{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:23Z","timestamp":1755825023730,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","funder":[{"name":"Ministry of Education of Humanities and Social Science Project","award":["23YJAZH220, 24YJAZH244"],"award-info":[{"award-number":["23YJAZH220, 24YJAZH244"]}]},{"DOI":"10.13039\/501100006374","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["24BXW047"],"award-info":[{"award-number":["24BXW047"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376062"],"award-info":[{"award-number":["62376062"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Philosophy and Social Sciences 14th Five-Year Plan Project of Guangdong Province","award":["GD23CTS03"],"award-info":[{"award-number":["GD23CTS03"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733314","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:39Z","timestamp":1750876299000},"page":"1432-1441","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DomainDiff: Unified Two-Stage Optimization for Text-Video Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2031-7635","authenticated-orcid":false,"given":"Chenxu","family":"Wang","sequence":"first","affiliation":[{"name":"Guangdong University of Foreign Studies, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3310-8347","authenticated-orcid":false,"given":"Dong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Guangdong University of Foreign Studies, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5935-2110","authenticated-orcid":false,"given":"Jianghao","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangdong University of Foreign Studies, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2661-3078","authenticated-orcid":false,"given":"Yongmei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Guangdong University of Foreign Studies, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1751-4801","authenticated-orcid":false,"given":"Aimin","family":"Yang","sequence":"additional","affiliation":[{"name":"Lingnan Normal University, Zhanjiang, China"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"Akbari Hassan","year":"2021","unstructured":"Hassan Akbari, Liangzhe Yuan, Rui Qian, Wei-Hong Chuang, Shih-Fu Chang, Yin Cui, and Boqing Gong. 2021. Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text. Advances in Neural Information Processing Systems, Vol. 34 (2021), 24206--24221.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Machine Learning. PMLR, 290--306","author":"Alaa Ahmed","year":"2022","unstructured":"Ahmed Alaa, Boris Van Breugel, Evgeny S Saveliev, and Mihaela Van Der Schaar. 2022. How faithful is your synthetic data? sample-level metrics for evaluating and auditing generative models. In International Conference on Machine Learning. PMLR, 290--306."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_1_5_1","volume-title":"Generative or discriminative? getting the best of both worlds. Bayesian statistics","author":"Bernardo JM","year":"2007","unstructured":"JM Bernardo, MJ Bayarri, JO Berger, AP Dawid, D Heckerman, AFM Smith, and M West. 2007. Generative or discriminative? getting the best of both worlds. Bayesian statistics, Vol. 8, 3 (2007), 3--24."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.29955"},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Chen Sihan","year":"2024","unstructured":"Sihan Chen, Handong Li, Qunbo Wang, Zijia Zhao, Mingzhen Sun, Xinxin Zhu, and Jing Liu. 2024. Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"e_1_3_2_1_10_1","volume-title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss. CoRR","author":"Cheng Xing","year":"2021","unstructured":"Xing Cheng, Hezheng Lin, Xiangyu Wu, Fan Yang, and Dong Shen. 2021. Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss. CoRR, Vol. abs\/2109.04290 (2021). showeprint[arXiv]2109.04290"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01776"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_2_1_13_1","volume-title":"Gramian Multimodal Representation Learning and Alignment. arXiv preprint arXiv:2412.11959","author":"Cicchetti Giordano","year":"2024","unstructured":"Giordano Cicchetti, Eleonora Grassucci, Luigi Sigillo, and Danilo Comminiello. 2024. Gramian Multimodal Representation Learning and Alignment. arXiv preprint arXiv:2412.11959 (2024)."},{"key":"e_1_3_2_1_14_1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"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, Vol. 34 (2021), 8780--8794.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_1_17_1","volume-title":"the 14th international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 315--323","author":"Glorot Xavier","year":"2011","unstructured":"Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Deep sparse rectifier neural networks. In the 14th international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 315--323."},{"key":"e_1_3_2_1_18_1","volume-title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5006--5015","author":"Gorti Satya Krishna","year":"2022","unstructured":"Satya Krishna Gorti, No\u00ebl Vouitsis, Junwei Ma, Keyvan Golestan, Maksims Volkovs, Animesh Garg, and Guangwei Yu. 2022. X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5006--5015."},{"key":"e_1_3_2_1_19_1","volume-title":"European Conference on Computer Vision. Springer, 124--140","author":"Han Dongchen","year":"2024","unstructured":"Dongchen Han, Tianzhu Ye, Yizeng Han, Zhuofan Xia, Siyuan Pan, Pengfei Wan, Shiji Song, and Gao Huang. 2024b. Agent attention: On the integration of softmax and linear attention. In European Conference on Computer Vision. Springer, 124--140."},{"key":"e_1_3_2_1_20_1","volume-title":"Dynamic neural networks: A survey","author":"Han Yizeng","year":"2021","unstructured":"Yizeng Han, Gao Huang, Shiji Song, Le Yang, Honghui Wang, and Yulin Wang. 2021. Dynamic neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 11 (2021), 7436--7456."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393530"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_23_1","volume-title":"Denoising Diffusion Probabilistic Models. In Annual Conference on Neural Information Processing Systems(2020)","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Annual Conference on Neural Information Processing Systems(2020)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01107"},{"key":"e_1_3_2_1_25_1","first-page":"30291","article-title":"Expectation-maximization contrastive learning for compact video-and-language representations","volume":"35","author":"Jin Peng","year":"2022","unstructured":"Peng Jin, Jinfa Huang, Fenglin Liu, Xian Wu, Shen Ge, Guoli Song, David Clifton, and Jie Chen. 2022. Expectation-maximization contrastive learning for compact video-and-language representations. Advances in Neural Information Processing Systems, Vol. 35 (2022), 30291--30306.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"e_1_3_2_1_27_1","volume-title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment. In International Joint Conference on Artificial Intelligence. ijcai.org, 938--946","author":"Jin Peng","year":"2023","unstructured":"Peng Jin, Hao Li, Zesen Cheng, Jinfa Huang, Zhennan Wang, Li Yuan, Chang Liu, and Jie Chen. 2023b. Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment. In International Joint Conference on Artificial Intelligence. ijcai.org, 938--946."},{"key":"e_1_3_2_1_28_1","volume-title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model. In IEEE\/CVF International Conference on Computer Vision (ICCV). 2470--2481","author":"Jin Peng","year":"2023","unstructured":"Peng Jin, Hao Li, Zesen Cheng, Kehan Li, Xiangyang Ji, Chang Liu, Li Yuan, and Jie Chen. 2023c. DiffusionRet: Generative Text-Video Retrieval with Diffusion Model. In IEEE\/CVF International Conference on Computer Vision (ICCV). 2470--2481."},{"volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations.","author":"Diederik","key":"e_1_3_2_1_29_1","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations."},{"volume-title":"Auto-Encoding Variational Bayes. In International Conference on Learning Representations.","author":"Diederik","key":"e_1_3_2_1_30_1","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"e_1_3_2_1_33_1","first-page":"65948","article-title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","volume":"36","author":"Li Pandeng","year":"2023","unstructured":"Pandeng Li, Chen-Wei Xie, Hongtao Xie, Liming Zhao, Lei Zhang, Yun Zheng, Deli Zhao, and Yongdong Zhang. 2023b. MomentDiff: Generative Video Moment Retrieval from Random to Real. In Advances in Neural Information Processing Systems, Vol. 36. 65948--65966.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_11"},{"key":"e_1_3_2_1_35_1","volume-title":"Denoising Autoregressive Representation Learning. In International Conference on Machine Learning.","author":"Li Yazhe","year":"2024","unstructured":"Yazhe Li, Jorg Bornschein, and Ting Chen. 2024. Denoising Autoregressive Representation Learning. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_36_1","first-page":"31360","article-title":"Gmmseg: Gaussian mixture based generative semantic segmentation models","volume":"35","author":"Liang Chen","year":"2022","unstructured":"Chen Liang, Wenguan Wang, Jiaxu Miao, and Yi Yang. 2022. Gmmseg: Gaussian mixture based generative semantic segmentation models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 31360--31375.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","first-page":"38655","article-title":"Text-adaptive multiple visual prototype matching for video-text retrieval","volume":"35","author":"Lin Chengzhi","year":"2022","unstructured":"Chengzhi Lin, Ancong Wu, Junwei Liang, Jun Zhang, Wenhang Ge, Wei-Shi Zheng, and Chunhua Shen. 2022b. Text-adaptive multiple visual prototype matching for video-text retrieval. Advances in Neural Information Processing Systems, Vol. 35 (2022), 38655--38666.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_24"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3479776"},{"key":"e_1_3_2_1_40_1","volume-title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts. CoRR","author":"Liu Yang","year":"2019","unstructured":"Yang Liu, Samuel Albanie, Arsha Nagrani, and Andrew Zisserman. 2019. Use What You Have: Video Retrieval Using Representations From Collaborative Experts. CoRR, Vol. abs\/1907.13487 (2019). showeprint[arXiv]1907.13487"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"e_1_3_2_1_42_1","volume-title":"Sgdr: Stochastic Gradient Descent with Warm Restarts. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Sgdr: Stochastic Gradient Descent with Warm Restarts. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_43_1","volume-title":"Generative Video Diffusion for Unseen Cross-Domain Video Moment Retrieval. CoRR","author":"Luo Dezhao","year":"2024","unstructured":"Dezhao Luo, Shaogang Gong, Jiabo Huang, Hailin Jin, and Yang Liu. 2024. Generative Video Diffusion for Unseen Cross-Domain Video Moment Retrieval. CoRR, Vol. abs\/2401.13329 (2024). showeprint[arXiv]2401.13329"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_46_1","volume-title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data. CoRR","author":"Miech Antoine","year":"2018","unstructured":"Antoine Miech, Ivan Laptev, and Josef Sivic. 2018. Learning a Text-Video Embedding from Incomplete and Heterogeneous Data. CoRR, Vol. abs\/1804.02516 (2018). showeprint[arXiv]1804.02516"},{"key":"e_1_3_2_1_47_1","volume-title":"International conference on machine learning. 7176--7185","author":"Naeem Muhammad Ferjad","year":"2020","unstructured":"Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, and Jaejun Yoo. 2020. Reliable fidelity and diversity metrics for generative models. In International conference on machine learning. 7176--7185."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"e_1_3_2_1_49_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning","volume":"139","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning, Vol. 139. 8748--8763."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"e_1_3_2_1_51_1","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al. 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in Neural Information Processing Systems, Vol. 34 (2021), 24261--24272.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_52_1","volume-title":"Advances in Neural Information Processing Systems","volume":"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, Vol. 30 (2017)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"e_1_3_2_1_54_1","volume-title":"High-Quality Multilingual Dataset for Video-and-Language Research. In IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Wang Xin","year":"2019","unstructured":"Xin Wang, Jiawei Wu, Junkun Chen, Lei Li, Yuan-Fang Wang, and William Yang Wang. 2019. VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research. In IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547968"},{"key":"e_1_3_2_1_57_1","volume-title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval. In IEEE\/CVF International Conference on Computer Vision (ICCV). 2816--2827","author":"Wang Ziyang","year":"2023","unstructured":"Ziyang Wang, Yi-Lin Sung, Feng Cheng, Gedas Bertasius, and Mohit Bansal. 2023. Unified Coarse-to-Fine Alignment for Video-Text Retrieval. In IEEE\/CVF International Conference on Computer Vision (ICCV). 2816--2827."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_60_1","volume-title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment. CoRR","author":"Xue Hongwei","year":"2022","unstructured":"Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, and Jiebo Luo. 2022. CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment. CoRR, Vol. abs\/2209.06430 (2022). showeprint[arXiv]2209.06430"},{"key":"e_1_3_2_1_61_1","volume-title":"Rui Yan, and Zechao Li.","author":"Zhao Henghao","year":"2024","unstructured":"Henghao Zhao, Kevin Qinghong Lin, Rui Yan, and Zechao Li. 2024. DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection. arxiv: 2308.15109"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:14:25Z","timestamp":1755749665000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":63,"alternative-id":["10.1145\/3731715.3733314","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733314","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}