do, T. and Le, N. and Le, N. and Nguyen, H. and Tjiputra, E. and Tran, Q. and Nguyen, A.",
TITLE = "Style Transfer for 2D Talking Head Generation",
BOOKTITLE = GCV24,
YEAR = "2024",
PAGES = "7500-7509",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105030"}
@inproceedings{bb108316,
AUTHOR = "Xu, C. and Liu, Y. and Xing, J.Z. and Wang, W. and Sun, M.Z. and Dan, J. and Huang, T.X. and Li, S.Y. and Cheng, Z.Q. and Tai, Y. and Sun, B.",
TITLE = "FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking
Faces from Disentangled Audio",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "1292-1302",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105031"}
@inproceedings{bb108317,
AUTHOR = "Stypulkowski, M. and Vougioukas, K. and He, S. and Zieba, M. and Petridis, S. and Pantic, M.",
TITLE = "Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5089-5098",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105032"}
@inproceedings{bb108318,
AUTHOR = "Ni, H.M. and Liu, J.C. and Xue, Y. and Huang, S.X.",
TITLE = "3D-Aware Talking-Head Video Motion Transfer",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4942-4952",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105033"}
@inproceedings{bb108319,
AUTHOR = "Zhao, L. and Li, H.X. and Ning, X.F. and Jiang, X.",
TITLE = "THInImg: Cross-modal Steganography for Presenting Talking Heads in
Images",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5541-5550",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105034"}
@inproceedings{bb108320,
AUTHOR = "Liu, Y.F. and Lin, L.J. and Yu, F. and Zhou, C.Y. and Li, Y.",
TITLE = "MODA: Mapping-Once Audio-driven Portrait Animation with Dual
Attentions",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22963-22972",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105035"}
@inproceedings{bb108321,
AUTHOR = "Zheng, J.L. and Jang, Y. and Papaioannou, A. and Kampouris, C. and Potamias, R.A. and Papantoniou, F.P. and Galanakis, E. and Leonardis, A. and Zafeiriou, S.",
TITLE = "ILSH: The Imperial Light-Stage Head Dataset for Human Head View
Synthesis",
BOOKTITLE = RHWC23,
YEAR = "2023",
PAGES = "1104-1112",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105036"}
@inproceedings{bb108322,
AUTHOR = "Muaz, U. and Jang, W. and Tripathi, R. and Mani, S. and Ouyang, W.B. and Gadde, R.T. and Gecer, B. and Elizondo, S. and Madad, R. and Nair, N.",
TITLE = "SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant
Learning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7799-7808",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105037"}
@inproceedings{bb108323,
AUTHOR = "Li, W.C. and Zhang, L.H. and Wang, D. and Zhao, B. and Wang, Z.G. and Chen, M. and Zhang, B. and Wang, Z.J. and Bo, L. and Li, X.L.",
TITLE = "One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural
Radiance Field",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "17969-17978",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105038"}
@inproceedings{bb108324,
AUTHOR = "Jeong, Y.J. and Ryoo, W. and Lee, S.H. and Seo, D. and Byeon, W. and Kim, S. and Kim, J.",
TITLE = "The Power of Sound (TPoS): Audio Reactive Video Generation with
Stable Diffusion",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7788-7798",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105039"}
@inproceedings{bb108325,
AUTHOR = "Gururani, S. and Mallya, A. and Wang, T.C. and Valle, R. and Liu, M.Y.",
TITLE = "SPACE: Speech-driven Portrait Animation with Controllable Expression",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20857-20866",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105040"}
@inproceedings{bb108326,
AUTHOR = "Thambiraja, B. and Habibie, I. and Aliakbarian, S. and Cosker, D. and Theobalt, C. and Thies, J.",
TITLE = "Imitator: Personalized Speech-driven 3D Facial Animation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20564-20574",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105041"}
@inproceedings{bb108327,
AUTHOR = "Yang, P. and Wei, H. and Zhong, Y.C. and Wang, Z.S.",
TITLE = "Semi-supervised Speech-driven 3D Facial Animation via Cross-modal
Encoding",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20975-20984",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105042"}
@inproceedings{bb108328,
AUTHOR = "Wu, X.Z. and Hu, P.F. and Wu, Y. and Lyu, X.Y. and Cao, Y.P. and Shan, Y. and Yang, W.M. and Sun, Z.Q. and Qi, X.J.",
TITLE = "Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a
Short Video",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22111-22120",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105043"}
@inproceedings{bb108329,
AUTHOR = "He, S. and He, H. and Yang, S. and Wu, X.Y. and Xia, P.C. and Yin, B. and Liu, C. and Dai, L.R. and Xu, C.",
TITLE = "Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for
Speech-Driven 3D Facial Animation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "14146-14156",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105044"}
@inproceedings{bb108330,
AUTHOR = "Choi, J. and Hong, J. and Ro, Y.M.",
TITLE = "DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided
Speaker Embedding",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7778-7787",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105045"}
@inproceedings{bb108331,
AUTHOR = "Gong, Y. and Zhang, Y. and Cun, X.D. and Yin, F. and Fan, Y.B. and Wang, X. and Wu, B.Y. and Yang, Y.",
TITLE = "ToonTalker: Cross-Domain Face Reenactment",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7656-7666",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105046"}
@inproceedings{bb108332,
AUTHOR = "Yu, Z.T. and Yin, Z.X. and Zhou, D.Y. and Wang, D. and Wong, F. and Wang, B.Y.",
TITLE = "Talking Head Generation with Probabilistic Audio-to-Visual Diffusion
Priors",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7611-7621",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105047"}
@inproceedings{bb108333,
AUTHOR = "Oorloff, T. and Yacoob, Y.",
TITLE = "Expressive Talking Head Video Encoding in StyleGAN2 Latent Space",
BOOKTITLE = CVEU23,
YEAR = "2023",
PAGES = "2990-2999",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105048"}
@inproceedings{bb108334,
AUTHOR = "Chen, L.Y. and Wu, Z.Y. and Li, R. and Bao, W.H. and Ling, J. and Tan, X. and Zhao, S.",
TITLE = "VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial
Style Transfer",
BOOKTITLE = CVEU23,
YEAR = "2023",
PAGES = "2969-2979",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105049"}
@inproceedings{bb108335,
AUTHOR = "Hong, F.T. and Xu, D.",
TITLE = "Implicit Identity Representation Conditioned Memory Compensation
Network for Talking Head Video Generation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "23005-23015",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105050"}
@inproceedings{bb108336,
AUTHOR = "Nocentini, F. and Ferrari, C. and Berretti, S.",
TITLE = "Learning Landmarks Motion from Speech for Speaker-agnostic 3d Talking
Heads Generation",
BOOKTITLE = CIAP23,
YEAR = "2023",
PAGES = "I:340-351",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105051"}
@inproceedings{bb108337,
AUTHOR = "Wang, Q. and Li, D. and Liao, L. and Song, H. and Li, W. and Xiao, J.",
TITLE = "ASVFI: Audio-Driven Speaker Video Frame Interpolation",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "3200-3204",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105052"}
@inproceedings{bb108338,
AUTHOR = "Zeng, B. and Liu, X.H. and Gao, S.C. and Liu, B. and Li, H. and Liu, J.Z. and Zhang, B.C.",
TITLE = "Face Animation with an Attribute-Guided Diffusion Model",
BOOKTITLE = GCV23,
YEAR = "2023",
PAGES = "628-637",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105053"}
@inproceedings{bb108339,
AUTHOR = "Shen, S. and Zhao, W.L. and Meng, Z. and Li, W. and Zhu, Z. and Zhou, J. and Lu, J.W.",
TITLE = "DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven
Portraits Animation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1982-1991",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105054"}
@inproceedings{bb108340,
AUTHOR = "Zhang, B. and Qi, C.Y. and Zhang, P. and Zhang, B. and Wu, H.T. and Chen, D. and Chen, Q.F. and Wang, Y. and Wen, F.",
TITLE = "MetaPortrait: Identity-Preserving Talking Head Generation with Fast
Personalized Adaptation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22096-22105",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105055"}
@inproceedings{bb108341,
AUTHOR = "Vahdati, D.S. and Nguyen, T.D. and Stamm, M.C.",
TITLE = "Defending Low-Bandwidth Talking Head Videoconferencing Systems From
Real-Time Puppeteering Attacks",
BOOKTITLE = WMF23,
YEAR = "2023",
PAGES = "983-992",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105056"}
@inproceedings{bb108342,
AUTHOR = "Wang, D. and Deng, Y. and Yin, Z.X. and Shum, H.Y. and Wang, B.Y.",
TITLE = "Progressive Disentangled Representation Learning for Fine-Grained
Controllable Talking Head Synthesis",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "17979-17989",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105057"}
@inproceedings{bb108343,
AUTHOR = "Wang, J.Y. and Zhao, K. and Zhang, S.W. and Zhang, Y.Y. and Shen, Y.J. and Zhao, D.L. and Zhou, J.",
TITLE = "LipFormer: High-fidelity and Generalizable Talking Face Generation
with A Pre-learned Facial Codebook",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "13844-13853",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105058"}
@inproceedings{bb108344,
AUTHOR = "Zhong, W.Z. and Fang, C.W. and Cai, Y.Q. and Wei, P.X. and Zhao, G.M. and Lin, L. and Li, G.B.",
TITLE = "Identity-Preserving Talking Face Generation with Landmark and
Appearance Priors",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "9729-9738",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105059"}
@inproceedings{bb108345,
AUTHOR = "Zhang, W.X. and Cun, X.D. and Wang, X. and Zhang, Y. and Shen, X. and Guo, Y. and Shan, Y. and Wang, F.",
TITLE = "SadTalker: Learning Realistic 3D Motion Coefficients for Stylized
Audio-Driven Single Image Talking Face Animation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "8652-8661",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105060"}
@inproceedings{bb108346,
AUTHOR = "Gao, Y. and Zhou, Y. and Wang, J.L. and Li, X. and Ming, X. and Lu, Y.",
TITLE = "High-Fidelity and Freely Controllable Talking Head Video Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "5609-5619",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105061"}
@inproceedings{bb108347,
AUTHOR = "Huang, R.C. and Lai, P.W. and Qin, Y.P. and Li, G.B.",
TITLE = "Parametric Implicit Face Representation for Audio-Driven Facial
Reenactment",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "12759-12768",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105062"}
@inproceedings{bb108348,
AUTHOR = "Xing, J. and Xia, M. and Zhang, Y.C. and Cun, X.D. and Wang, J. and Wong, T.T.",
TITLE = "CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion
Prior",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "12780-12790",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105063"}
@inproceedings{bb108349,
AUTHOR = "Chatziagapi, A. and Samaras, D.",
TITLE = "AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "16878-16889",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105064"}
@inproceedings{bb108350,
AUTHOR = "Gustafson, J. and Szekely, E. and Alexandersson, S. and Beskow, J.",
TITLE = "Casual chatter or speaking up? Adjusting articulatory effort in
generation of speech and animation for conversational characters",
BOOKTITLE = FG23,
YEAR = "2023",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105065"}
@inproceedings{bb108351,
AUTHOR = "Agarwal, A. and Sen, B. and Mukhopadhyay, R. and Namboodiri, V. and Jawahar, C.V.",
TITLE = "Towards MOOCs for Lipreading: Using Synthetic Talking Heads to Train
Humans in Lipreading at Scale",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "2216-2225",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105066"}
@inproceedings{bb108352,
AUTHOR = "Agarwal, M. and Mukhopadhyay, R. and Namboodiri, V. and Jawahar, C.V.",
TITLE = "Audio-Visual Face Reenactment",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "5167-5176",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105067"}
@inproceedings{bb108353,
AUTHOR = "Kim, K. and Park, S. and Lee, J. and Chung, S. and Lee, J. and Choo, J.",
TITLE = "AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head
Reenactment",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "VIII:414-430",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105068"}
@inproceedings{bb108354,
AUTHOR = "Ling, J.W. and Wang, Z.B. and Lu, M. and Wang, Q. and Qian, C. and Xu, F.",
TITLE = "Structure-Aware Editable Morphable Model for 3D Facial Detail Animation
and Manipulation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "III:249-267",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105069"}
@inproceedings{bb108355,
AUTHOR = "Youwang, K. and Ji Yeon, K. and Oh, T.H.",
TITLE = "CLIP-Actor: Text-Driven Recommendation and Stylization for Animating
Human Meshes",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "III:173-191",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105070"}
@inproceedings{bb108356,
AUTHOR = "Zhou, M. and Bai, Y. and Zhang, W. and Yao, T. and Zhao, T.J. and Mei, T.",
TITLE = "Responsive Listening Head Generation: A Benchmark Dataset and Baseline",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVIII:124-142",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105071"}
@inproceedings{bb108357,
AUTHOR = "Hong, J. and Kim, M. and Ro, Y.M.",
TITLE = "VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via
Speech-Visage Feature Selection",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:452-468",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105072"}
@inproceedings{bb108358,
AUTHOR = "Shen, S. and Li, W.H. and Zhu, Z. and Duan, Y.Q. and Zhou, J. and Lu, J.W.",
TITLE = "Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head
Synthesis",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XII:666-682",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105073"}
@inproceedings{bb108359,
AUTHOR = "Liang, B. and Pan, Y. and Guo, Z.Z. and Zhou, H. and Hong, Z.B. and Han, X.G. and Han, J.Y. and Liu, J.T. and Ding, E. and Wang, J.D.",
TITLE = "Expressive Talking Head Generation with Granular Audio-Visual Control",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3377-3386",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105074"}
@inproceedings{bb108360,
AUTHOR = "Fan, Y.R. and Lin, Z.J. and Saito, J. and Wang, W.P. and Komura, T.",
TITLE = "FaceFormer: Speech-Driven 3D Facial Animation with Transformers",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18749-18758",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105075"}
@inproceedings{bb108361,
AUTHOR = "Liu, X. and Wu, Q.Y. and Zhou, H. and Xu, Y.H. and Qian, R. and Lin, X.Y. and Zhou, X.W. and Wu, W. and Dai, B. and Zhou, B.",
TITLE = "Learning Hierarchical Cross-Modal Association for Co-Speech Gesture
Generation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10452-10462",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105076"}
@inproceedings{bb108362,
AUTHOR = "Medina, S. and Tome, D. and Stoll, C. and Tiede, M. and Munhall, K. and Hauptmann, A. and Matthews, I.",
TITLE = "Speech Driven Tongue Animation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "20374-20384",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105077"}
@inproceedings{bb108363,
AUTHOR = "Song, H.K. and Woo, S.H. and Lee, J. and Yang, S.M. and Cho, H. and Lee, Y. and Choi, D. and Kim, K.W.",
TITLE = "Talking Face Generation with Multilingual TTS",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "21393-21398",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105078"}
@inproceedings{bb108364,
AUTHOR = "Richard, A. and Zollhofer, M. and Wen, Y.D. and de la Torre, F. and Sheikh, Y.",
TITLE = "MeshTalk: 3D Face Animation from Speech using Cross-Modality
Disentanglement",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1153-1162",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105079"}
@inproceedings{bb108365,
AUTHOR = "Zhang, C.X. and Zhao, Y.F. and Huang, Y.F. and Zeng, M. and Ni, S.F. and Budagavi, M. and Guo, X.H.",
TITLE = "FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute
Learning",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "3847-3856",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105080"}
@inproceedings{bb108366,
AUTHOR = "Guo, Y.D. and Chen, K.Y. and Liang, S. and Liu, Y.J. and Bao, H.J. and Zhang, J.Y.",
TITLE = "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head
Synthesis",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "5764-5774",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105081"}
@inproceedings{bb108367,
AUTHOR = "Meshry, M. and Suri, S. and Davis, L.S. and Shrivastava, A.",
TITLE = "Learned Spatial Representations for Few-shot Talking-Head Synthesis",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "13809-13818",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105082"}
@inproceedings{bb108368,
AUTHOR = "Wang, Q.L. and Zhang, L. and Li, B.",
TITLE = "SAFA: Structure Aware Face Animation",
BOOKTITLE = "3DV21",
YEAR = "2021",
PAGES = "679-688",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105083"}
@inproceedings{bb108369,
AUTHOR = "Zhou, H. and Sun, Y.S. and Wu, W. and Loy, C.C. and Wang, X.G. and Liu, Z.W.",
TITLE = "Pose-Controllable Talking Face Generation by Implicitly Modularized
Audio-Visual Representation",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "4174-4184",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105084"}
@inproceedings{bb108370,
AUTHOR = "Ye, S.Q. and Han, C. and Lin, J.Y. and Han, G.Q. and He, S.F.",
TITLE = "Coherence and Identity Learning for Arbitrary-length Face Video
Generation",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "915-922",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105085"}
@inproceedings{bb108371,
AUTHOR = "Liang, H. and Yu, L. and Xu, G. and Raj, B. and Singh, R.",
TITLE = "Controlled Autoencoders to Generate Faces from Voices",
BOOKTITLE = ISVC20,
YEAR = "2020",
PAGES = "I:476-487",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105086"}
@inproceedings{bb108372,
AUTHOR = "Liao, M. and Zhang, S. and Wang, P. and Zhu, H. and Zuo, X. and Yang, R.G.",
TITLE = "Speech2video Synthesis with 3d Skeleton Regularization and Expressive
Body Poses",
BOOKTITLE = ACCV20,
YEAR = "2020",
PAGES = "V:308-323",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105087"}
@inproceedings{bb108373,
AUTHOR = "Xue, H. and Ling, J. and Song, L. and Xie, R. and Zhang, W.",
TITLE = "Realistic Talking Face Synthesis With Geometry-Aware Feature
Transformation",
BOOKTITLE = ICIP20,
YEAR = "2020",
PAGES = "1581-1585",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105088"}
@inproceedings{bb108374,
AUTHOR = "Chen, L. and Cui, G.F. and Liu, C.L. and Li, Z. and Kou, Z. and Xu, Y. and Xu, C.L.",
TITLE = "Talking-head Generation with Rhythmic Head Motion",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "IX:35-51",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105089"}
@inproceedings{bb108375,
AUTHOR = "Khakhulin, T. and Sklyarova, V. and Lempitsky, V. and Zakharov, E.",
TITLE = "Realistic One-Shot Mesh-Based Head Avatars",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "II:345-362",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT105090"}
@inproceedings{bb108376,
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#TT105091"}
@inproceedings{bb108377,
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#TT105092"}
@inproceedings{bb108378,
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#TT105093"}
@inproceedings{bb108379,
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#TT105094"}
@inproceedings{bb108380,
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#TT105095"}
@inproceedings{bb108381,
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#TT105096"}
@inproceedings{bb108382,
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#TT105097"}
@inproceedings{bb108383,
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#TT105098"}
@inproceedings{bb108384,
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#TT105099"}
@inproceedings{bb108385,
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#TT105100"}
@inproceedings{bb108386,
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#TT105101"}
@inproceedings{bb108387,
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#TT105102"}
@inproceedings{bb108388,
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#TT105103"}
@inproceedings{bb108389,
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#TT105104"}
@inproceedings{bb108390,
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#TT105105"}
@inproceedings{bb108391,
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#TT105106"}
@inproceedings{bb108392,
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#TT105107"}
@inproceedings{bb108393,
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#TT105108"}
@inproceedings{bb108394,
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#TT105109"}
@inproceedings{bb108395,
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#TT105110"}
@inproceedings{bb108396,
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#TT105111"}
@inproceedings{bb108397,
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#TT105112"}
@inproceedings{bb108398,
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#TT105113"}
@inproceedings{bb108399,
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#TT105114"}
Last update:Nov 26, 2025 at 20:24:09