{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T01:55:27Z","timestamp":1776390927322,"version":"3.51.2"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031919060","type":"print"},{"value":"9783031919077","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\/978-3-031-91907-7_12","type":"book-chapter","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T15:45:19Z","timestamp":1748360719000},"page":"201-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Contextual Knowledge Pursuit for\u00a0Faithful Visual Synthesis"],"prefix":"10.1007","author":[{"given":"Jinqi","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwan Ho Ryan","family":"Chan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitris","family":"Dimos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ren\u00e9","family":"Vidal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"12_CR1","unstructured":"Betker, J., et al.: Improving image generation with better captions. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf (2023)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Bianchi, F., et al.: Easily accessible text-to-image generation amplifies demographic stereotypes at large scale. In: FAccT (2023)","DOI":"10.1145\/3593013.3594095"},{"key":"12_CR3","unstructured":"Blattmann, A., Rombach, R., Oktay, K., M\u00fcller, J., Ommer, B.: Semi-parametric neural image synthesis. In: NeurIPS (2022)"},{"key":"12_CR4","unstructured":"Chattopadhyay, A., Chan, K.H.R., Haeffele, B.D., Geman, D., Vidal, R.: Variational information pursuit for interpretable predictions. In: ICLR (2023)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Chattopadhyay, A., Slocum, S., Haeffele, B.D., Vidal, R., Geman, D.: Interpretable by design: Learning predictors by composing interpretable queries. In: IEEE TPAMI (2022)","DOI":"10.1109\/TPAMI.2022.3225162"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Zaharia, M., Zou, J.: How is ChatGPT\u2019s behavior changing over time? arXiv preprint arXiv:2307.09009 (2023)","DOI":"10.1162\/99608f92.5317da47"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Cho, J., Zala, A., Bansal, M.: DALL-Eval: probing the reasoning skills and social biases of text-to-image generation models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"12_CR8","unstructured":"Competition, G.U.I.E.: GUIE LAION-5B dataset. Kaggle (2022)"},{"key":"12_CR9","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: NeurIPS (2023)"},{"key":"12_CR10","unstructured":"Dhariwal, P., Nichol, A.Q.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"12_CR11","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.W.: REALM: retrieval-augmented language model pre-training. In: ICML (2020)"},{"key":"12_CR12","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: ICLR (2021)"},{"key":"12_CR13","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":"12_CR14","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"12_CR15","unstructured":"Hu, C., Fu, J., Du, C., Luo, S., Zhao, J.J., Zhao, H.: ChatDB: Augmenting LLMs with databases as their symbolic memory. arXiv preprint arXiv:2306.03901 (2023)"},{"key":"12_CR16","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"12_CR17","unstructured":"Izacard, G., et al.: Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)"},{"key":"12_CR18","unstructured":"Jiang, Z., et al.: Active retrieval augmented generation. arXiv preprint arXiv:2305.06983 (2023)"},{"key":"12_CR19","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. In: IEEE Transactions on Big Data (2019)"},{"key":"12_CR20","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. In: NeurIPS (2020)"},{"key":"12_CR21","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":"12_CR22","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: text-to-image diffusion models are zero-shot video generators. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: DiffusionCLIP: text-guided diffusion models for robust image manipulation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"12_CR24","unstructured":"Kwon, M., Jeong, J., Uh, Y.: Diffusion models already have a semantic latent space. In: ICLR (2023)"},{"key":"12_CR25","unstructured":"Lee, T., et al.: Holistic evaluation of text-to-image models. In: NeurIPS Datasets and Benchmarks Track (2023)"},{"key":"12_CR26","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: NeurIPS (2020)"},{"key":"12_CR27","unstructured":"Lian, L., Li, B., Yala, A., Darrell, T.: LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models. arXiv preprint arXiv:2305.13655 (2023)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: Common objects in context. arXiv preprint arXiv:1405.0312 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Luo, J., Wang, Z., Wu, C.H., Huang, D., Torre, F.D.L.: Zero-shot model diagnosis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01119"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: VideoFusion: decomposed diffusion models for high-quality video generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.10308948"},{"key":"12_CR32","unstructured":"Nguyen, T., Gadre, S.Y., Ilharco, G., Oh, S., Schmidt, L.: Improving multimodal datasets with image captioning. In: NeurIPS Datasets and Benchmarks Track (2023)"},{"key":"12_CR33","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: text-driven manipulation of StyleGAN imagery. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"12_CR35","unstructured":"Podell, D., et al.: SDXL: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"12_CR36","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: ICLR (2023)"},{"key":"12_CR37","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"12_CR38","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 (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR39","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NeurIPS (2016)"},{"key":"12_CR40","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: NeurIPS Datasets and Benchmarks Track (2022)"},{"key":"12_CR41","unstructured":"Secretariat, G.: Global biodiversity information facility backbone taxonomy. https:\/\/doi.org\/10.15468\/39omei (2014)"},{"key":"12_CR42","unstructured":"Shi, W., et al.: REPLUG: Retrieval-augmented black-box language models. arXiv preprint arXiv: 2301.12652 (2023)"},{"key":"12_CR43","unstructured":"Shonenkov, A., Konstantinov, M., Bakshandaeva, D., Schuhmann, C., Ivanova, K., Klokova, N.: DeepFloyd-IF. Hugging Face (2023)"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Si, C., Huang, Z., Jiang, Y., Liu, Z.: FreeU: Free lunch in diffusion U-Net. arXiv preprint arXiv:2309.11497 (2023)","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"12_CR45","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"12_CR46","unstructured":"Sterling, S.: Zeroscope v2. Hugging Face (2023)"},{"key":"12_CR47","unstructured":"Sun, Q., et al.: Generative pretraining in multimodality. arXiv preprint arXiv:2307.05222 (2023)"},{"key":"12_CR48","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 datase. Tech. Rep. CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Y.O., Chung, Y., Wu, C.H., De\u00a0la Torre, F.: Domain gap embeddings for generative dataset augmentation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02710"},{"key":"12_CR50","unstructured":"Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: NeurIPS (2023)"},{"key":"12_CR51","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lischinski, D., Shechtman, E.: StyleSpace analysis: disentangled controls for StyleGAN image generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"12_CR52","unstructured":"Yasunaga, M., et al.: Retrieval-augmented multimodal language modeling. In: ICML (2023)"},{"key":"12_CR53","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation. In: TMLR (2022)"},{"key":"12_CR54","unstructured":"Zakka, C., et al.: Almanac: Retrieval-augmented language models for clinical medicine. arXiv preprint arXiv:2303.01229 (2023)"},{"key":"12_CR55","unstructured":"Zhang, T., Zhang, Y., Vineet, V., Joshi, N., Wang, X.: Controllable text-to-image generation with GPT-4. arXiv preprint arXiv:2305.18583 (2023)"}],"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\/978-3-031-91907-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T15:45:39Z","timestamp":1748360739000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91907-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031919060","9783031919077"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91907-7_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"}}]}}