{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:02:38Z","timestamp":1777568558871,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728891","type":"print"},{"value":"9783031728907","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-3-031-72890-7_19","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:45:24Z","timestamp":1733514324000},"page":"318-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Lost in\u00a0Translation: Latent Concept Misalignment in\u00a0Text-to-Image Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6638-2283","authenticated-orcid":false,"given":"Juntu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6313-7378","authenticated-orcid":false,"given":"Junyu","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1882-2960","authenticated-orcid":false,"given":"Yixin","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0912-9076","authenticated-orcid":false,"given":"Chongxuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0932-1631","authenticated-orcid":false,"given":"Zhijie","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8270-8448","authenticated-orcid":false,"given":"Dequan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"19_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"19_CR2","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"issue":"4","key":"19_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graph. (TOG) 42(4), 1\u201310 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"19_CR4","unstructured":"Chern, E., Su, J., Ma, Y., Liu, P.: Anole: an open, autoregressive and native multimodal models for interleaved image-text generation. GitHub repository (2024). https:\/\/github.com\/GAIR-NLP\/anole"},{"key":"19_CR5","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)"},{"key":"19_CR6","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"19_CR7","unstructured":"Ding, M., et\u00a0al.: CogView: mastering text-to-image generation via transformers. In: NeurIPS (2021)"},{"key":"19_CR8","unstructured":"Dong, Q., et al.: Large language model for science: a study on P vs. NP. arXiv preprint arXiv:2309.05689 (2023)"},{"key":"19_CR9","unstructured":"Du, Y., et al.: Reduce, reuse, recycle: compositional generation with energy-based diffusion models and MCMC. In: ICML (2023)"},{"key":"19_CR10","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. TPAMI (2021)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"19_CR12","unstructured":"Ho, J., et\u00a0al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"19_CR13","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"19_CR15","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. In: NeurIPS (2019)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"19_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/978-3-031-19790-1_26","volume-title":"Computer Vision \u2013 ECCV 2022","author":"N Liu","year":"2022","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 423\u2013439. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26"},{"key":"19_CR18","unstructured":"Mansimov, E., Parisotto, E., Ba, J.L., Salakhutdinov, R.: Generating images from captions with attention. arXiv preprint arXiv:1511.02793 (2015)"},{"key":"19_CR19","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"19_CR20","unstructured":"Midjourney: Midjourney (V5.2) [Text-to-Image Model] (2023). https:\/\/www.midjourney.com"},{"key":"19_CR21","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"19_CR22","unstructured":"OpenAI: ChatGPT (Aug 3 Version) [Large Language Model] (2023). https:\/\/chat.openai.com"},{"key":"19_CR23","unstructured":"OpenAI: Dall$$\\cdot $$e 3 system card. OpenAI technical report (2023)"},{"key":"19_CR24","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"19_CR25","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"19_CR26","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"19_CR27","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML (2016)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"19_CR29","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":"19_CR30","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)"},{"key":"19_CR31","unstructured":"Schuhmann, C., et\u00a0al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: NeurIPS (2022)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"19_CR33","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. arXiv preprint arXiv:2303.01469 (2023)"},{"key":"19_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"19_CR35","unstructured":"Wang, R., Chen, Z., Chen, C., Ma, J., Lu, H., Lin, X.: Compositional text-to-image synthesis with attention map control of diffusion models. arXiv preprint arXiv:2305.13921 (2023)"},{"key":"19_CR36","unstructured":"Wu, C., et al.: NUWA-infinity: autoregressive over autoregressive generation for infinite visual synthesis. arXiv preprint arXiv:2207.09814 (2022)"},{"key":"19_CR37","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977 (2023)"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. arXiv preprint arXiv:1711.10485 (2017)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"19_CR39","unstructured":"Yu, J., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.629"}],"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\/978-3-031-72890-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:06:18Z","timestamp":1733515578000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72890-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9783031728891","9783031728907"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72890-7_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 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"}}]}}