{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:48:28Z","timestamp":1777657708521,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":58,"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"}],"funder":[{"name":"Advanced Research and Technology Innovation Centre (ARTIC), the National University of Singapore","award":["A-8000969-00-00"],"award-info":[{"award-number":["A-8000969-00-00"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681632","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"9271-9280","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Hierarchical Debiasing and Noisy Correction for Cross-domain Video Tube Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7613-7628","authenticated-orcid":false,"given":"Jingqiao","family":"Xiu","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3482-234X","authenticated-orcid":false,"given":"Mengze","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-9768","authenticated-orcid":false,"given":"Wei","family":"Ji","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0415-6937","authenticated-orcid":false,"given":"Jingyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-4534","authenticated-orcid":false,"given":"Hanbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6995-6447","authenticated-orcid":false,"given":"Shin'ichi","family":"Satoh","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7410-2590","authenticated-orcid":false,"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"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":"Distance spectra of graphs: A survey. Linear algebra and its applications","author":"Aouchiche Mustapha","year":"2014","unstructured":"Mustapha Aouchiche and Pierre Hansen. 2014. Distance spectra of graphs: A survey. Linear algebra and its applications, Vol. 458 (2014), 301--386."},{"key":"e_1_3_2_1_2_1","unstructured":"BirdFly16. 2023. I2OVOG--R2MVOG. https:\/\/github.com\/BirdFly16\/I2OVOG--R2MVOG. https:\/\/github.com\/BirdFly16\/I2OVOG--R2MVOG."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01172"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00889"},{"key":"e_1_3_2_1_5_1","unstructured":"Meilin Chen Weijie Chen Shicai Yang Jie Song Xinchao Wang Lei Zhang Yunfeng Yan Donglian Qi Yueting Zhuang Di Xie et al. 2022. Learning domain adaptive object detection with probabilistic teacher. arXiv preprint arXiv:2206.06293 (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00642"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"e_1_3_2_1_8_1","volume-title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatially Relation Matching. arXiv preprint arXiv:2311.12751","author":"Chu Meng","year":"2023","unstructured":"Meng Chu, Zhedong Zheng, Wei Ji, and Tat-Seng Chua. 2023. Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatially Relation Matching. arXiv preprint arXiv:2311.12751 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00408"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02282"},{"key":"e_1_3_2_1_11_1","volume-title":"Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language. In Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Fang Xiang","year":"2024","unstructured":"Xiang Fang, Daizong Liu, Wanlong Fang, Pan Zhou, Zichuan Xu, Wenzheng Xu, Junyang Chen, and Renfu Li. 2024. Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 1735--1743."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222965"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00242"},{"key":"e_1_3_2_1_14_1","volume-title":"Hierarchical local-global transformer for temporal sentence grounding","author":"Fang Xiang","year":"2023","unstructured":"Xiang Fang, Daizong Liu, Pan Zhou, Zichuan Xu, and Ruixuan Li. 2023. Hierarchical local-global transformer for temporal sentence grounding. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"European Conference on Computer Vision. Springer.","author":"Fang Xiang","year":"2024","unstructured":"Xiang Fang, Zeyu Xiong, Wanlong Fang, Xiaoye Qu, Chen Chen, Jianfeng Dong, Keke Tang, Pan Zhou, Yu Cheng, and Daizong Liu. 2024. Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective. In European Conference on Computer Vision. Springer."},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 1180--1189","author":"Ganin Yaroslav","year":"2015","unstructured":"Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In International conference on machine learning. PMLR, 1180--1189."},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin Yaroslav","year":"2016","unstructured":"Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Franccois Laviolette, Mario March, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. Journal of machine learning research, Vol. 17, 59 (2016), 1--35.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00525"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612088"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02204"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447846"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651942"},{"key":"e_1_3_2_1_24_1","first-page":"29192","article-title":"Embracing consistency: A one-stage approach for spatio-temporal video grounding","volume":"35","author":"Jin Yang","year":"2022","unstructured":"Yang Jin, Zehuan Yuan, Yadong Mu, et al. 2022. Embracing consistency: A one-stage approach for spatio-temporal video grounding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 29192--29204.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991050"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28098"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02211"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.254"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.596"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548333"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612314"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.592"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00743"},{"key":"e_1_3_2_1_35_1","first-page":"8494","article-title":"Hake: a knowledge engine foundation for human activity understanding","volume":"45","author":"Li Yong-Lu","year":"2022","unstructured":"Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Yizhuo Li, Zuoyu Qiu, Liang Xu, Yue Xu, Hao-Shu Fang, and Cewu Lu. 2022. Hake: a knowledge engine foundation for human activity understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 7 (2022), 8494--8506.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02212"},{"key":"e_1_3_2_1_37_1","first-page":"22968","article-title":"Cycle self-training for domain adaptation","volume":"34","author":"Liu Hong","year":"2021","unstructured":"Hong Liu, Jianmin Wang, and Mingsheng Long. 2021. Cycle self-training for domain adaptation. Advances in Neural Information Processing Systems, Vol. 34 (2021), 22968--22981.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_39_1","first-page":"23386","article-title":"Contrast and mix: Temporal contrastive video domain adaptation with background mixing","volume":"34","author":"Sahoo Aadarsh","year":"2021","unstructured":"Aadarsh Sahoo, Rutav Shah, Rameswar Panda, Kate Saenko, and Abir Das. 2021. Contrast and mix: Temporal contrastive video domain adaptation with background mixing. Advances in Neural Information Processing Systems, Vol. 34 (2021), 23386--23400.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00712"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00156"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"e_1_3_2_1_43_1","volume-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems","author":"Tarvainen Antti","year":"2017","unstructured":"Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_44_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_45_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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_46_1","volume-title":"A tutorial on spectral clustering. Statistics and computing","author":"Luxburg Ulrike Von","year":"2007","unstructured":"Ulrike Von Luxburg. 2007. A tutorial on spectral clustering. Statistics and computing, Vol. 17 (2007), 395--416."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613822"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475317"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00194"},{"key":"e_1_3_2_1_50_1","volume-title":"Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519","author":"Wu Shengqiong","year":"2023","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2023. Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"e_1_3_2_1_52_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xiao Zhiqing","year":"2024","unstructured":"Zhiqing Xiao, Haobo Wang, Ying Jin, Lei Feng, Gang Chen, Fei Huang, and Junbo Zhao. 2024. SPA: A Graph Spectral Alignment Perspective for Domain Adaptation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_37"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01745"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"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\/3664647.3681632","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":58,"alternative-id":["10.1145\/3664647.3681632","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681632","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"}}]}}