{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T21:59:02Z","timestamp":1790978342842,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","funder":[{"name":"Science and Technology Program of Chengdu","award":["2024YF0501231SN"],"award-info":[{"award-number":["2024YF0501231SN"]}]},{"name":"Sichuan Provincial Science and Technology Achievements Transfer and Transformation Project","award":["2025ZHCG0012"],"award-info":[{"award-number":["2025ZHCG0012"]}]},{"name":"Central-guided Local Science and Technology Development Special Fund Project","award":["2024ZYD0265"],"award-info":[{"award-number":["2024ZYD0265"]}]},{"name":"Sichuan Natural Science Foundation","award":["2025ZNSFSC0478"],"award-info":[{"award-number":["2025ZNSFSC0478"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202506070076"],"award-info":[{"award-number":["202506070076"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754901","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"11249-11258","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Bimodal Debiasing for Text-to-Image Diffusion: Adaptive Guidance in Textual and Visual Spaces"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4320-2721","authenticated-orcid":false,"given":"Liu","family":"Yu","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China and The University of Auckland, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1525-7978","authenticated-orcid":false,"given":"Jiajun","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3088-7135","authenticated-orcid":false,"given":"Ping","family":"Kuang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7955-9418","authenticated-orcid":false,"given":"Rui","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8038-8150","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0597-9866","authenticated-orcid":false,"given":"Zhikun","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the European conference on computer vision (ECCV) workshops. 0-0.","author":"Alvi Mohsan","year":"2018","unstructured":"Mohsan Alvi, Andrew Zisserman, and Christoffer Nell\u00e5ker. 2018. Turning a blind eye: Explicit removal of biases and variation from deep neural network embeddings. In Proceedings of the European conference on computer vision (ECCV) workshops. 0-0."},{"key":"e_1_3_2_2_2_1","volume-title":"How well can text-to-image generative models understand ethical natural language interventions? arXiv preprint arXiv:2210.15230","author":"Bansal Hritik","year":"2022","unstructured":"Hritik Bansal, Da Yin, Masoud Monajatipoor, and Kai-Wei Chang. 2022. How well can text-to-image generative models understand ethical natural language interventions? arXiv preprint arXiv:2210.15230 (2022)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-main.61"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594095"},{"key":"e_1_3_2_2_5_1","volume-title":"Vinay Uday Prabhu, and Emmanuel Kahembwe","author":"Birhane Abeba","year":"2021","unstructured":"Abeba Birhane, Vinay Uday Prabhu, and Emmanuel Kahembwe. 2021. Multimodal datasets: misogyny, pornography, and malignant stereotypes. arXiv preprint arXiv:2110.01963 (2021)."},{"key":"e_1_3_2_2_6_1","volume-title":"Hal Daum\u00e9 III, and Hanna Wallach","author":"Blodgett Su Lin","year":"2020","unstructured":"Su Lin Blodgett, Solon Barocas, Hal Daum\u00e9 III, and Hanna Wallach. 2020. Language (technology) is power: A critical survey of'' bias'' in nlp. arXiv preprint arXiv:2005.14050 (2020)."},{"key":"e_1_3_2_2_7_1","volume-title":"Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems","author":"Bolukbasi Tolga","year":"2016","unstructured":"Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_2_8_1","first-page":"25365","article-title":"Sega: Instructing text-to-image models using semantic guidance","volume":"36","author":"Brack Manuel","year":"2023","unstructured":"Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, and Kristian Kersting. 2023. Sega: Instructing text-to-image models using semantic guidance. Advances in Neural Information Processing Systems, Vol. 36 (2023), 25365-25389.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681624"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709308"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"e_1_3_2_2_16_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Choi Kristy","year":"2020","unstructured":"Kristy Choi, Aditya Grover, Trisha Singh, Rui Shu, and Stefano Ermon. 2020. Fair generative modeling via weak supervision. In International Conference on Machine Learning. PMLR, 1887-1898."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30202"},{"key":"e_1_3_2_2_18_1","volume-title":"Debiasing vision-language models via biased prompts. arXiv preprint arXiv:2302.00070","author":"Chuang Ching-Yao","year":"2023","unstructured":"Ching-Yao Chuang, Varun Jampani, Yuanzhen Li, Antonio Torralba, and Stefanie Jegelka. 2023. Debiasing vision-language models via biased prompts. arXiv preprint arXiv:2302.00070 (2023)."},{"key":"e_1_3_2_2_19_1","volume-title":"FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs. arXiv preprint arXiv:2403.15593","author":"Dehdashtian Sepehr","year":"2024","unstructured":"Sepehr Dehdashtian, Lan Wang, and Vishnu Naresh Boddeti. 2024. FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs. arXiv preprint arXiv:2403.15593 (2024)."},{"key":"e_1_3_2_2_20_1","volume-title":"Fair diffusion: Instructing text-to-image generation models on fairness. arXiv preprint arXiv:2302.10893","author":"Friedrich Felix","year":"2023","unstructured":"Felix Friedrich, Manuel Brack, Lukas Struppek, Dominik Hintersdorf, Patrick Schramowski, Sasha Luccioni, and Kristian Kersting. 2023. Fair diffusion: Instructing text-to-image generation models on fairness. arXiv preprint arXiv:2302.10893 (2023)."},{"key":"e_1_3_2_2_21_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_2_22_1","volume-title":"Bias correction of learned generative models using likelihood-free importance weighting. Advances in neural information processing systems","author":"Grover Aditya","year":"2019","unstructured":"Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric J Horvitz, and Stefano Ermon. 2019. Bias correction of learned generative models using likelihood-free importance weighting. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_23_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_2_24_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_2_25_1","first-page":"78723","article-title":"T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","volume":"36","author":"Huang Kaiyi","year":"2023","unstructured":"Kaiyi Huang, Kaiyue Sun, Enze Xie, Zhenguo Li, and Xihui Liu. 2023. T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 78723-78747.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_26_1","volume-title":"International conference on machine learning. PMLR, 9226-9259","author":"Huang Yu","year":"2022","unstructured":"Yu Huang, Junyang Lin, Chang Zhou, Hongxia Yang, and Longbo Huang. 2022. Modality competition: What makes joint training of multi-modal network fail in deep learning?(provably). In International conference on machine learning. PMLR, 9226-9259."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680748"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00159"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_2_33_1","volume-title":"Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960","author":"Kwon Mingi","year":"2022","unstructured":"Mingi Kwon, Jaeseok Jeong, and Youngjung Uh. 2022. Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960 (2022)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01141"},{"key":"e_1_3_2_2_35_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. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.27000"},{"key":"e_1_3_2_2_37_1","volume-title":"GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations. arXiv preprint arXiv:2305.19962","author":"Melzi Pietro","year":"2023","unstructured":"Pietro Melzi, Christian Rathgeb, Ruben Tolosana, Ruben Vera-Rodriguez, Dominik Lawatsch, Florian Domin, and Maxim Schaubert. 2023. GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations. arXiv preprint arXiv:2305.19962 (2023)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_2_39_1","volume-title":"StereoSet: Measuring stereotypical bias in pretrained language models. arXiv preprint arXiv:2004.09456","author":"Nadeem Moin","year":"2020","unstructured":"Moin Nadeem, Anna Bethke, and Siva Reddy. 2020. StereoSet: Measuring stereotypical bias in pretrained language models. arXiv preprint arXiv:2004.09456 (2020)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00637"},{"key":"e_1_3_2_2_41_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_42_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. 2022a. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_2_43_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. 2022b. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_2_47_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","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."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00659"},{"key":"e_1_3_2_2_49_1","volume-title":"Finetuning Text-to-Image Diffusion Models for Fairness. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=hnrB5YHoYu","author":"Shen Xudong","year":"2024","unstructured":"Xudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, and Mohan Kankanhalli. 2024. Finetuning Text-to-Image Diffusion Models for Fairness. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=hnrB5YHoYu"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01140"},{"key":"e_1_3_2_2_52_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_2_53_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Teo Christopher","year":"2024","unstructured":"Christopher Teo, Milad Abdollahzadeh, and Ngai-Man Man Cheung. 2024. On measuring fairness in generative models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_54_1","volume-title":"Effective data augmentation with diffusion models. arXiv preprint arXiv:2302.07944","author":"Trabucco Brandon","year":"2023","unstructured":"Brandon Trabucco, Kyle Doherty, Max Gurinas, and Ruslan Salakhutdinov. 2023. Effective data augmentation with diffusion models. arXiv preprint arXiv:2302.07944 (2023)."},{"key":"e_1_3_2_2_55_1","volume-title":"Are gender-neutral queries really gender-neutral? mitigating gender bias in image search. arXiv preprint arXiv:2109.05433","author":"Wang Jialu","year":"2021","unstructured":"Jialu Wang, Yang Liu, and Xin Eric Wang. 2021. Are gender-neutral queries really gender-neutral? mitigating gender bias in image search. arXiv preprint arXiv:2109.05433 (2021)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00934"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00894"},{"key":"e_1_3_2_2_58_1","unstructured":"Laura Weidinger John Mellor Maribeth Rauh Conor Griffin Jonathan Uesato Po-Sen Huang Myra Cheng Mia Glaese Borja Balle Atoosa Kasirzadeh et al. 2021. Ethical and social risks of harm from language models. arXiv preprint arXiv:2112.04359 (2021)."},{"key":"e_1_3_2_2_59_1","first-page":"22422","article-title":"Generative visual prompt: Unifying distributional control of pre-trained generative models","volume":"35","author":"Wu Chen Henry","year":"2022","unstructured":"Chen Henry Wu, Saman Motamed, Shaunak Srivastava, and Fernando D De la Torre. 2022. Generative visual prompt: Unifying distributional control of pre-trained generative models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 22422-22437.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622525"},{"key":"e_1_3_2_2_61_1","volume-title":"International Conference on Machine Learning. PMLR, 38728-38748","author":"Xu Haiyang","year":"2023","unstructured":"Haiyang Xu, Qinghao Ye, Ming Yan, Yaya Shi, Jiabo Ye, Yuanhong Xu, Chenliang Li, Bin Bi, Qi Qian, Wei Wang, et al., 2023. mplug-2: A modularized multi-modal foundation model across text, image and video. In International Conference on Machine Learning. PMLR, 38728-38748."},{"key":"e_1_3_2_2_62_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_2_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30532"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889057"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591938"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00367"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00367"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_69_1","volume-title":"Gender bias in contextualized word embeddings. arXiv preprint arXiv:1904.03310","author":"Zhao Jieyu","year":"2019","unstructured":"Jieyu Zhao, Tianlu Wang, Mark Yatskar, Ryan Cotterell, Vicente Ordonez, and Kai-Wei Chang. 2019. Gender bias in contextualized word embeddings. arXiv preprint arXiv:1904.03310 (2019)."},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.232"},{"key":"e_1_3_2_2_71_1","volume-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment. arXiv preprint arXiv:2310.01852","author":"Zhu Bin","year":"2023","unstructured":"Bin Zhu, Bin Lin, Munan Ning, Yang Yan, Jiaxi Cui, HongFa Wang, Yatian Pang, Wenhao Jiang, Junwu Zhang, Zongwei Li, et al., 2023. Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment. arXiv preprint arXiv:2310.01852 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:38:45Z","timestamp":1765309125000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754901"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":71,"alternative-id":["10.1145\/3746027.3754901","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754901","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}