{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:56:02Z","timestamp":1770965762509,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589335.3648315","type":"proceedings-article","created":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T18:41:21Z","timestamp":1715539281000},"page":"180-189","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["A New Creative Generation Pipeline for Click-Through Rate with Stable Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1277-2628","authenticated-orcid":false,"given":"Hao","family":"Yang","sequence":"first","affiliation":[{"name":"Shopee Discovery Ads, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0854-1001","authenticated-orcid":false,"given":"Jianxin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shopee Discovery Ads, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3296-2814","authenticated-orcid":false,"given":"Shuai","family":"Yang","sequence":"additional","affiliation":[{"name":"Shopee Discovery Ads, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0052-7814","authenticated-orcid":false,"given":"Linhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Shopee Discovery Ads, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9459-5901","authenticated-orcid":false,"given":"Shuo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shopee Discovery Ads, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6143-3043","authenticated-orcid":false,"given":"Yifan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Shopee Discovery Ads, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Christopher John Cornish Hellaby Watkins. 1989. Learning from delayed rewards. (1989)."},{"key":"e_1_3_2_2_2_1","volume-title":"Reducing the dimensionality of data with neural networks. science 313, 5786","author":"Hinton Geoffrey E","year":"2006","unstructured":"Geoffrey E Hinton and Ruslan R Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. science 313, 5786 (2006), 504--507."},{"key":"e_1_3_2_2_3_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_2_4_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_2_5_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5--9, 2015, Proceedings, Part III 18. Springer, 234--241."},{"key":"e_1_3_2_2_6_1","volume-title":"International conference on machine learning. PMLR, 1060--1069","author":"Reed Scott","year":"2016","unstructured":"Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, and Honglak Lee. 2016. Generative adversarial text to image synthesis. In International conference on machine learning. PMLR, 1060--1069."},{"key":"e_1_3_2_2_7_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_8_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_2_9_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_10_1","volume-title":"Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196","author":"Karras Tero","year":"2017","unstructured":"Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2017. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)."},{"key":"e_1_3_2_2_11_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272007"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Vincent Fran\u00e7ois-Lavet Peter Henderson Riashat Islam Marc G Bellemare Joelle Pineau et al. 2018. An introduction to deep reinforcement learning. Foundations and Trends\u00ae in Machine Learning 11 3--4 (2018) 219--354.","DOI":"10.1561\/2200000071"},{"key":"e_1_3_2_2_14_1","volume-title":"Aaron Van den Oord, and Oriol Vinyals","author":"Razavi Ali","year":"2019","unstructured":"Ali Razavi, Aaron Van den Oord, and Oriol Vinyals. 2019. Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the 28th ACM international conference on information and knowledge management. 2605--2613","author":"Zhao Zhichen","year":"2019","unstructured":"Zhichen Zhao, Lei Li, Bowen Zhang, Meng Wang, Yuning Jiang, Li Xu, Fengkun Wang, and Weiying Ma. 2019. What you look matters? offline evaluation of advertising creatives for cold-start problem. In Proceedings of the 28th ACM international conference on information and knowledge management. 2605--2613."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_2_18_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_3_2_2_19_1","volume-title":"Fashion Recommender Systems","author":"Vempati Sreekanth","unstructured":"Sreekanth Vempati, Korah T Malayil, V Sruthi, and R Sandeep. 2020. Enabling hyper-personalisation: Automated ad creative generation and ranking for fashion e-commerce. In Fashion Recommender Systems. Springer, 25--48."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412720"},{"key":"e_1_3_2_2_21_1","first-page":"852","article-title":"Alias-free generative adversarial networks","volume":"34","author":"Karras Tero","year":"2021","unstructured":"Tero Karras, Miika Aittala, Samuli Laine, Erik H\u00e4rk\u00f6nen, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2021. Alias-free generative adversarial networks. Advances in Neural Information Processing Systems 34 (2021), 852--863.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_22_1","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding Ming","year":"2021","unstructured":"Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, et al. 2021. Cogview: Mastering text-to-image generation via transformers. Advances in Neural Information Processing Systems 34 (2021), 19822--19835.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_23_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34 (2021), 8780--8794."},{"key":"e_1_3_2_2_24_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449910"},{"key":"e_1_3_2_2_26_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_27_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_2_28_1","first-page":"17480","article-title":"Projected gans converge faster","volume":"34","author":"Sauer Axel","year":"2021","unstructured":"Axel Sauer, Kashyap Chitta, Jens M\u00fcller, and Andreas Geiger. 2021. Projected gans converge faster. Advances in Neural Information Processing Systems 34 (2021), 17480--17492.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Machine Learning. PMLR, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821--8831."},{"key":"e_1_3_2_2_32_1","volume-title":"Caponimage: Context-driven dense-captioning on image. arXiv preprint arXiv:2204.12974","author":"Gao Yiqi","year":"2022","unstructured":"Yiqi Gao, Xinglin Hou, Yuanmeng Zhang, Tiezheng Ge, Yuning Jiang, and Peng Wang. 2022. Caponimage: Context-driven dense-captioning on image. arXiv preprint arXiv:2204.12974 (2022)."},{"key":"e_1_3_2_2_33_1","volume-title":"Composition-aware graphic layout GAN for visual-textual presentation designs. arXiv preprint arXiv:2205.00303","author":"Zhou Min","year":"2022","unstructured":"Min Zhou, Chenchen Xu, Ye Ma, Tiezheng Ge, Yuning Jiang, and Weiwei Xu. 2022. Composition-aware graphic layout GAN for visual-textual presentation designs. arXiv preprint arXiv:2205.00303 (2022)."},{"key":"e_1_3_2_2_34_1","volume-title":"Contrastive Learning for Topic-Dependent Image Ranking. In Workshop on Recommender Systems in Fashion and Retail. Springer, 79--98","author":"Ko Jihyeong","year":"2022","unstructured":"Jihyeong Ko, Jisu Jeong, and Kyumgmin Kim. 2022. Contrastive Learning for Topic-Dependent Image Ranking. In Workshop on Recommender Systems in Fashion and Retail. Springer, 79--98."},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of the 30th ACM International Conference on Multimedia. 7261--7269","author":"Liu Qi","year":"2022","unstructured":"ShiyaoWang, Qi Liu, Yicheng Zhong, Zhilong Zhou, Tiezheng Ge, Defu Lian, and Yuning Jiang. 2022. CreaGAN: An Automatic Creative Generation Framework for Display Advertising. In Proceedings of the 30th ACM International Conference on Multimedia. 7261--7269."},{"key":"e_1_3_2_2_36_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2 (2022), 3."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_3"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531855"},{"key":"e_1_3_2_2_40_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_2_2_42_1","volume-title":"Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al.","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al. 2022. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 2, 3 (2022), 5."},{"key":"e_1_3_2_2_43_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_2_45_1","volume-title":"Improving image generation with better captions. Computer Science. https:\/\/cdn. openai. com\/papers\/dall-e-3. pdf","author":"Betker James","year":"2023","unstructured":"James Betker, Gabriel Goh, and et.al. Jing. 2023. Improving image generation with better captions. Computer Science. https:\/\/cdn. openai. com\/papers\/dall-e-3. pdf (2023)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"e_1_3_2_2_47_1","volume-title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation. arXiv preprint arXiv:2308.05095","author":"Qu Leigang","year":"2023","unstructured":"Leigang Qu, Shengqiong Wu, Hao Fei, Liqiang Nie, and Tat-Seng Chua. 2023. LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation. arXiv preprint arXiv:2308.05095 (2023)."},{"key":"e_1_3_2_2_48_1","unstructured":"Simo Ryu. 2023. Low-rank adaptation for fast text-to-image diffusion fine-tuning."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614707"},{"key":"e_1_3_2_2_50_1","volume-title":"Staging e-commerce products for online advertising using retrieval assisted image generation. arXiv preprint arXiv:2307.15326","author":"Ku Yueh-Ning","year":"2023","unstructured":"Yueh-Ning Ku, Mikhail Kuznetsov, Shaunak Mishra, and Paloma de Juan. 2023. Staging e-commerce products for online advertising using retrieval assisted image generation. arXiv preprint arXiv:2307.15326 (2023)."},{"key":"e_1_3_2_2_51_1","volume-title":"Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301","author":"Black Kevin","year":"2023","unstructured":"Kevin Black, Michael Janner, Yilun Du, Ilya Kostrikov, and Sergey Levine. 2023. Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301 (2023)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584646"},{"key":"e_1_3_2_2_53_1","volume-title":"Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles. arXiv preprint arXiv:2303.03751","author":"Tang Zhiwei","year":"2023","unstructured":"Zhiwei Tang, Dmitry Rybin, and Tsung-Hui Chang. 2023. Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles. arXiv preprint arXiv:2303.03751 (2023)."}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3648315","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3648315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:38:36Z","timestamp":1755823116000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3648315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":53,"alternative-id":["10.1145\/3589335.3648315","10.1145\/3589335"],"URL":"https:\/\/doi.org\/10.1145\/3589335.3648315","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}