{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T18:53:57Z","timestamp":1760986437777,"version":"3.41.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915802","type":"print"},{"value":"9783031915819","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-91581-9_12","type":"book-chapter","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T15:24:15Z","timestamp":1748359455000},"page":"167-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Face Generation Quality and\u00a0Prompt Following with\u00a0Synthetic Captions"],"prefix":"10.1007","author":[{"given":"Michail","family":"Tarasiou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stylianos","family":"Moschoglou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiankang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanos","family":"Zafeiriou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"12_CR1","unstructured":"https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"12_CR2","unstructured":"https:\/\/huggingface.co\/stabilityai\/stable-diffusion-2-1"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Ververas, E., Kotsia, I., Zafeiriou, S.: Retinaface: single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"12_CR4","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis (2024)"},{"key":"12_CR5","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. CoRR abs\/2006.11239 (2020). https:\/\/arxiv.org\/abs\/2006.11239"},{"key":"12_CR6","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_CR7","unstructured":"Kapitanov, A., Kvanchiani, K., Sofia, K.: Easyportrait - face parsing and portrait segmentation dataset. arXiv preprint arXiv:2304.13509 (2023)"},{"key":"12_CR8","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models (2022)"},{"key":"12_CR9","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. CoRR abs\/1812.04948 (2018). http:\/\/arxiv.org\/abs\/1812.04948"},{"key":"12_CR10","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: Diffwave: a versatile diffusion model for audio synthesis. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=a-xFK8Ymz5J"},{"key":"12_CR11","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback (2022)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Pham, L., Vu, T.H., Tran, T.A.: Facial expression recognition using residual masking network. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 4513\u20134519. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9411919"},{"key":"12_CR13","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. CoRR abs\/2103.00020 (2021). https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"12_CR14","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR16","doi-asserted-by":"publisher","unstructured":"Serengil, S.I., Ozpinar, A.: Lightface: a hybrid deep face recognition framework. In: 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), pp. 23\u201327. IEEE (2020). https:\/\/doi.org\/10.1109\/ASYU50717.2020.9259802, https:\/\/ieeexplore.ieee.org\/document\/9259802","DOI":"10.1109\/ASYU50717.2020.9259802"},{"key":"12_CR17","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"12_CR18","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. CoRR abs\/2011.13456 (2020). https:\/\/arxiv.org\/abs\/2011.13456"},{"key":"12_CR19","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models (2023)"},{"key":"12_CR20","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena (2023)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: General facial representation learning in a visual-linguistic manner. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18697\u201318709 (2022)","DOI":"10.1109\/CVPR52688.2022.01814"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91581-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T15:24:22Z","timestamp":1748359462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91581-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915802","9783031915819"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91581-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}