{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:20:41Z","timestamp":1783437641861,"version":"3.54.6"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729881","type":"print"},{"value":"9783031729898","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72989-8_27","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"472-489","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An Empirical Study and\u00a0Analysis of\u00a0Text-to-Image Generation Using Large Language Model-Powered Textual Representation"],"prefix":"10.1007","author":[{"given":"Zhiyu","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengping","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luozheng","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"27_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"27_CR2","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Arar, M., et al.: Domain-agnostic tuning-encoder for fast personalization of text-to-image models. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618173"},{"key":"27_CR4","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. https:\/\/openai.com\/dall-e-3 (2023)"},{"key":"27_CR5","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"27_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR7","unstructured":"Chen, J., et\u00a0al.: PixArt-$$alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426 (2023)"},{"key":"27_CR8","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatGPT quality. https:\/\/vicuna.lmsys.org (2023)"},{"key":"27_CR9","unstructured":"Dai, X., et\u00a0al.: Emu: enhancing image generation models using photogenic needles in a haystack. arXiv preprint arXiv:2309.15807 (2023)"},{"key":"27_CR10","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR11","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. Adv. Neural. Inf. Process. Syst. 34, 19822\u201319835 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR12","first-page":"16890","volume":"35","author":"M Ding","year":"2022","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: CogView2: faster and better text-to-image generation via hierarchical transformers. Adv. Neural. Inf. Process. Syst. 35, 16890\u201316902 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR13","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: International Conference on Learning Representations (2023)"},{"key":"27_CR14","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":"27_CR15","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: Advances in Neural Information Processing Systems (2017)"},{"key":"27_CR16","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR17","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"27_CR18","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR19","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)"},{"key":"27_CR20","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5143773","author":"G Ilharco","year":"2021","unstructured":"Ilharco, G., et al.: OpenCLIP (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","journal-title":"OpenCLIP"},{"key":"27_CR21","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Li, X., Lan, W., Dong, J., Liu, H.: Adding Chinese captions to images. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, pp. 271\u2013275 (2016)","DOI":"10.1145\/2911996.2912049"},{"issue":"9","key":"27_CR23","doi-asserted-by":"publisher","first-page":"2347","DOI":"10.1109\/TMM.2019.2896494","volume":"21","author":"X Li","year":"2019","unstructured":"Li, X., et al.: COCO-CN for cross-lingual image tagging, captioning, and retrieval. IEEE Trans. Multimedia 21(9), 2347\u20132360 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"27_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"27_CR25","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":"27_CR26","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"27_CR27","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"27_CR28","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"27_CR29","unstructured":"OpenAI, T.: ChatGPT: optimizing language models for dialogue. OpenAI (2022)"},{"key":"27_CR30","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)"},{"key":"27_CR31","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"27_CR32","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":"27_CR33","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)"},{"key":"27_CR34","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":"27_CR35","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"27_CR36","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":"27_CR37","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"27_CR39","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR40","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR41","unstructured":"Shing, M., Sawada, K.: Japanese stable diffusion. https:\/\/github.com\/rinnakk\/japanese-stable-diffusion (2022)"},{"key":"27_CR42","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"27_CR43","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (2021)"},{"key":"27_CR44","unstructured":"Stability-AI: stable diffusion public release (2023)"},{"key":"27_CR45","unstructured":"Sun, K., et\u00a0al.: JourneyDB: a benchmark for generative image understanding. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"27_CR46","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"27_CR47","unstructured":"Wang, J., et al.: Fengshenbang 1.0: being the foundation of Chinese cognitive intelligence. arXiv preprint arXiv:2209.02970 (2022)"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Wu, C.H., De\u00a0la Torre, F.: A latent space of stochastic diffusion models for zero-shot image editing and guidance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7378\u20137387 (2023)","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"27_CR49","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual ChatGPT: talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671 (2023)"},{"key":"27_CR50","unstructured":"Wu, X., et al.: Taiyi-Diffusion-XL: advancing bilingual text-to-image generation with large vision-language model support. arXiv preprint arXiv:2401.14688 (2024)"},{"key":"27_CR51","unstructured":"Yang, A., et\u00a0al.: Baichuan 2: open large-scale language models. arXiv preprint arXiv:2309.10305 (2023)"},{"key":"27_CR52","unstructured":"Yang, A., et al.: Chinese CLIP: contrastive vision-language pretraining in Chinese. arXiv preprint arXiv:2211.01335 (2022)"},{"key":"27_CR53","unstructured":"Ye, F., Liu, G., Wu, X., Wu, L.: AltDiffusion: a multilingual text-to-image diffusion model. arXiv preprint arXiv:2308.09991 (2023)"},{"key":"27_CR54","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguis. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguis."},{"key":"27_CR55","unstructured":"Zhang, H., et al: ERNIE-ViLG: unified generative pre-training for bidirectional vision-language generation. arXiv preprint arXiv:2112.15283 (2021)"},{"key":"27_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"27_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"27_CR58","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)"}],"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\/978-3-031-72989-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:14:47Z","timestamp":1729876487000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72989-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031729881","9783031729898"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72989-8_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 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"}}]}}