{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:46:29Z","timestamp":1765503989872,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761554","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:18:04Z","timestamp":1762561084000},"page":"5583-5591","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["T-Stars-Poster: A Framework for Product-Centric Advertising Image Design"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7682-1775","authenticated-orcid":false,"given":"Hongyu","family":"Chen","sequence":"first","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7041-3959","authenticated-orcid":false,"given":"Min","family":"Zhou","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5424-6338","authenticated-orcid":false,"given":"Jing","family":"Jiang","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3309-9495","authenticated-orcid":false,"given":"Jiale","family":"Chen","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3103-3799","authenticated-orcid":false,"given":"Yang","family":"Lu","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7884-0044","authenticated-orcid":false,"given":"Zihang","family":"Lin","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3392-3293","authenticated-orcid":false,"given":"Bo","family":"Xiao","sequence":"additional","affiliation":[{"name":"Unaffiliated, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1381-2692","authenticated-orcid":false,"given":"Tiezheng","family":"Ge","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4037-6315","authenticated-orcid":false,"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"DAMO Academy. 2024. https:\/\/vision.aliyun.com\/experience\/detail?tagName=imageseg&children=SegmentHDCommonImage."},{"key":"e_1_3_2_1_2_1","volume-title":"Multidiffusion: Fusing diffusion paths for controlled image generation.","author":"Bar-Tal Omer","year":"2023","unstructured":"Omer Bar-Tal, Lior Yariv, Yaron Lipman, and Tali Dekel. 2023. Multidiffusion: Fusing diffusion paths for controlled image generation. (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680753"},{"key":"e_1_3_2_1_4_1","volume-title":"SceneBooth: Diffusion-based Framework for Subject-preserved Text-to-Image Generation. arXiv preprint arXiv:2501.03490","author":"Chai Shang","year":"2025","unstructured":"Shang Chai, Zihang Lin, Min Zhou, Xubin Li, Liansheng Zhuang, and Houqiang Li. 2025. SceneBooth: Diffusion-based Framework for Subject-preserved Text-to-Image Generation. arXiv preprint arXiv:2501.03490 (2025)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"e_1_3_2_1_7_1","unstructured":"Alimama Creative. 2024. https:\/\/huggingface.co\/alimama-creative\/EcomXL_controlnet_inpaint."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"e_1_3_2_1_9_1","unstructured":"Xiaoyi Dong Pan Zhang Yuhang Zang Yuhang Cao Bin Wang Linke Ouyang Xilin Wei Songyang Zhang Haodong Duan Maosong Cao et al. 2024. Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model. arXiv preprint arXiv:2401.16420 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Towards Reliable Advertising Image Generation Using Human Feedback. In European Conference on Computer Vision. Springer, 399-415","author":"Du Zhenbang","year":"2024","unstructured":"Zhenbang Du, Wei Feng, Haohan Wang, Yaoyu Li, Jingsen Wang, Jian Li, Zheng Zhang, Jingjing Lv, Xin Zhu, Junsheng Jin, et al., 2024. Towards Reliable Advertising Image Generation Using Human Feedback. In European Conference on Computer Vision. Springer, 399-415."},{"key":"e_1_3_2_1_11_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_14_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00583"},{"key":"e_1_3_2_1_16_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615028"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_1_20_1","unstructured":"Zhaochen Li Fengheng Li Wei Feng Honghe Zhu An Liu Yaoyu Li Zheng Zhang Jingjing Lv Xin Zhu Junjie Shen et al. 2023a. Planning and Rendering: Towards End-to-End Product Poster Generation. arXiv preprint arXiv:2312.08822 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611930"},{"key":"e_1_3_2_1_22_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024a. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"European Conference on Computer Vision. Springer, 38-55","author":"Liu Shilong","year":"2024","unstructured":"Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, et al., 2024c. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In European Conference on Computer Vision. Springer, 38-55."},{"key":"e_1_3_2_1_24_1","volume-title":"European Conference on Computer Vision. Springer, 361-377","author":"Liu Zeyu","year":"2024","unstructured":"Zeyu Liu, Weicong Liang, Zhanhao Liang, Chong Luo, Ji Li, Gao Huang, and Yuhui Yuan. 2024b. Glyph-byt5: A customized text encoder for accurate visual text rendering. In European Conference on Computer Vision. Springer, 361-377."},{"key":"e_1_3_2_1_25_1","volume-title":"Generating high fidelity images with subscale pixel networks and multidimensional upscaling. arXiv preprint arXiv:1812.01608","author":"Menick Jacob","year":"2018","unstructured":"Jacob Menick and Nal Kalchbrenner. 2018. Generating high fidelity images with subscale pixel networks and multidimensional upscaling. arXiv preprint arXiv:1812.01608 (2018)."},{"key":"e_1_3_2_1_26_1","unstructured":"OpenAI. 2024. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_2_1_27_1","unstructured":"PaddlePaddle. 2023. https:\/\/github.com\/PaddlePaddle\/PaddleOCR."},{"key":"e_1_3_2_1_28_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_29_1","first-page":"10674","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Rombach Robin","year":"2021","unstructured":"Robin Rombach, A. Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 10674-10685. https:\/\/api.semanticscholar.org\/CorpusID:245335280"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_31_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/a1859debfb3b59d094f3504d5ebb6c25-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_2_1_32_1","volume-title":"PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation. arXiv preprint arXiv:2404.00995","author":"Seol Jaejung","year":"2024","unstructured":"Jaejung Seol, Seojun Kim, and Jaejun Yoo. 2024. PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation. arXiv preprint arXiv:2404.00995 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.15098"},{"key":"e_1_3_2_1_35_1","volume-title":"Fourier features let networks learn high frequency functions in low dimensional domains. Advances in neural information processing systems","author":"Tancik Matthew","year":"2020","unstructured":"Matthew Tancik, Pratul Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan Barron, and Ren Ng. 2020. Fourier features let networks learn high frequency functions in low dimensional domains. Advances in neural information processing systems, Vol. 33 (2020), 7537-7547."},{"key":"e_1_3_2_1_36_1","volume-title":"International conference on machine learning. PMLR, 1747-1756","author":"Den Oord A\u00e4ron Van","year":"2016","unstructured":"A\u00e4ron Van Den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu. 2016. Pixel recurrent neural networks. In International conference on machine learning. PMLR, 1747-1756."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671636"},{"key":"e_1_3_2_1_38_1","unstructured":"Haohan Wang Wei Feng Yang Lu Yaoyu Li Zheng Zhang Jingjing Lv Xin Zhu Junjie Shen Zhangang Lin Lixing Bo et al. 2023. Generate E-commerce Product Background by Integrating Category Commonality and Personalized Style. arXiv preprint arXiv:2312.13309 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681495"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449910"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01209"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.24963\/IJCAI.2022\/692"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:42:14Z","timestamp":1765503734000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":45,"alternative-id":["10.1145\/3746252.3761554","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761554","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}