{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:09:53Z","timestamp":1765544993284,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":52,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680753","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"10774-10783","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Product2IMG: Prompt-Free E-commerce Product Background Generation with Diffusion Model and Self-Improved LMM"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2062-983X","authenticated-orcid":false,"given":"Tingfeng","family":"Cao","sequence":"first","affiliation":[{"name":"Alibaba Group, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9990-4941","authenticated-orcid":false,"given":"Junsheng","family":"Kong","sequence":"additional","affiliation":[{"name":"Alibaba Group, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9407-9919","authenticated-orcid":false,"given":"Xue","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8135-7523","authenticated-orcid":false,"given":"Wenqing","family":"Yao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4466-0946","authenticated-orcid":false,"given":"Junwei","family":"Ding","sequence":"additional","affiliation":[{"name":"Alibaba Group, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8751-5178","authenticated-orcid":false,"given":"Jinhui","family":"Zhu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3404-1559","authenticated-orcid":false,"given":"Jiandong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Marcelo Bertalmio Guillermo Sapiro Vincent Caselles and Coloma Ballester. 2000. Image inpainting. In SIGGRAPH. 417--424.","DOI":"10.1145\/344779.344972"},{"key":"e_1_3_2_1_3_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc?Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track. 1--11","author":"Cao Tingfeng","year":"2023","unstructured":"Tingfeng Cao, Chengyu Wang, Bingyan Liu, Ziheng Wu, Jinhui Zhu, and Jun Huang. 2023. Beautiful Prompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track. 1--11."},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Machine Learning. PMLR, 3676--3713","author":"Carta Thomas","year":"2023","unstructured":"Thomas Carta, Cl\u00e9ment Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, and Pierre-Yves Oudeyer. 2023. Grounding large language models in interactive environments with online reinforcement learning. In International Conference on Machine Learning. PMLR, 3676--3713."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00861"},{"key":"e_1_3_2_1_7_1","volume-title":"Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128","author":"Chen Xinyun","year":"2023","unstructured":"Xinyun Chen, Maxwell Lin, Nathanael Sch\u00e4rli, and Denny Zhou. 2023. Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Thomas Dideriksen, Himanshu Arora, Matthieu Guillaumin, and Jitendra Malik.","author":"Collins Jasmine","year":"2022","unstructured":"Jasmine Collins, Shubham Goel, Kenan Deng, Achleshwar Luthra, Leon Xu, Erhan Gundogdu, Xi Zhang, Tomas F Yago Vicente, Thomas Dideriksen, Himanshu Arora, Matthieu Guillaumin, and Jitendra Malik. 2022. ABO: Dataset and Benchmarks for Real-World 3D Object Understanding. CVPR (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"e_1_3_2_1_10_1","volume-title":"A survey on in-context learning. arXiv preprint arXiv:2301.00234","author":"Dong Qingxiu","year":"2022","unstructured":"Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, and Zhifang Sui. 2022. A survey on in-context learning. arXiv preprint arXiv:2301.00234 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Gautam. 2019. Image dataset. https:\/\/doi.org\/10.5281\/zenodo.3356917","DOI":"10.5281\/zenodo.3356917"},{"key":"e_1_3_2_1_12_1","volume-title":"Weinberger (Eds.)","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. In Advances in Neural Information Processing Systems, Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K.Q. Weinberger (Eds.), Vol. 27. Curran Associates, Inc."},{"key":"e_1_3_2_1_13_1","volume-title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. In Second Agent Learning in Open-Endedness Workshop.","author":"Gou Zhibin","year":"2023","unstructured":"Zhibin Gou, Zhihong Shao, Yeyun Gong, Yujiu Yang, Nan Duan, Weizhu Chen, et al. 2023. CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. In Second Agent Learning in Open-Endedness Workshop."},{"key":"e_1_3_2_1_14_1","volume-title":"Optimizing prompts for text-to-image generation. Advances in Neural Information Processing Systems 36","author":"Hao Yaru","year":"2024","unstructured":"Yaru Hao, Zewen Chi, Li Dong, and Furu Wei. 2024. Optimizing prompts for text-to-image generation. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30","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 30 (2017)."},{"key":"e_1_3_2_1_16_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 33 (2020), 6840--6851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","volume-title":"Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han.","author":"Huang Jiaxin","year":"2022","unstructured":"Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. 2022. Large language models can self-improve. arXiv preprint arXiv:2210.11610 (2022)."},{"key":"e_1_3_2_1_18_1","unstructured":"Yipo Huang Quan Yuan Xiangfei Sheng Zhichao Yang Haoning Wu Pengfei Chen Yuzhe Yang Leida Li and Weisi Lin. 2024. AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception. arXiv:2401.08276 [cs.CV]"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00213"},{"key":"e_1_3_2_1_20_1","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras Tero","year":"2022","unstructured":"Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine. 2022. Elucidating the design space of diffusion-based generative models. Advances in Neural Information Processing Systems 35 (2022), 26565--26577.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","volume-title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation. arXiv preprint arXiv:2305.01569","author":"Kirstain Yuval","year":"2023","unstructured":"Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, and Omer Levy. 2023. Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation. arXiv preprint arXiv:2305.01569 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models. Transactions on Machine Learning Research","author":"Lian Long","year":"2024","unstructured":"Long Lian, Boyi Li, Adam Yala, and Trevor Darrell. 2024. LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models. Transactions on Machine Learning Research (2024). https: \/\/openreview.net\/forum?id=hFALpTb4fR Featured Certification."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01371"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_2_1_25_1","volume-title":"Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems 36","author":"Madaan Aman","year":"2024","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. 2024. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453","author":"Mou Chong","year":"2023","unstructured":"Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, and Xiaohu Qie. 2023. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Making images real again: A comprehensive survey on deep image composition. arXiv preprint arXiv:2106.14490","author":"Niu Li","year":"2021","unstructured":"Li Niu, Wenyan Cong, Liu Liu, Yan Hong, Bo Zhang, Jing Liang, and Liqing Zhang. 2021. Making images real again: A comprehensive survey on deep image composition. arXiv preprint arXiv:2106.14490 (2021)."},{"key":"e_1_3_2_1_28_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. In The Twelfth International Conference on Learning Representations.","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. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_29_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_30_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","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 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_32_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_1_33_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_1_34_1","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade W Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Machine Learning. PMLR, 2256--2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning. PMLR, 2256--2265."},{"key":"e_1_3_2_1_36_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613806"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.299"},{"key":"e_1_3_2_1_40_1","volume-title":"In-Memory Learning: A Declarative Learning Framework for Large Language Models. arXiv preprint arXiv:2403.02757","author":"Wang Bo","year":"2024","unstructured":"Bo Wang, Tianxiang Sun, Hang Yan, Siyin Wang, Qingyuan Cheng, and Xipeng Qiu. 2024. In-Memory Learning: A Declarative Learning Framework for Large Language Models. arXiv preprint arXiv:2403.02757 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896","author":"Wang Zijie J","year":"2022","unstructured":"Zijie J Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen Horng Chau. 2022. Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022), 24824--24837."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351083"},{"key":"e_1_3_2_1_44_1","volume-title":"Understanding and improving the realism of image composites. ACM Transactions on graphics (TOG) 31, 4","author":"Xue Su","year":"2012","unstructured":"Su Xue, Aseem Agarwala, Julie Dorsey, and Holly Rushmeier. 2012. Understanding and improving the realism of image composites. ACM Transactions on graphics (TOG) 31, 4 (2012), 1--10."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_46_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Yang Chengrun","year":"2023","unstructured":"Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. 2023. Large Language Models as Optimizers. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_47_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_48_1","volume-title":"Self-taught optimizer (stop): Recursively self-improving code generation. arXiv preprint arXiv:2310.02304","author":"Zelikman Eric","year":"2023","unstructured":"Eric Zelikman, Eliana Lorch, Lester Mackey, and Adam Tauman Kalai. 2023. Self-taught optimizer (stop): Recursively self-improving code generation. arXiv preprint arXiv:2310.02304 (2023)."},{"key":"e_1_3_2_1_49_1","first-page":"15476","article-title":"Star: Bootstrapping reasoning with reasoning","volume":"35","author":"Zelikman Eric","year":"2022","unstructured":"Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah Goodman. 2022. Star: Bootstrapping reasoning with reasoning. Advances in Neural Information Processing Systems 35 (2022), 15476--15488.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_51_1","volume-title":"William Yang Wang, and Linda Ruth Petzold","author":"Zhang Xinlu","year":"2023","unstructured":"Xinlu Zhang, Yujie Lu, Weizhi Wang, An Yan, Jun Yan, Lianke Qin, Heng Wang, Xifeng Yan, William Yang Wang, and Linda Ruth Petzold. 2023. Gpt-4v (ision) as a generalist evaluator for vision-language tasks. arXiv preprint arXiv:2311.01361 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"A Task isWorth OneWord: Learning with Task Prompts for High-Quality Versatile Image Inpainting. arXiv preprint arXiv:2312.03594","author":"Zhuang Junhao","year":"2023","unstructured":"Junhao Zhuang, Yanhong Zeng, Wenran Liu, Chun Yuan, and Kai Chen. 2023. A Task isWorth OneWord: Learning with Task Prompts for High-Quality Versatile Image Inpainting. arXiv preprint arXiv:2312.03594 (2023)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680753","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680753","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\/3664647.3680753"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3664647.3680753","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680753","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"}}]}}