{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:25:11Z","timestamp":1776489911792,"version":"3.51.2"},"publisher-location":"Cham","reference-count":90,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200700","type":"print"},{"value":"9783031200717","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20071-7_38","type":"book-chapter","created":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T05:15:09Z","timestamp":1668230109000},"page":"650-667","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":105,"title":["CelebV-HQ: A Large-Scale Video Facial Attributes Dataset"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2155-1488","authenticated-orcid":false,"given":"Hao","family":"Zhu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-8151","authenticated-orcid":false,"given":"Wayne","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5483-0259","authenticated-orcid":false,"given":"Wentao","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8109-5598","authenticated-orcid":false,"given":"Liming","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3105-551X","authenticated-orcid":false,"given":"Siwei","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-2137","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,13]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Bezryadin, S., Bourov, P., Ilinih, D.: Brightness calculation in digital image processing. In: TDPF (2007)","DOI":"10.2352\/ISSN.2169-4672.2007.1.0.10"},{"key":"38_CR2","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2018)"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-GAN: periodic implicit generative adversarial networks for 3D-aware image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R.K., Duan, Z., Xu, C.: Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wu, Q., Zheng, C., Cham, T.J., Cai, J.: Sem2NeRF: converting single-view semantic masks to neural radiance fields. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19781-9_42"},{"key":"38_CR7","unstructured":"Cheng, W., et al.: Generalizable neural performer: Learning robust radiance fields for human novel view synthesis. arXiv preprint arxiv:2204.11798 (2022)"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: StarGAN v2: diverse image synthesis for multiple domains. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: deep speaker recognition. In: INTERSPEECH (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"38_CR10","first-page":"2233","volume":"10","author":"L Da Xu","year":"2014","unstructured":"Da Xu, L., He, W., Li, S.: Internet of things in industries: a survey. IEEE TII 10, 2233\u20132243 (2014)","journal-title":"IEEE TII"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Ding, H., Zhou, H., Zhou, S., Chellappa, R.: A deep cascade network for unaligned face attribute classification. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12303"},{"key":"38_CR12","doi-asserted-by":"publisher","first-page":"592","DOI":"10.3390\/s20030592","volume":"20","author":"A Dzedzickis","year":"2020","unstructured":"Dzedzickis, A., Kaklauskas, A., Bucinskas, V.: Human emotion recognition: review of sensors and methods. Sensors 20, 592 (2020)","journal-title":"Sensors"},{"key":"38_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201357","volume":"37","author":"A Ephrat","year":"2018","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM TOG 37, 1\u201311 (2018)","journal-title":"ACM TOG"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Gafni, G., Thies, J., Zollh\u00f6fer, M., Nie\u00dfner, M.: Dynamic neural radiance fields for monocular 4D facial avatar reconstruction. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Gao, G., Huang, H., Fu, C., Li, Z., He, R.: Information bottleneck disentanglement for identity swapping. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00341"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: VisualVoice: audio-visual speech separation with cross-modal consistency. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"38_CR17","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"38_CR18","unstructured":"Gu, J., Liu, L., Wang, P., Theobalt, C.: StyleNeRF: a style-based 3D aware generator for high-resolution image synthesis. In: ICLR (2021)"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, K., Liang, S., Liu, Y., Bao, H., Zhang, J.: AD-NeRF: audio driven neural radiance fields for talking head synthesis. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Haliassos, A., Vougioukas, K., Petridis, S., Pantic, M.: Lips don\u2019t lie: a generalisable and robust approach to face forgery detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"38_CR21","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1109\/TPAMI.2017.2738004","volume":"40","author":"H Han","year":"2017","unstructured":"Han, H., Jain, A.K., Wang, F., Shan, S., Chen, X.: Heterogeneous face attribute estimation: a deep multi-task learning approach. IEEE TPAMI 40, 2597\u20132609 (2017)","journal-title":"IEEE TPAMI"},{"key":"38_CR22","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)"},{"key":"38_CR23","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: CogVideo: large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868 (2022)"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"Hong, Y., Peng, B., Xiao, H., Liu, L., Zhang, J.: HeadNeRF: a real-time nerf-based parametric head model. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01973"},{"key":"38_CR25","unstructured":"Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: ECCV Workshop (2008)"},{"key":"38_CR26","doi-asserted-by":"crossref","unstructured":"Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Hui, T.W., Loy, C.C.: LiteFlowNet3: resolving correspondence ambiguity for more accurate optical flow estimation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58565-5_11"},{"key":"38_CR28","unstructured":"Inc., S.: Snapchat. In: https:\/\/www.snapchat.com\/ (2022)"},{"key":"38_CR29","volume":"32","author":"I Jegham","year":"2020","unstructured":"Jegham, I., Khalifa, A.B., Alouani, I., Mahjoub, M.A.: Vision-based human action recognition: an overview and real world challenges. Forensic Sci. Int.: Digit. Invest. 32, 200901 (2020)","journal-title":"Forensic Sci. Int.: Digit. Invest."},{"key":"38_CR30","doi-asserted-by":"crossref","unstructured":"Ji, X., et al.: Audio-driven emotional video portraits. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"38_CR31","unstructured":"Jiang, L., Dai, B., Wu, W., Loy, C.C.: Deceive D: adaptive pseudo augmentation for GAN training with limited data. In: NeurIPS (2021)"},{"key":"38_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Huang, Z., Pan, X., Loy, C.C., Liu, Z.: Talk-to-edit: fine-grained facial editing via dialog. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01354"},{"key":"38_CR33","doi-asserted-by":"crossref","unstructured":"Karkkainen, K., Joo, J.: FairFace: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00159"},{"key":"38_CR34","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR (2018)"},{"key":"38_CR35","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: NeurIPS (2021)"},{"key":"38_CR36","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"38_CR37","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of styleGAN. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"38_CR38","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"38_CR39","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, S., Kim, S., Park, J., Sohn, K.: Context-aware emotion recognition networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01024"},{"key":"38_CR40","doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, T., Jiang, M.: Quality assessment of in-the-wild videos. In: ACM MM (2019)","DOI":"10.1145\/3343031.3351028"},{"key":"38_CR41","unstructured":"Li, L., Bao, J., Yang, H., Chen, D., Wen, F.: FaceShifter: towards high fidelity and occlusion aware face swapping. arXiv preprint arxiv:1912.13457 (2019)"},{"key":"38_CR42","doi-asserted-by":"crossref","unstructured":"Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., Guo, B.: Face X-Ray for more general face forgery detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"38_CR43","doi-asserted-by":"crossref","unstructured":"Li, Y., Min, M., Shen, D., Carlson, D., Carin, L.: Video generation from text. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"38_CR44","doi-asserted-by":"crossref","unstructured":"Liang, B., et al.: Expressive talking head generation with granular audio-visual control. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"38_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"38_CR46","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S.R., Russo, F.A.: The Ryerson audio-visual database of emotional speech and song (Ravdess): a dynamic, multimodal set of facial and vocal expressions in north American english. PLoS ONE 13, e0196391 (2018)","journal-title":"PLoS ONE"},{"key":"38_CR47","unstructured":"Ltd., F.T.: Faceapp. In: https:\/\/www.faceapp.com\/ (2022)"},{"key":"38_CR48","unstructured":"Ltd., T.P.: Tiktok. In: https:\/\/www.tiktok.com (2022)"},{"key":"38_CR49","first-page":"4695","volume":"21","author":"A Mittal","year":"2012","unstructured":"Mittal, A., Moorthy, A.K., Bovik, A.C.: No-reference image quality assessment in the spatial domain. IEEE TIP 21, 4695\u20134708 (2012)","journal-title":"IEEE TIP"},{"key":"38_CR50","doi-asserted-by":"crossref","unstructured":"Munro, J., Damen, D.: Multi-modal domain adaptation for fine-grained action recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"38_CR51","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: INTERSPEECH (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"38_CR52","doi-asserted-by":"crossref","unstructured":"Or-El, R., Luo, X., Shan, M., Shechtman, E., Park, J.J., Kemelmacher-Shlizerman, I.: StyleSDF: high-resolution 3D-consistent image and geometry generation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01314"},{"key":"38_CR53","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Animatable neural radiance fields for modeling dynamic human bodies. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"38_CR54","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NeRF: neural radiance fields for dynamic scenes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"38_CR55","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arxiv:1511.06434 (2015)"},{"key":"38_CR56","unstructured":"R\u00f6ssler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nie\u00dfner, M.: FaceForensics: a large-scale video dataset for forgery detection in human faces. arXiv preprint arxiv:1803.09179 (2018)"},{"key":"38_CR57","doi-asserted-by":"crossref","unstructured":"Saito, M., Matsumoto, E., Saito, S.: Temporal generative adversarial nets with singular value clipping. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.308"},{"key":"38_CR58","unstructured":"Schmidt, L., Santurkar, S., Tsipras, D., Talwar, K., Madry, A.: Adversarially robust generalization requires more data. In: NeurIPS (2018)"},{"key":"38_CR59","doi-asserted-by":"crossref","unstructured":"Serengil, S.I., Ozpinar, A.: Hyperextended lightface: a facial attribute analysis framework. In: ICEET (2021)","DOI":"10.1109\/ICEET53442.2021.9659697"},{"key":"38_CR60","doi-asserted-by":"crossref","unstructured":"Shen, W., Liu, R.: Learning residual images for face attribute manipulation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.135"},{"issue":"4","key":"38_CR61","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1109\/TPAMI.2020.3034267","volume":"44","author":"Y Shen","year":"2022","unstructured":"Shen, Y., Yang, C., Tang, X., Zhou, B.: InterfaceGAN: interpreting the disentangled face representation learned by GANs. IEEE TPAMI 44(4), 2004\u20132018 (2022)","journal-title":"IEEE TPAMI"},{"key":"38_CR62","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. In: NeurIPS (2019)"},{"key":"38_CR63","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Tulyakov, S., Elhoseiny, M.: StyleGAN-v: a continuous video generator with the price, image quality and perks of styleGAN2. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"38_CR64","unstructured":"Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: NeurIPS (2014)"},{"key":"38_CR65","unstructured":"Tian, Y., et al.: A good image generator is what you need for high-resolution video synthesis. In: ICLR (2020)"},{"issue":"4","key":"38_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459838","volume":"40","author":"O Tov","year":"2021","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for styleGAN image manipulation. ACM TOG 40(4), 1\u201314 (2021)","journal-title":"ACM TOG"},{"key":"38_CR67","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"38_CR68","doi-asserted-by":"crossref","unstructured":"Tzaban, R., Mokady, R., Gal, R., Bermano, A.H., Cohen-Or, D.: Stitch it in time: GAN-based facial editing of real videos. arXiv preprint arxiv:2201.08361 (2022)","DOI":"10.1145\/3550469.3555382"},{"key":"38_CR69","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arxiv:1812.01717 (2018)"},{"key":"38_CR70","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NeurIPS (2016)"},{"key":"38_CR71","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"38_CR72","doi-asserted-by":"crossref","unstructured":"Wang, K., et al.: Mead: a large-scale audio-visual dataset for emotional talking-face generation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"38_CR73","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Mallya, A., Liu, M.Y.: One-shot free-view neural talking-head synthesis for video conferencing. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"38_CR74","unstructured":"Wu, C., et al.: N$$\\backslash $$\" uwa: visual synthesis pre-training for neural visual world creation. arXiv preprint arXiv:2111.12417 (2021)"},{"key":"38_CR75","doi-asserted-by":"crossref","unstructured":"Wu, W., Qian, C., Yang, S., Wang, Q., Cai, Y., Zhou, Q.: Look at boundary: a boundary-aware face alignment algorithm. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00227"},{"key":"38_CR76","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhang, Y., Li, C., Qian, C., Loy, C.C.: ReenactGAN: learning to reenact faces via boundary transfer. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_37"},{"key":"38_CR77","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Transeditor: transformer-based dual-space GAN for highly controllable facial editing. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00753"},{"key":"38_CR78","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: VideoGPT: video generation using VQ-VAE and transformers. arXiv preprint arxiv:2104.10157 (2021)"},{"key":"38_CR79","doi-asserted-by":"crossref","unstructured":"Yao, X., Newson, A., Gousseau, Y., Hellier, P.: A latent transformer for disentangled face editing in images and videos. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01353"},{"key":"38_CR80","doi-asserted-by":"crossref","unstructured":"Yao, X., Newson, A., Gousseau, Y., Hellier, P.: A latent transformer for disentangled face editing in images and videos. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01353"},{"key":"38_CR81","unstructured":"Yu, S., et al.: Generating videos with dynamics-aware implicit generative adversarial networks. In: ICLR (2021)"},{"key":"38_CR82","doi-asserted-by":"crossref","unstructured":"Zakharov, E., Ivakhnenko, A., Shysheya, A., Lempitsky, V.: Fast Bi-layer neural synthesis of one-shot realistic head avatars. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58610-2_31"},{"key":"38_CR83","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.inffus.2020.01.011","volume":"59","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Yin, Z., Chen, P., Nichele, S.: Emotion recognition using multi-modal data and machine learning techniques: a tutorial and review. Inf. Fusion 59, 103\u2013126 (2020)","journal-title":"Inf. Fusion"},{"key":"38_CR84","unstructured":"Zhong, Y., Sullivan, J., Li, H.: Face attribute prediction using off-the-shelf CNN features. In: ICB (2016)"},{"key":"38_CR85","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Y., Liu, Z., Luo, P., Wang, X.: Talking face generation by adversarially disentangled audio-visual representation. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"38_CR86","doi-asserted-by":"crossref","unstructured":"Zhou, H., Sun, Y., Wu, W., Loy, C.C., Wang, X., Liu, Z.: Pose-controllable talking face generation by implicitly modularized audio-visual representation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"38_CR87","unstructured":"Zhu, H., Fu, C., Wu, Q., Wu, W., Qian, C., He, R.: AOT: appearance optimal transport based identity swapping for forgery detection. In: NeurIPS (2020)"},{"key":"38_CR88","doi-asserted-by":"crossref","unstructured":"Zhu, H., Huang, H., Li, Y., Zheng, A., He, R.: Arbitrary talking face generation via attentional audio-visual coherence learning. In: IJCAI (2021)","DOI":"10.24963\/ijcai.2020\/327"},{"key":"38_CR89","first-page":"351","volume":"18","author":"H Zhu","year":"2021","unstructured":"Zhu, H., Luo, M.D., Wang, R., Zheng, A.H., He, R.: Deep audio-visual learning: a survey. IJAC 18, 351\u2013376 (2021)","journal-title":"IJAC"},{"key":"38_CR90","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, H., Fei, H., Lei, Z., Li, S.Z.: Face forgery detection by 3D decomposition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00295"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20071-7_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T22:24:54Z","timestamp":1678573494000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20071-7_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200700","9783031200717"],"references-count":90,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20071-7_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"13 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}