{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:09:00Z","timestamp":1788995340933,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375766","type":"print"},{"value":"9783032375773","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37577-3_20","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:56:51Z","timestamp":1788994611000},"page":"360-379","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DSH-Bench: A Difficulty and\u00a0Scenario-Aware Benchmark with\u00a0Hierarchical Subject Taxonomy for\u00a0Subject-Driven Text-to-Image Generation"],"prefix":"10.1007","author":[{"given":"Zhenyu","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Te","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luo","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longfei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengge","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Shu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"issue":"6","key":"20_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618322","volume":"42","author":"Y Alaluf","year":"2023","unstructured":"Alaluf, Y., Richardson, E., Metzer, G., Cohen-Or, D.: A neural space-time representation for text-to-image personalization. ACM Trans. Graph. (TOG) 42(6), 1\u201310 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"20_CR2","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"20_CR3","unstructured":"Balaji, Y., et al.: ediff-i: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"20_CR4","unstructured":"Batifol, S., et al.: Flux. 1 kontext: flow matching for in-context image generation and editing in latent space. arXiv e-prints pp. arXiv\u20132506 (2025)"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"20_CR6","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers. In: International Conference on Machine Learning, pp. 4055\u20134075. PMLR (2023)"},{"key":"20_CR7","doi-asserted-by":"publisher","first-page":"30286","DOI":"10.52202\/075280-1318","volume":"36","author":"W Chen","year":"2023","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. Adv. Neural. Inf. Process. Syst. 36, 30286\u201330305 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR8","unstructured":"Chen, Z., et al.: Dreamidentity: improved editability for efficient face-identity preserved image generation (2023). https:\/\/arxiv.org\/abs\/2307.00300"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR10","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":"20_CR11","unstructured":"Dong, R., et al.: Dreamllm: synergistic multimodal comprehension and creation. In: ICLR (2024)"},{"key":"20_CR12","unstructured":"Dosovitskiy, A., Brox, T.: Generating images with perceptual similarity metrics based on deep networks. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a029. Curran Associates, Inc. (2016). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2016\/file\/371bce7dc83817b7893bcdeed13799b5-Paper.pdf"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Fu, S., et al.: Dreamsim: learning new dimensions of human visual similarity using synthetic data. In: Advances in Neural Information Processing Systems, vol. 36, pp. 50742\u201350768 (2023)","DOI":"10.52202\/075280-2208"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: scene-based text-to-image generation with human priors. In: European Conference on Computer Vision, pp. 89\u2013106. Springer (2022)","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"20_CR15","doi-asserted-by":"publisher","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion (2022). https:\/\/doi.org\/10.48550\/ARXIV.2208.01618. https:\/\/arxiv.org\/abs\/2208.01618","DOI":"10.48550\/ARXIV.2208.01618"},{"key":"20_CR16","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=NAQvF08TcyG"},{"issue":"4","key":"20_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592133","volume":"42","author":"R Gal","year":"2023","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Encoder-based domain tuning for fast personalization of text-to-image models. ACM Trans. Graph. (TOG) 42(4), 1\u201313 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"20_CR18","unstructured":"Google: Introducing gemini 2.5 flash image, our state-of-the-art image model (2025). https:\/\/developers.googleblog.com\/introducing-gemini-2-5-flash-image\/. Accessed 15 Dec 2025"},{"key":"20_CR19","unstructured":"Han, I., Yang, S., Kwon, T., Ye, J.C.: Highly personalized text embedding for image manipulation by stable diffusion. arXiv preprint arXiv:2303.08767 (2023)"},{"key":"20_CR20","unstructured":"Hao, S., Han, K., Zhao, S., Wong, K.Y.K.: Vico: plug-and-play visual condition for personalized text-to-image generation. arXiv preprint arXiv:2306.00971 (2023)"},{"key":"20_CR21","unstructured":"He, J., Tuo, Y., Chen, B., Zhong, C., Geng, Y., Bo, L.: Anystory: towards unified single and multiple subject personalization in text-to-image generation (2025). https:\/\/arxiv.org\/abs\/2501.09503"},{"key":"20_CR22","unstructured":"Hu, H., et al.: Instruct-imagen: image generation with multi-modal instruction (2024). https:\/\/arxiv.org\/abs\/2401.01952"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Hu, H., et al.: Instruct-imagen: image generation with multi-modal instruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4754\u20134763 (2024)","DOI":"10.1109\/CVPR52733.2024.00455"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Hua, H., et al.: Mmig-bench: towards comprehensive and explainable evaluation of multi-modal image generation models. Adv. Neural. Inf. Process. Syst. 38 (2025)","DOI":"10.52202\/085713-4818"},{"key":"20_CR25","unstructured":"Hua, M., Liu, J., Ding, F., Liu, W., Wu, J., He, Q.: Dreamtuner: single image is enough for subject-driven generation (2023). https:\/\/arxiv.org\/abs\/2312.13691"},{"key":"20_CR26","unstructured":"Huang, L., Lin, H., Zhou, Y., Xiao, K.: Flexip: dynamic control of preservation and personality for customized image generation (2025). https:\/\/arxiv.org\/abs\/2504.07405"},{"key":"20_CR27","unstructured":"Huang, Z., et al.: Wegen: a unified model for interactive multimodal generation as we chat (2025). https:\/\/arxiv.org\/abs\/2503.01115"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"20_CR29","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"20_CR30","doi-asserted-by":"publisher","first-page":"36652","DOI":"10.52202\/075280-1594","volume":"36","author":"Y Kirstain","year":"2023","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. Adv. Neural. Inf. Process. Syst. 36, 36652\u201336663 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR31","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":"20_CR32","unstructured":"Le, D.H., et al.: One diffusion to generate them all (2024). https:\/\/arxiv.org\/abs\/2411.16318"},{"key":"20_CR33","doi-asserted-by":"publisher","first-page":"30146","DOI":"10.52202\/075280-1312","volume":"36","author":"D Li","year":"2023","unstructured":"Li, D., Li, J., Hoi, S.: Blip-diffusion: pre-trained subject representation for controllable text-to-image generation and editing. Adv. Neural. Inf. Process. Syst. 36, 30146\u201330166 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Li, Z., Cao, M., Wang, X., Qi, Z., Cheng, M.M., Shan, Y.: Photomaker: customizing realistic human photos via stacked id embedding (2023). https:\/\/arxiv.org\/abs\/2312.04461","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"20_CR35","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":"20_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., Rodriguez-Opazo, C., Teney, D., Gould, S.: Image retrieval on real-life images with pre-trained vision-and-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2125\u20132134 (2021)","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"20_CR37","unstructured":"Liu, Z., et al.: Cones 2: customizable image synthesis with multiple subjects (2023). https:\/\/arxiv.org\/abs\/2305.19327"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, J., Chen, C., Lu, H.: Subject-diffusion: open domain personalized text-to-image generation without test-time fine-tuning (2024). https:\/\/arxiv.org\/abs\/2307.11410","DOI":"10.1145\/3641519.3657469"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Mao, C., et al.: ACE++: instruction-based image creation and editing via context-aware content filling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1958\u20131966 (2025)","DOI":"10.1109\/ICCVW69036.2025.00207"},{"key":"20_CR40","unstructured":"Mao, Z., Huang, M., Ding, F., Liu, M., He, Q., Zhang, Y.: Realcustom++: representing images as real-word for real-time customization. arXiv e-prints pp. arXiv\u20132408 (2024)"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: Dreamo: a unified framework for image customization. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201312 (2025)","DOI":"10.1145\/3757377.3763956"},{"key":"20_CR42","unstructured":"OpenAI: Introducing gpt-4o and more tools to chatgpt free users (2024). https:\/\/openai.com\/index\/gpt-4o-and-more-tools-to-chatgpt-free\/. Accessed 15 June 2024"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Gal, R., Ostashev, D., Tulyakov, S., Aberman, K., Cohen-Or, D.: Nested attention: semantic-aware attention values for concept personalization (2025). https:\/\/arxiv.org\/abs\/2501.01407","DOI":"10.1145\/3721238.3730634"},{"key":"20_CR44","unstructured":"Patel, M., Jung, S., Baral, C., Yang, Y.: $$\\lambda $$-eclipse: multi-concept personalized text-to-image diffusion models by leveraging clip latent space. arXiv preprint arXiv:2402.05195 (2024)"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers (2023). https:\/\/arxiv.org\/abs\/2212.09748","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"20_CR46","unstructured":"Peng, Y., et al.: Dreambench++: a human-aligned benchmark for personalized image generation. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=4GSOESJrk6"},{"key":"20_CR47","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis (2023). https:\/\/arxiv.org\/abs\/2307.01952"},{"key":"20_CR48","doi-asserted-by":"publisher","unstructured":"Prashnani, E., Cai, H., Mostofi, Y., Sen, P.: Pieapp: perceptual image-error assessment through pairwise preference. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1808\u20131817 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00194","DOI":"10.1109\/CVPR.2018.00194"},{"key":"20_CR49","doi-asserted-by":"publisher","first-page":"79320","DOI":"10.52202\/075280-3472","volume":"36","author":"Z Qiu","year":"2023","unstructured":"Qiu, Z., et al.: Controlling text-to-image diffusion by orthogonal finetuning. Adv. Neural. Inf. Process. Syst. 36, 79320\u201379362 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR50","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"20_CR51","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":"20_CR52","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022). https:\/\/arxiv.org\/abs\/2112.10752","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"20_CR53","doi-asserted-by":"crossref","unstructured":"Rowles, C., Vainer, S., Nigris, D.D., Elizarov, S., Kutsy, K., Donn\u00e9, S.: Ipadapter-instruct: resolving ambiguity in image-based conditioning using instruct prompts (2024). https:\/\/arxiv.org\/abs\/2408.03209","DOI":"10.1007\/978-3-031-91838-4_4"},{"key":"20_CR54","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":"20_CR55","doi-asserted-by":"publisher","first-page":"36479","DOI":"10.52202\/068431-2643","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":"20_CR56","unstructured":"Shi, J., Xiong, W., Lin, Z., Jung, H.J.: Instantbooth: personalized text-to-image generation without test-time finetuning (2023). https:\/\/arxiv.org\/abs\/2304.03411"},{"key":"20_CR57","doi-asserted-by":"crossref","unstructured":"Slobodkin, A., et al.: Refvnli: towards scalable evaluation of subject-driven text-to-image generation. arXiv preprint arXiv:2504.17502 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.447"},{"key":"20_CR58","doi-asserted-by":"crossref","unstructured":"Sun, Q., et al.: Generative multimodal models are in-context learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14398\u201314409 (2024)","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"20_CR59","unstructured":"Sun, S., Qu, B., Liang, X., Fan, S., Gao, W.: IE-bench: advancing the measurement of text-driven image editing for human perception alignment. arXiv preprint arXiv:2501.09927 (2025)"},{"key":"20_CR60","doi-asserted-by":"crossref","unstructured":"Tan, Z., Liu, S., Yang, X., Xue, Q., Wang, X.: Ominicontrol: minimal and universal control for diffusion transformer. arXiv preprint arXiv:2411.15098 (2024)","DOI":"10.1109\/ICCV51701.2025.01386"},{"key":"20_CR61","unstructured":"Unsplash: Unsplash. https:\/\/unsplash.com\/. Accessed 23 June 2026"},{"key":"20_CR62","unstructured":"Voynov, A., Chu, Q., Cohen-Or, D., Aberman, K.: P+: extended textual conditioning in text-to-image generation (2023). https:\/\/arxiv.org\/abs\/2303.09522"},{"key":"20_CR63","unstructured":"Wang, H., Spinelli, M., Wang, Q., Bai, X., Qin, Z., Chen, A.: Instantstyle: free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733 (2024)"},{"key":"20_CR64","unstructured":"Wang, X., Fu, S., Huang, Q., He, W., Jiang, H.: MS-diffusion: multi-subject zero-shot image personalization with layout guidance. arXiv preprint arXiv:2406.07209 (2024)"},{"key":"20_CR65","unstructured":"Wang, Y., Zang, Y., Li, H., Jin, C., Wang, J.: Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236 (2025)"},{"key":"20_CR66","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)","DOI":"10.52202\/068431-1800"},{"key":"20_CR67","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: encoding visual concepts into textual embeddings for customized text-to-image generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15943\u201315953 (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"20_CR68","doi-asserted-by":"crossref","unstructured":"Wu, S., Huang, M., Wu, W., Cheng, Y., Ding, F., He, Q.: Less-to-more generalization: unlocking more controllability by in-context generation. arXiv preprint arXiv:2504.02160 (2025)","DOI":"10.1109\/ICCV51701.2025.01736"},{"key":"20_CR69","doi-asserted-by":"crossref","unstructured":"Wu, X., Sun, K., Zhu, F., Zhao, R., Li, H.: Human preference score: better aligning text-to-image models with human preference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2096\u20132105 (2023)","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"20_CR70","unstructured":"Xiao, S., et al.: Omnigen: unified image generation. arXiv preprint arXiv:2409.11340 (2024)"},{"key":"20_CR71","unstructured":"Xiong, Z., Xiong, W., Shi, J., Zhang, H., Song, Y., Jacobs, N.: Groundingbooth: grounding text-to-image customization (2025). https:\/\/arxiv.org\/abs\/2409.08520"},{"key":"20_CR72","unstructured":"Xu, J., et al.: Visionreward: fine-grained multi-dimensional human preference learning for image and video generation. arXiv preprint arXiv:2412.21059 (2024)"},{"key":"20_CR73","doi-asserted-by":"publisher","first-page":"15903","DOI":"10.52202\/075280-0700","volume":"36","author":"J Xu","year":"2023","unstructured":"Xu, J., et al.: Imagereward: learning and evaluating human preferences for text-to-image generation. Adv. Neural. Inf. Process. Syst. 36, 15903\u201315935 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR74","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"20_CR75","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et al.: Jedi: joint-image diffusion models for finetuning-free personalized text-to-image generation (2024). https:\/\/arxiv.org\/abs\/2407.06187","DOI":"10.1109\/CVPR52733.2024.00648"},{"key":"20_CR76","doi-asserted-by":"publisher","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00068","DOI":"10.1109\/CVPR.2018.00068"},{"key":"20_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: SSR-encoder: encoding selective subject representation for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8069\u20138078 (2024)","DOI":"10.1109\/CVPR52733.2024.00771"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37577-3_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:57:09Z","timestamp":1788994629000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37577-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375766","9783032375773"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37577-3_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}