{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:46:38Z","timestamp":1772905598478,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372314"],"award-info":[{"award-number":["62372314"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the National Natural Science Foundation of China","award":["62276254"],"award-info":[{"award-number":["62276254"]}]},{"name":"HK RGC Theme-based Research Scheme","award":["T43-513\/23-N"],"award-info":[{"award-number":["T43-513\/23-N"]}]},{"name":"InnoHK program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680773","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"10669-10677","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Generative Active Learning for Image Synthesis Personalization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2473-460X","authenticated-orcid":false,"given":"Xulu","family":"Zhang","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University & CAIR, HKISI, CAS, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2347-4183","authenticated-orcid":false,"given":"Wengyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5706-5177","authenticated-orcid":false,"given":"Xiaoyong","family":"Wei","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7877-5728","authenticated-orcid":false,"given":"Jinlin","family":"Wu","sequence":"additional","affiliation":[{"name":"CASIA & CAIR, HKISI, CAS, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"CASIA & UCAS, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"CASIA & UCAS, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"SIGGRAPH Asia 2023 Conference. 1--10","author":"Arar Moab","unstructured":"Moab Arar, Rinon Gal, Yuval Atzmon, Gal Chechik, Daniel Cohen-Or, Ariel Shamir, and Amit H. Bermano. 2023. Domain-agnostic tuning-encoder for fast personalization of text-to-image models. In SIGGRAPH Asia 2023 Conference. 1--10."},{"key":"e_1_3_2_1_2_1","volume-title":"Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466","author":"Azizi Shekoofeh","year":"2023","unstructured":"Shekoofeh Azizi, Simon Kornblith, Chitwan Saharia, Mohammad Norouzi, and David J Fleet. 2023. Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704","author":"Chang Huiwen","year":"2023","unstructured":"Huiwen Chang, Han Zhang, Jarred Barber, AJ Maschinot, Jose Lezama, Lu Jiang, Ming-Hsuan Yang, Kevin Murphy, William T Freeman, Michael Rubinstein, et al. 2023. Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Learning Representations.","author":"Chen Hong","year":"2023","unstructured":"Hong Chen, Yipeng Zhang, Simin Wu, Xin Wang, Xuguang Duan, Yuwei Zhou, and Wenwu Zhu. 2023. Disenbooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_5_1","volume-title":"Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186","author":"Chen Wenhu","year":"2023","unstructured":"Wenhu Chen, Hexiang Hu, Yandong Li, Nataniel Rui, Xuhui Jia, Ming-Wei Chang, and William W Cohen. 2023. Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations.","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit Haim Bermano, Gal Chechik, and Daniel Cohen-or. 2022. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_8_1","volume-title":"Deep active learning over the long tail. arXiv preprint arXiv:1711.00941","author":"Geifman Yonatan","year":"2017","unstructured":"Yonatan Geifman and Ran El-Yaniv. 2017. Deep active learning over the long tail. arXiv preprint arXiv:1711.00941 (2017)."},{"key":"e_1_3_2_1_9_1","volume-title":"Advances in Neural Information Processing Systems","volume":"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, Vol. 27 (2014)."},{"key":"e_1_3_2_1_10_1","volume-title":"Svdiff: Compact parameter space for diffusion fine-tuning. arXiv preprint arXiv:2303.11305","author":"Han Ligong","year":"2023","unstructured":"Ligong Han, Yinxiao Li, Han Zhang, Peyman Milanfar, Dimitris Metaxas, and Feng Yang. 2023. Svdiff: Compact parameter space for diffusion fine-tuning. arXiv preprint arXiv:2303.11305 (2023)."},{"key":"e_1_3_2_1_11_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"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, Vol. 33 (2020), 6840--6851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00807"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_1_14_1","volume-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. arXiv preprint arXiv:2305.14720","author":"Li Dongxu","year":"2023","unstructured":"Dongxu Li, Junnan Li, and Steven CH Hoi. 2023. Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. arXiv preprint arXiv:2305.14720 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Cones: Concept neurons in diffusion models for customized generation. arXiv preprint arXiv:2303.05125","author":"Liu Zhiheng","year":"2023","unstructured":"Zhiheng Liu, Ruili Feng, Kai Zhu, Yifei Zhang, Kecheng Zheng, Yu Liu, Deli Zhao, Jingren Zhou, and Yang Cao. 2023. Cones: Concept neurons in diffusion models for customized generation. arXiv preprint arXiv:2303.05125 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Synthetic data for deep learning","author":"Nikolenko Sergey I","unstructured":"Sergey I Nikolenko. 2021. Synthetic data for deep learning. Vol. 174. Springer."},{"key":"e_1_3_2_1_17_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, Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","volume-title":"Tali Dekel, Aleksander Holynski, Angjoo Kanazawa, et al.","author":"Po Ryan","year":"2023","unstructured":"Ryan Po, Wang Yifan, Vladislav Golyanik, Kfir Aberman, Jonathan T Barron, Amit H Bermano, Eric Ryan Chan, Tali Dekel, Aleksander Holynski, Angjoo Kanazawa, et al. 2023. State of the art on diffusion models for visual computing. arXiv preprint arXiv:2310.07204 (2023)."},{"key":"e_1_3_2_1_19_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_1_20_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_1_21_1","volume-title":"IJCAI 2001 workshop on empirical methods in artificial intelligence","volume":"3","author":"Irina","unstructured":"Irina Rish et al. 2001. An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence, Vol. 3. 41--46."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_24_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, Vol. 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach. In International Conference on Learning Representations.","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Silvio Savarese. 2018. Active Learning for Convolutional Neural Networks: A Core-Set Approach. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130417"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"e_1_3_2_1_28_1","volume-title":"StyleDrop: Text-to-Image Generation in Any Style. In Conference on Neural Information Processing Systems. Neural Information Processing Systems Foundation.","author":"Sohn Kihyuk","year":"2023","unstructured":"Kihyuk Sohn, Nataniel Ruiz, Kimin Lee, Daniel Castro Chin, Irina Blok, Huiwen Chang, Jarred Barber, Lu Jiang, Glenn Entis, Yuanzhen Li, et al. 2023. StyleDrop: Text-to-Image Generation in Any Style. In Conference on Neural Information Processing Systems. Neural Information Processing Systems Foundation."},{"key":"e_1_3_2_1_29_1","volume-title":"Denoising Diffusion Implicit Models. In International Conference on Learning Representations.","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"e_1_3_2_1_31_1","first-page":"820","article-title":"A Survey on Active Learning: State-of-the-Art","volume":"11","author":"Tharwat Alaa","year":"2023","unstructured":"Alaa Tharwat and Wolfram Schenck. 2023. A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions. Mathematics, Vol. 11, 4 (2023), 820.","journal-title":"Practical Challenges and Research Directions. Mathematics"},{"key":"e_1_3_2_1_32_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. PMLR, 6295--6304","author":"Tran Toan","year":"2019","unstructured":"Toan Tran, Thanh-Toan Do, Ian Reid, and Gustavo Carneiro. 2019. Bayesian generative active deep learning. In International Conference on Machine Learning. PMLR, 6295--6304."},{"key":"e_1_3_2_1_34_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research, Vol. 9, 11 (2008).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_35_1","volume-title":"A new active labeling method for deep learning. In 2014 International joint conference on neural networks (IJCNN)","author":"Wang Dan","unstructured":"Dan Wang and Yi Shang. 2014. A new active labeling method for deep learning. In 2014 International joint conference on neural networks (IJCNN). IEEE, 112--119."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459371"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072356"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2222902"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"e_1_3_2_1_41_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721","author":"Ye Hu","year":"2023","unstructured":"Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)."},{"key":"e_1_3_2_1_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, Vol. 2, 3 (2022), 5."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28565"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"e_1_3_2_1_45_1","volume-title":"Generative adversarial active learning. arXiv preprint arXiv:1702.07956","author":"Zhu Jia-Jie","year":"2017","unstructured":"Jia-Jie Zhu and Jos\u00e9 Bento. 2017. Generative adversarial active learning. arXiv preprint arXiv:1702.07956 (2017)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680773","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:42Z","timestamp":1750294662000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680773"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":45,"alternative-id":["10.1145\/3664647.3680773","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680773","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}