{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T16:11:00Z","timestamp":1788883860569,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374462","type":"print"},{"value":"9783032374479","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37447-9_12","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:49:06Z","timestamp":1788882546000},"page":"209-227","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EmoteGPT: 3D Human Facial Expressions from\u00a0Natural Language Descriptions"],"prefix":"10.1007","author":[{"given":"Haoran","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohit","family":"Mendiratta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Theobalt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Kortylewski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","unstructured":"Aneja, S., Thies, J., Dai, A., Niessner, M.: Clipface: Text-guided editing of textured 3d morphable models. In: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings. p. 1\u201311. SIGGRAPH \u201923, ACM (Jul 2023). https:\/\/doi.org\/10.1145\/3588432.3591566, http:\/\/dx.doi.org\/10.1145\/3588432.3591566","DOI":"10.1145\/3588432.3591566"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: 26th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH 1999). pp. 187\u2013194. ACM Press (1999)","DOI":"10.1145\/311535.311556"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Comas-Massagu\u00e9, A., Qiu, D., Chai, M., B\u00fchler, M., Raj, A., Gao, R., Xu, Q., Matthews, M., Gotardo, P., Camps, O., Orts-Escolano, S., Beeler, T.: Magicmirror: Fast and high-quality avatar generation with a constrained search space (2024), https:\/\/arxiv.org\/abs\/2404.01296","DOI":"10.1007\/978-3-031-72848-8_11"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Dan\u011b\u010dek, R., Black, M.J., Bolkart, T.: Emoca: emotion driven monocular face capture and animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20311\u201320322 (2022)","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Dan\u011b\u010dek, R., Chhatre, K., Tripathi, S., Wen, Y., Black, M., Bolkart, T.: Emotional speech-driven animation with content-emotion disentanglement. ACM (Dec 2023). https:\/\/doi.org\/10.1145\/3610548.3618183, https:\/\/emote.is.tue.mpg.de\/index.html","DOI":"10.1145\/3610548.3618183"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Egger, B.: 3D morphable face models\u2013past, present, and future. ACM Trans. Graph. (ToG) 39(5), 1\u201338 (2020)","DOI":"10.1145\/3395208"},{"key":"12_CR7","doi-asserted-by":"publisher","unstructured":"Egger, B., Sutherland, S., Medin, S.C., Tenenbaum, J.: Identity-expression ambiguity in 3D morphable face models . In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp.\u00a01\u20137. IEEE Computer Society, Los Alamitos, CA, USA (Dec 2021). https:\/\/doi.org\/10.1109\/FG52635.2021.9667002, https:\/\/doi.ieeecomputersociety.org\/10.1109\/FG52635.2021.9667002","DOI":"10.1109\/FG52635.2021.9667002"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Feng, Y., Lin, J., Dwivedi, S.K., Sun, Y., Patel, P., Black, M.J.: Chatpose: Chatting about 3D human pose. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: Imagebind: One embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15180\u201315190 (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"12_CR10","unstructured":"Hendrycks, D., Gimpel, K.: Bridging nonlinearities and stochastic regularizers with gaussian error linear units. CoRR abs\/1606.08415 (2016). http:\/\/arxiv.org\/abs\/1606.08415"},{"key":"12_CR11","unstructured":"Hu, E.J., et al.: LoRA: Low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Huang, X., et al.: Humannorm: Learning normal diffusion model for high-quality and realistic 3D human generation (2024)","DOI":"10.1109\/CVPR52733.2024.00437"},{"key":"12_CR13","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01354"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4217\u20134228 (Dec 2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2970919, https:\/\/doi.ieeecomputersociety.org\/10.1109\/TPAMI.2020.2970919","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Lisa: Reasoning segmentation via large language model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 36(6), 194:1\u2013194:17 (2017). https:\/\/doi.org\/10.1145\/3130800.3130813","DOI":"10.1145\/3130800.3130813"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.52202\/075280-1516"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, p. 36 (2024)","DOI":"10.52202\/075280-1516"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"12_CR20","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"12_CR21","unstructured":"Ma, Y., et al.: Talkclip: Talking head generation with text-guided expressive speaking styles (2024). https:\/\/arxiv.org\/abs\/2304.00334"},{"key":"12_CR22","doi-asserted-by":"publisher","unstructured":"Manu, P., Srivastava, A., Sharma, A.: Clip-head: Text-guided generation of textured neural parametric 3D head models. In: SIGGRAPH Asia 2023 Technical Communications. SA \u201923, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3610543.3626169","DOI":"10.1145\/3610543.3626169"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Mendiratta, M., et al.: Avatarstudio: Text-driven editing of 3d dynamic human head avatars. ACM Trans. Graph. 42(6) (Dec 2023). https:\/\/doi.org\/10.1145\/3618368","DOI":"10.1145\/3618368"},{"key":"12_CR24","doi-asserted-by":"publisher","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: A database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. 10(1), 18\u201331 (Jan 2019). https:\/\/doi.org\/10.1109\/TAFFC.2017.2740923","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"12_CR25","unstructured":"OpenAI, Achiam, J., et al.: GPT-4 technical report (2024)"},{"key":"12_CR26","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: Text-to-3D using 2D diffusion. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=FjNys5c7VyY"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Prinzler, M., Zakharov, E., Sklyarova, V., Kabadayi, B., Thies, J.: Joker: Conditional 3D head synthesis with extreme facial expressions (2024). https:\/\/arxiv.org\/abs\/2410.16395","DOI":"10.1109\/3DV66043.2025.00148"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Qian, S., Kirschstein, T., Schoneveld, L., Davoli, D., Giebenhain, S., Nie\u00dfner, M.: Gaussianavatars: Photorealistic head avatars with rigged 3D gaussians. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20299\u201320309 (2024)","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. SC \u201920, IEEE Press (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"12_CR30","doi-asserted-by":"publisher","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3505\u20133506. KDD \u201920, Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3394486.3406703","DOI":"10.1145\/3394486.3406703"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Retsinas, G., et al.: 3D facial expressions through analysis-by-neural-synthesis (2024). https:\/\/arxiv.org\/abs\/2404.04104","DOI":"10.1109\/CVPR52733.2024.00241"},{"key":"12_CR32","unstructured":"Su, Y., Lan, T., Li, H., Xu, J., Wang, Y., Cai, D.: Pandagpt: One model to instruction-follow them all . arXiv preprint arXiv:2305.16355 (2023)"},{"key":"12_CR33","doi-asserted-by":"publisher","unstructured":"Sun, J., Li, Q., Wang, W., Zhao, J., Sun, Z.: Multi-caption text-to-face synthesis: Dataset and algorithm. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2290\u20132298. MM \u201921, Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3474085.3475391","DOI":"10.1145\/3474085.3475391"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Tan, S., Ji, B., Pan, Y.: Style2talker: High-resolution talking head generation with emotion style and art style. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 5079\u20135087 (2024)","DOI":"10.1609\/aaai.v38i5.28313"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Taubner, F., Zhang, R., Tuli, M., Bahmani, S., Lindell, D.B.: MVP4D: Multi-view portrait video diffusion for animatable 4D avatars (2025). https:\/\/arxiv.org\/abs\/2510.12785","DOI":"10.1145\/3757377.3763889"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Taubner, F., Zhang, R., Tuli, M., Lindell, D.B.: CAP4D: Creating animatable 4D portrait avatars with morphable multi-view diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5318\u20135330 (2025)","DOI":"10.1109\/CVPR52734.2025.00501"},{"key":"12_CR37","unstructured":"Toisoul, A., Kossaifi, J., Bulat, A., Tzimiropoulos, G., Pantic, M.: Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Nature Machine Intelligence (2021). https:\/\/www.nature.com\/articles\/s42256-020-00280-0"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Wei, C., Liu, C., Qiao, S., Zhang, Z., Yuille, A., Yu, J.: De-diffusion makes text a strong cross-modal interface. arXiv preprint arXiv:2311.00618 (2023)","DOI":"10.1109\/CVPR52733.2024.01281"},{"key":"12_CR39","doi-asserted-by":"publisher","unstructured":"Wu, M., Zhu, H., Huang, L., Zhuang, Y., Lu, Y., Cao, X.: High-fidelity 3d face generation from natural language descriptions. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4521\u20134530. IEEE Computer Society, Los Alamitos, CA, USA (Jun 2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00439, https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52729.2023.00439","DOI":"10.1109\/CVPR52729.2023.00439"},{"key":"12_CR40","unstructured":"Wu, S., Fei, H., Qu, L., Ji, W., Chua, T.S.: Next-GPT: Any-to-any multimodal LLM. arXiv preprint arXiv:2309.05519 (2023)"},{"key":"12_CR41","doi-asserted-by":"publisher","unstructured":"Wu, Y., et al.: Portrait3D: Text-guided high-quality 3D portrait generation using pyramid representation and GANs prior. ACM Trans. Graph. 43(4) (Jul 2024). https:\/\/doi.org\/10.1145\/3658162","DOI":"10.1145\/3658162"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Xia, W., Yang, Y., Xue, J.H., Wu, B.: Tedigan: Text-guided diverse face image generation and manipulation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"12_CR43","unstructured":"Zheng, D., Cecilia, Z., Zhihao, X., Lars, J., Zhuowen, T., Xiuming, Z.: Diffusionrig: learning personalized priors for facial appearance editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with mt-bench and chatbot arena. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. NIPS \u201923, Curran Associates Inc., Red Hook, NY, USA (2023)","DOI":"10.52202\/075280-2020"},{"key":"12_CR45","doi-asserted-by":"publisher","unstructured":"Zhong, Y., Wei, H., Yang, P., Wang, Z.: Expclip: bridging text and facial expressions via semantic alignment. In: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence. AAAI\u201924\/IAAI\u201924\/EAAI\u201924, AAAI Press (2024). https:\/\/doi.org\/10.1609\/aaai.v38i7.28594","DOI":"10.1609\/aaai.v38i7.28594"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Jingwan, L., Jimei, Y., Hao, L.: On the continuity of rotation representations in neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00589"},{"key":"12_CR47","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Shimada, N.: Generative adversarial network for text-to-face synthesis and manipulation with pretrained BERT model. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp. 01\u201308 (2021). https:\/\/doi.org\/10.1109\/FG52635.2021.9666791","DOI":"10.1109\/FG52635.2021.9666791"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Ma, F., Fan, H., Yang, Z., Yang, Y.: Headstudio: Text to animatable head avatars with 3D Gaussian splatting (2024)","DOI":"10.1007\/978-3-031-73411-3_9"},{"key":"12_CR49","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Zielonka, W., Bolkart, T., Thies, J.: Towards metrical reconstruction of human faces. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19778-9_15"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37447-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:49:12Z","timestamp":1788882552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37447-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374462","9783032374479"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37447-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}