{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T15:35:34Z","timestamp":1778600134262,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731129","type":"print"},{"value":"9783031731136","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73113-6_6","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T08:53:27Z","timestamp":1732092807000},"page":"89-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["PEA-Diffusion: Parameter-Efficient Adapter with\u00a0Knowledge Distillation in\u00a0Non-english Text-to-Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0057-3033","authenticated-orcid":false,"given":"Jian","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3498-2527","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6974-2019","authenticated-orcid":false,"given":"Qingsong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6332-2785","authenticated-orcid":false,"given":"Haonan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"6_CR1","unstructured":"Aggarwal, P., Kale, A.: Towards zero-shot cross-lingual image retrieval. arXiv preprint arXiv:2012.05107 (2020)"},{"key":"6_CR2","unstructured":"Carlsson, F., Eisen, P., Rekathati, F., Sahlgren, M.: Cross-lingual and multilingual clip. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 6848\u20136854 (2022)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, G., et al.: mCLIP: multilingual clip via cross-lingual transfer. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 13028\u201313043 (2023)","DOI":"10.18653\/v1\/2023.acl-long.728"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Liu, G., Zhang, B.W., Ye, F., Yang, Q., Wu, L.: AltCLIP: altering the language encoder in clip for extended language capabilities (2022)","DOI":"10.18653\/v1\/2023.findings-acl.552"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"6_CR6","unstructured":"Ding, M., et al.: Cogview: mastering text-to-image generation via transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 19822\u201319835 (2021)"},{"key":"6_CR7","unstructured":"Gu, J., et al.: Wukong: a 100 million large-scale Chinese cross-modal pre-training benchmark. In: Advances in Neural Information Processing Systems, vol. 35, pp. 26418\u201326431 (2022)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"6_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"6_CR10","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 6840\u20136851 (2020)"},{"key":"6_CR11","unstructured":"Hou, L., Huang, Z., Shang, L., Jiang, X., Chen, X., Liu, Q.: DynaBERT: dynamic BERT with adaptive width and depth. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9782\u20139793 (2020)"},{"key":"6_CR12","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models (2021)"},{"key":"6_CR13","unstructured":"Hu, J., et al.: Efficient cross-lingual transfer for Chinese stable diffusion with images as pivots. arXiv preprint arXiv:2305.11540 (2023)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: TinyBERT: distilling BERT for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"6_CR15","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation (2023)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Chang, C.Y., Rawls, S., Vuli\u0107, I., Korhonen, A.: Translation-enhanced multilingual text-to-image generation. arXiv preprint arXiv:2305.19216 (2023)","DOI":"10.18653\/v1\/2023.acl-long.510"},{"key":"6_CR18","unstructured":"Liu, S., Leng, D., Yin, Y.: Bridge diffusion model: bridge non-English language-native text-to-image diffusion model with English communities (2023)"},{"key":"6_CR19","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: Synthesizing high-resolution images with few-step inference (2023)"},{"key":"6_CR20","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"6_CR21","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Qin, C., et al.: GlueGEN: plug and play multi-modal encoders for x-to-image generation. arXiv preprint arXiv:2303.10056 (2023)","DOI":"10.1109\/ICCV51070.2023.02110"},{"key":"6_CR23","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR24","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022)"},{"key":"6_CR25","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"6_CR28","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding (2022)"},{"key":"6_CR29","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models (2022)"},{"key":"6_CR30","unstructured":"Xu, J., et al.: Imagereward: learning and evaluating human preferences for text-to-image generation (2023)"},{"key":"6_CR31","unstructured":"Yang, A., et al.: Chinese clip: contrastive vision-language pretraining in Chinese. arXiv preprint arXiv:2211.01335 (2022)"},{"key":"6_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-031-20083-0_4","volume-title":"Computer Vision - ECCV 2022","author":"Z Yang","year":"2022","unstructured":"Yang, Z., Li, Z., Shao, M., Shi, D., Yuan, Z., Yuan, C.: Masked generative distillation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 53\u201369. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_4"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Ye, F., Liu, G., Wu, X., Wu, L.: AltDiffusion: a multilingual text-to-image diffusion model (2023)","DOI":"10.1609\/aaai.v38i7.28487"},{"key":"6_CR34","unstructured":"Zhang, H., et al.: ERNIE-ViLG: unified generative pre-training for bidirectional vision-language generation. arXiv preprint arXiv:2112.15283 (2021)"},{"key":"6_CR35","unstructured":"Zhang, J., et al.: Fengshenbang 1.0: being the foundation of Chinese cognitive intelligence. CoRR abs\/2209.02970 (2022)"},{"key":"6_CR36","unstructured":"Zhang, J., et\u00a0al.: Fengshenbang 1.0: being the foundation of Chinese cognitive intelligence. arXiv preprint arXiv:2209.02970 (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73113-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T10:03:23Z","timestamp":1732097003000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73113-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031731129","9783031731136"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73113-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","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"}}]}}