{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:22:02Z","timestamp":1781587322325,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755468","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"6153-6162","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Hubness Reduction with Dual Bank Sinkhorn Normalization for Cross-Modal Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2003-0728","authenticated-orcid":false,"given":"Zhengxin","family":"Pan","sequence":"first","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1617-0920","authenticated-orcid":false,"given":"Haishuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9618-8965","authenticated-orcid":false,"given":"Fangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7973-2746","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1097-2044","authenticated-orcid":false,"given":"Jiajun","family":"Bu","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_2_1","volume-title":"Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach. In The Thirteenth International Conference on Learning Representations.","author":"Bai Zechen","year":"2025","unstructured":"Zechen Bai, Tianjun Xiao, Tong He, WANG Pichao, Zheng Zhang, Thomas Brox, and Mike Zheng Shou. 2025. Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on artificial intelligence and statistics. PMLR, 880--889","author":"Blondel Mathieu","year":"2018","unstructured":"Mathieu Blondel, Vivien Seguy, and Antoine Rolet. 2018. Smooth and sparse optimal transport. In International conference on artificial intelligence and statistics. PMLR, 880--889."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-024-02972-2"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02865"},{"key":"e_1_3_2_1_8_1","volume-title":"Improved probabilistic image-text representations. arXiv preprint arXiv:2305.18171","author":"Chun Sanghyuk","year":"2023","unstructured":"Sanghyuk Chun. 2023. Improved probabilistic image-text representations. arXiv preprint arXiv:2305.18171 (2023)."},{"key":"e_1_3_2_1_9_1","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: lightspeed computation of optimal transport. In Advances in Neural Information Processing Systems. 2292--2300."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_11_1","volume-title":"Improving zeroshot learning by mitigating the hubness problem. arXiv preprint arXiv:1412.6568","author":"Dinu Georgiana","year":"2014","unstructured":"Georgiana Dinu, Angeliki Lazaridou, and Marco Baroni. 2014. Improving zeroshot learning by mitigating the hubness problem. arXiv preprint arXiv:1412.6568 (2014)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"e_1_3_2_1_14_1","volume-title":"Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097","author":"Fang Han","year":"2021","unstructured":"Han Fang, Pengfei Xiong, Luhui Xu, and Yu Chen. 2021. Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00021"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-018-1205-y"},{"key":"e_1_3_2_1_17_1","volume-title":"Devise: A deep visual-semantic embedding model. In Advances in Neural Information Processing Systems. 4357--3469.","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. 2013. Devise: A deep visual-semantic embedding model. In Advances in Neural Information Processing Systems. 4357--3469."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02485"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32336"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10240"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Kang Dabin","year":"2025","unstructured":"Jeong-hun Hong, Dong-hun Lee, Dabin Kang, Semin Myeong, Sang-hyo Park, Hyeyoung Park, et al. 2025. Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Kim Chris Dongjoo","year":"2019","unstructured":"Chris Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. 2019. Audiocaps: Generating captions for audios in the wild. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 119--132."},{"key":"e_1_3_2_1_26_1","volume-title":"The Hungarian method for the assignment problem. Naval research logistics quarterly 2, 1--2","year":"1955","unstructured":"HaroldWKuhn. 1955. The Hungarian method for the assignment problem. Naval research logistics quarterly 2, 1--2 (1955), 83--97."},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on learning representations.","author":"Lample Guillaume","year":"2018","unstructured":"Guillaume Lample, Alexis Conneau, Marc'Aurelio Ranzato, Ludovic Denoyer, and Herv\u00e9 J\u00e9gou. 2018. Word translation without parallel data. In International conference on learning representations."},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_30_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems 34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems 34 (2021), 9694--9705."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00379"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_34_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems 36 (2023), 34892--34916."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_39_1","volume-title":"On metric learning for audio-text cross-modal retrieval. arXiv preprint arXiv:2203.15537","author":"Mei Xinhao","year":"2022","unstructured":"Xinhao Mei, Xubo Liu, Jianyuan Sun, Mark D Plumbley, and Wenwu Wang. 2022. On metric learning for audio-text cross-modal retrieval. arXiv preprint arXiv:2203.15537 (2022)."},{"key":"e_1_3_2_1_40_1","volume-title":"Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_1_41_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL]"},{"key":"e_1_3_2_1_42_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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. arXiv preprint arXiv:2103.00020 (2021)."},{"key":"e_1_3_2_1_43_1","volume-title":"Hubs in space: Popular nearest neighbors in high-dimensional data. Journal of Machine Learning Research 11, sept","author":"Radovanovic Milos","year":"2010","unstructured":"Milos Radovanovic, Alexandros Nanopoulos, Mirjana Ivanovic, Mark D, and Wang. 2010. Hubs in space: Popular nearest neighbors in high-dimensional data. Journal of Machine Learning Research 11, sept (2010), 2487--2531."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02574"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Anna Rohrbach Marcus Rohrbach Niket Tandon and Bernt Schiele. 2015. A dataset for movie description. 3202--3212.","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"e_1_3_2_1_46_1","article-title":"Local and global scaling reduce hubs in space","volume":"13","author":"Schnitzer Dominik","year":"2012","unstructured":"Dominik Schnitzer, Arthur Flexer, Markus Schedl, and Gerhard Widmer. 2012. Local and global scaling reduce hubs in space. Journal of Machine Learning Research 13, 10 (2012).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_47_1","volume-title":"Tempme: Video temporal token merging for efficient text-video retrieval. arXiv preprint arXiv:2409.01156","author":"Shen Leqi","year":"2024","unstructured":"Leqi Shen, Tianxiang Hao, Sicheng Zhao, Yifeng Zhang, Pengzhang Liu, Yongjun Bao, and Guiguang Ding. 2024. Tempme: Video temporal token merging for efficient text-video retrieval. arXiv preprint arXiv:2409.01156 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Steven Hamblin, and Nils Y Hammerla.","author":"Smith Samuel L","year":"2017","unstructured":"Samuel L Smith, David HP Turban, Steven Hamblin, and Nils Y Hammerla. 2017. Offline bilingual word vectors, orthogonal transformations and the inverted softmax. arXiv preprint arXiv:1702.03859 (2017)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00727"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"e_1_3_2_1_51_1","volume-title":"Disentangled representation learning for text-video retrieval. arXiv preprint arXiv:2203.07111","author":"Wang Qiang","year":"2022","unstructured":"Qiang Wang, Yanhao Zhang, Yun Zheng, Pan Pan, and Xian-Sheng Hua. 2022. Disentangled representation learning for text-video retrieval. arXiv preprint arXiv:2203.07111 (2022)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"e_1_3_2_1_53_1","volume-title":"Balance act: Mitigating hubness in cross-modal retrieval with query and gallery banks. arXiv preprint arXiv:2310.11612","author":"Wang Yimu","year":"2023","unstructured":"Yimu Wang, Xiangru Jian, and Bo Xue. 2023. Balance act: Mitigating hubness in cross-modal retrieval with query and gallery banks. arXiv preprint arXiv:2310.11612 (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Zuxuan Wu Ting Yao Yanwei Fu and Yu-Gang Jiang. 2017. Deep learning for video classification and captioning. In Frontiers of multimedia research. 3--29.","DOI":"10.1145\/3122865.3122867"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"e_1_3_2_1_60_1","volume-title":"Self-tuning spectral clustering. Advances in neural information processing systems 17","author":"Zelnik-Manor Lihi","year":"2004","unstructured":"Lihi Zelnik-Manor and Pietro Perona. 2004. Self-tuning spectral clustering. Advances in neural information processing systems 17 (2004)."}],"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\/3746027.3755468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:23:03Z","timestamp":1765308183000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755468"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":60,"alternative-id":["10.1145\/3746027.3755468","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755468","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"}}]}}