{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:29:36Z","timestamp":1764588576645,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"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\/3664647.3680594","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"4158-4166","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Attentive Linguistic Tracking in Diffusion Models for Training-free Text-guided Image Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5820-0704","authenticated-orcid":false,"given":"Bingyan","family":"Liu","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1010-9678","authenticated-orcid":false,"given":"Chengyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7706-7081","authenticated-orcid":false,"given":"Jun","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4748-5298","authenticated-orcid":false,"given":"Kui","family":"Jia","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1109\/CVPR52729.2023.01764"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, Mingxuan Wang and Imed Zitouni (Eds.). Association for Computational Linguistics","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 Textto-Image Synthesis. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, Mingxuan Wang and Imed Zitouni (Eds.). Association for Computational Linguistics, Singapore, 1--11. https:\/\/doi. org\/10.18653\/v1\/2023.emnlp-industry.1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1145\/3592116"},{"key":"e_1_3_2_1_5_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Couairon Guillaume","year":"2023","unstructured":"Guillaume Couairon, Jakob Verbeek, Holger Schwenk, and Matthieu Cord. 2023. DiffEdit: Diffusion-based semantic image editing with mask guidance. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_6_1","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems 35 (2022), 16344--16359.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_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)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_3_2_1_9_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_10_1","volume-title":"Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations.","author":"Hertz Amir","year":"2023","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-or. 2023. Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations."},{"unstructured":"Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings convolutional neural networks and incremental parsing. (2017). To appear.","key":"e_1_3_2_1_11_1"},{"key":"e_1_3_2_1_12_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_13_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ju Xuan","year":"2024","unstructured":"Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, and Qiang Xu. 2024. PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code. International Conference on Learning Representations (ICLR) (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.1109\/CVPR.2019.00453"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1109\/CVPR52729.2023.00582"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"e_1_3_2_1_17_1","volume-title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In International Conference on Learning Representations.","author":"Meng Chenlin","year":"2022","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, JiajunWu, Jun-Yan Zhu, and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_19_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)."},{"unstructured":"OpenAI. 2023. ChatGPT. https:\/\/openai.com\/chatgpt.","key":"e_1_3_2_1_20_1"},{"unstructured":"OpenAI. 2023. Improving Image Generation with Better Captions. https:\/\/cdn. openai.com\/papers\/dall-e-3.pdf.","key":"e_1_3_2_1_21_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1109\/WACV57701.2024.00415"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1145\/3588432.3591513"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_1_25_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_26_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_27_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Rassin Royi","year":"2023","unstructured":"Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, and Gal Chechik. 2023. Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment. In Thirty-seventh Conference on Neural Information Processing Systems."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_30_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_31_1","volume-title":"Denoising Diffusion Implicit Models. In International Conference on Learning Representations. https: \/\/openreview.net\/forum?id=St1giarCHLP","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In International Conference on Learning Representations. https: \/\/openreview.net\/forum?id=St1giarCHLP"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.18653\/v1\/2023.acl-long.310"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_1_34_1","volume-title":"Joost van de Weijer, et al.","author":"Yang Fei","year":"2024","unstructured":"Fei Yang, Shiqi Yang, Muhammad Atif Butt, Joost van de Weijer, et al. 2024. Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing. Advances in Neural Information Processing Systems 36 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1109\/ICCV51070.2023.00355"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '24","name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680594","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680594"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":35,"alternative-id":["10.1145\/3664647.3680594","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680594","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"}}]}}