{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:02:17Z","timestamp":1779235337972,"version":"3.51.4"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11432-024-4696-2","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T00:33:50Z","timestamp":1769474030000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["UML: uncertainty-aware and mutual learning for noise-robust cross-lingual cross-modal retrieval"],"prefix":"10.1007","volume":"69","author":[{"given":"Yu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haipeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingda","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"4696_CR1","first-page":"1","volume-title":"Proceedings of International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"X Yang","year":"2021","unstructured":"Yang X, Feng F, Ji W, et al. Deconfounded video moment retrieval with causal intervention. In: Proceedings of International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021. 1\u201310"},{"key":"4696_CR2","first-page":"4065","volume":"44","author":"J Dong","year":"2021","unstructured":"Dong J, Li X, Xu C, et al. Dual encoding for video retrieval by text. IEEE Trans Pattern Anal Mach Intell, 2021, 44: 4065\u20134080","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4696_CR3","first-page":"1339","volume-title":"Proceedings of International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"X Yang","year":"2020","unstructured":"Yang X, Dong J, Cao Y, et al. Tree-augmented cross-modal encoding for complex-query video retrieval. In: Proceedings of International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020. 1339\u20131348"},{"key":"4696_CR4","first-page":"14052","volume-title":"Proceedings of AAAI Conference on Artificial Intelligence","author":"Y Liu","year":"2024","unstructured":"Liu Y, Qin G, Chen H, et al. Causality-inspired invariant representation learning for text-based person retrieval. In: Proceedings of AAAI Conference on Artificial Intelligence, 2024. 14052\u201314060"},{"key":"4696_CR5","unstructured":"Zeng Y, Zhou W, Luo A, et al. Cross-view language modeling: towards unified cross-lingual cross-modal pre-training. 2022. ArXiv:2206.00621"},{"key":"4696_CR6","first-page":"4155","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"M Zhou","year":"2021","unstructured":"Zhou M, Zhou L, Wang S, et al. Uc2: universal cross-lingual cross-modal vision-and-language pre-training. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2021. 4155\u20134165"},{"key":"4696_CR7","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/3503161.3548003","volume-title":"Proceedings of ACM International Conference on Multimedia","author":"Y Wang","year":"2022","unstructured":"Wang Y, Dong J, Liang T, et al. Cross-lingual cross-modal retrieval with noise-robust learning. In: Proceedings of ACM International Conference on Multimedia, 2022. 422\u2013433"},{"key":"4696_CR8","first-page":"5651","volume-title":"Proceedings of AAAI Conference on Artificial Intelligence","author":"Y Wang","year":"2024","unstructured":"Wang Y, Wang F, Dong J, et al. Cl2cm: improving cross-lingual cross-modal retrieval via cross-lingual knowledge transfer. In: Proceedings of AAAI Conference on Artificial Intelligence, 2024. 5651\u20135659"},{"key":"4696_CR9","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.1109\/TIP.2024.3365248","volume":"33","author":"Y Wang","year":"2024","unstructured":"Wang Y, Wang S, Luo H, et al. Dual-view curricular optimal transport for cross-lingual cross-modal retrieval. IEEE Trans Image Process, 2024, 33: 1522\u20131533","journal-title":"IEEE Trans Image Process"},{"key":"4696_CR10","first-page":"2556","volume-title":"Proceedings of Annual Meeting of the Association for Computational Linguistics","author":"P Sharma","year":"2018","unstructured":"Sharma P, Ding N, Goodman S, et al. Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, 2018. 2556\u20132565"},{"key":"4696_CR11","first-page":"29406","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"Z Huang","year":"2021","unstructured":"Huang Z, Niu G, Liu X, et al. Learning with noisy correspondence for cross-modal matching. In: Proceedings of Conference on Neural Information Processing Systems, 2021. 29406\u201329419"},{"key":"4696_CR12","first-page":"4109","volume-title":"Proceedings of ACM International Conference on Multimedia","author":"X Shen","year":"2023","unstructured":"Shen X, Zhang X, Yang X, et al. Semantics-enriched cross-modal alignment for complex-query video moment retrieval. In: Proceedings of ACM International Conference on Multimedia, 2023. 4109\u20134118"},{"key":"4696_CR13","doi-asserted-by":"publisher","first-page":"4823","DOI":"10.1007\/s11263-024-02106-7","volume":"132","author":"X Yang","year":"2024","unstructured":"Yang X, Chang T, Zhang T, et al. Learning hierarchical visual transformation for domain generalizable visual matching and recognition. Int J Comput Vis, 2024, 132: 4823\u20134849","journal-title":"Int J Comput Vis"},{"key":"4696_CR14","first-page":"3977","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"M Ni","year":"2021","unstructured":"Ni M, Huang H, Su L, et al. M3p: learning universal representations via multitask multilingual multimodal pre-training. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2021. 3977\u20133986"},{"key":"4696_CR15","doi-asserted-by":"publisher","first-page":"2272","DOI":"10.1145\/3637528.3671787","volume-title":"Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Z Nie","year":"2024","unstructured":"Nie Z, Zhang R, Feng Z, et al. Improving the consistency in cross-lingual cross-modal retrieval with 1-to-K contrastive learning. In: Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024. 2272\u20132283"},{"key":"4696_CR16","doi-asserted-by":"crossref","unstructured":"Huang P Y, Patrick M, Hu J, et al. Multilingual multimodal pre-training for zero-shot cross-lingual transfer of vision-language models. 2021. ArXiv:2103.08849","DOI":"10.18653\/v1\/2021.naacl-main.195"},{"key":"4696_CR17","first-page":"2630","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"A Miech","year":"2019","unstructured":"Miech A, Zhukov D, Alayrac J B, et al. Howto100m: learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2019. 2630\u20132640"},{"key":"4696_CR18","first-page":"310","volume":"21","author":"Y Liu","year":"2024","unstructured":"Liu Y, Chen H, Qin G, et al. Bias mitigation and representation optimization for noise-robust cross-modal retrieval. ACM Trans Multimed Comput Commun Appl, 2024, 21: 310","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"4696_CR19","first-page":"27197","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"Y Qin","year":"2024","unstructured":"Qin Y, Chen Y, Peng D, et al. Noisy-correspondence learning for text-to-image person re-identification. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2024. 27197\u201327206"},{"key":"4696_CR20","doi-asserted-by":"publisher","first-page":"9150","DOI":"10.1109\/TKDE.2024.3423307","volume":"36","author":"Y Sun","year":"2024","unstructured":"Sun Y, Qin Y, Li Y, et al. Robust multi-view clustering with noisy correspondence. IEEE Trans Knowl Data Eng, 2024, 36: 9150\u20139162","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"4696_CR21","first-page":"14193","volume-title":"Proceedings of AAAI Conference on Artificial Intelligence","author":"Y Lu","year":"2024","unstructured":"Lu Y, Lin Y, Yang M, et al. Decoupled contrastive multi-view clustering with high-order random walks. In: Proceedings of AAAI Conference on Artificial Intelligence, 2024. 14193\u201314201"},{"key":"4696_CR22","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"A Kendall","year":"2017","unstructured":"Kendall A, Gal Y. What uncertainties do we need in Bayesian deep learning for computer vision? In: Proceedings of Conference on Neural Information Processing Systems, 2017"},{"key":"4696_CR23","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"A Malinin","year":"2018","unstructured":"Malinin A, Gales M. Predictive uncertainty estimation via prior networks. In: Proceedings of Conference on Neural Information Processing Systems, 2018"},{"key":"4696_CR24","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"M Sensoy","year":"2018","unstructured":"Sensoy M, Kaplan L, Kandemir M. Evidential deep learning to quantify classification uncertainty. In: Proceedings of Conference on Neural Information Processing Systems, 2018"},{"key":"4696_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-44792-4_1","volume-title":"Classic Works of the Dempster-Shafer Theory of Belief Functions: An Introduction","author":"L Liu","year":"2008","unstructured":"Liu L, Yager R R. Classic Works of the Dempster-Shafer Theory of Belief Functions: An Introduction. Berlin: Springer, 2008. 1\u201334"},{"key":"4696_CR26","volume-title":"Subjective Logic: A Formalism for Reasoning Under Uncertainty","author":"A Jsang","year":"2018","unstructured":"Jsang A. Subjective Logic: A Formalism for Reasoning Under Uncertainty. Berlin: Springer, 2018"},{"key":"4696_CR27","first-page":"13349","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"W Bao","year":"2021","unstructured":"Bao W, Yu Q, Kong Y. Evidential deep learning for open set action recognition. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2021. 13349\u201313358"},{"key":"4696_CR28","doi-asserted-by":"publisher","first-page":"4948","DOI":"10.1145\/3503161.3547922","volume-title":"Proceedings of ACM International Conference on Multimedia","author":"Y Qin","year":"2022","unstructured":"Qin Y, Peng D, Peng X, et al. Deep evidential learning with noisy correspondence for cross-modal retrieval. In: Proceedings of ACM International Conference on Multimedia, 2022. 4948\u20134956"},{"key":"4696_CR29","first-page":"6292","volume-title":"Proceedings of ACM International Conference on Multimedia","author":"S Li","year":"2023","unstructured":"Li S, Xu X, Yang Y, et al. Dcel: deep cross-modal evidential learning for text-based person retrieval. In: Proceedings of ACM International Conference on Multimedia, 2023. 6292\u20136300"},{"key":"4696_CR30","doi-asserted-by":"publisher","first-page":"2551","DOI":"10.1109\/TPAMI.2022.3171983","volume":"45","author":"Z Han","year":"2023","unstructured":"Han Z, Zhang C, Fu H, et al. Trusted multi-view classification with dynamic evidential fusion. IEEE Trans Pattern Anal Mach Intell, 2023, 45: 2551\u20132566","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4696_CR31","first-page":"3172","volume-title":"Proceedings of AAAI Conference on Artificial Intelligence","author":"S Li","year":"2024","unstructured":"Li S, He C, Xu X, et al. Adaptive uncertainty-based learning for text-based person retrieval. In: Proceedings of AAAI Conference on Artificial Intelligence, 2024. 3172\u20133180"},{"key":"4696_CR32","first-page":"7596","volume-title":"Proceedings of International Conference on Machine Learning","author":"D Deng","year":"2023","unstructured":"Deng D, Chen G, Yu Y, et al. Uncertainty estimation by Fisher information-based evidential deep learning. In: Proceedings of International Conference on Machine Learning, 2023. 7596\u20137616"},{"key":"4696_CR33","first-page":"1522","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"X Tian","year":"2021","unstructured":"Tian X, Zhang Z, Lin S, et al. Farewell to mutual information: variational distillation for cross-modal person re-identification. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2021. 1522\u20131531"},{"key":"4696_CR34","doi-asserted-by":"crossref","unstructured":"Yang Y, Chen H, Liu Z, et al. Action recognition with multi-stream motion modeling and mutual information maximization. 2023. ArXiv:2306.07576","DOI":"10.24963\/ijcai.2023\/184"},{"key":"4696_CR35","unstructured":"Wu S, Chen H, Yin Y, et al. Joint-motion mutual learning for pose estimation in videos. 2024. ArXiv:2408.02285"},{"key":"4696_CR36","unstructured":"Hjelm R D, Fedorov A, Lavoie-Marchildon S, et al. Learning deep representations by mutual information estimation and maximization. 2018. ArXiv:1808.06670"},{"key":"4696_CR37","unstructured":"Federici M, Dutta A, Forr\u00e9 P, et al. Learning robust representations via multi-view information bottleneck. 2020. ArXiv:2002.07017"},{"key":"4696_CR38","first-page":"12793","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"L Zhao","year":"2021","unstructured":"Zhao L, Wang Y, Zhao J, et al. Learning view-disentangled human pose representation by contrastive cross-view mutual information maximization. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2021. 12793\u201312802"},{"key":"4696_CR39","doi-asserted-by":"crossref","unstructured":"Elliott D, Frank S, Sima\u2019an K, et al. Multi30k: multilingual English-German image descriptions. 2016. ArXiv:1605.00459","DOI":"10.18653\/v1\/W16-3210"},{"key":"4696_CR40","first-page":"4581","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"X Wang","year":"2019","unstructured":"Wang X, Wu J, Chen J, et al. Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2019. 4581\u20134591"},{"key":"4696_CR41","unstructured":"Chen X, Fang H, Lin T Y, et al. Microsoft coco captions: data collection and evaluation server. 2015. ArXiv:1504.00325"},{"key":"4696_CR42","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young P, Lai A, Hodosh M, et al. From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist, 2014, 2: 67\u201378","journal-title":"Trans Assoc Comput Linguist"},{"key":"4696_CR43","first-page":"10638","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"S Chen","year":"2020","unstructured":"Chen S, Zhao Y, Jin Q, et al. Fine-grained video-text retrieval with hierarchical graph reasoning. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2020. 10638\u201310647"},{"key":"4696_CR44","first-page":"8748","volume-title":"Proceedings of Conference on Machine Learning","author":"A Radford","year":"2021","unstructured":"Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision. In: Proceedings of Conference on Machine Learning, 2021. 8748\u20138763"},{"key":"4696_CR45","first-page":"6299","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"J Carreira","year":"2017","unstructured":"Carreira J, Zisserman A. Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of Conference on Computer Vision and Pattern Recognition, 2017. 6299\u20136308"},{"key":"4696_CR46","unstructured":"Devlin J. Bert: pre-training of deep bidirectional transformers for language understanding. 2018. ArXiv:1810.04805"},{"key":"4696_CR47","doi-asserted-by":"crossref","unstructured":"Jain A, Guo M, Srinivasan K, et al. Mural: multimodal, multitask retrieval across languages. 2021. ArXiv:2109.05125","DOI":"10.18653\/v1\/2021.findings-emnlp.293"},{"key":"4696_CR48","unstructured":"Zhang L, Hu A, Jin Q. Generalizing multimodal pre-training into multilingual via language acquisition. 2022. ArXiv:2206.11091"},{"key":"4696_CR49","first-page":"2556","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","author":"P Sharma","year":"2018","unstructured":"Sharma P, Ding N, Goodman S, et al. Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018. 2556\u20132565"},{"key":"4696_CR50","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1109\/TIP.2022.3140611","volume":"31","author":"X Yang","year":"2022","unstructured":"Yang X, Wang S, Dong J, et al. Video moment retrieval with cross-modal neural architecture search. IEEE Trans Image Process, 2022, 31: 1204\u20131216","journal-title":"IEEE Trans Image Process"},{"key":"4696_CR51","first-page":"6171","volume-title":"Proceedings of ACM International Conference on Multimedia","author":"T Chang","year":"2023","unstructured":"Chang T, Yang X, Luo X, et al. Learning style-invariant robust representation for generalizable visual instance retrieval. In: Proceedings of ACM International Conference on Multimedia, 2023. 6171\u20136180"},{"key":"4696_CR52","doi-asserted-by":"publisher","first-page":"10924","DOI":"10.1109\/TMM.2024.3416669","volume":"26","author":"N Han","year":"2024","unstructured":"Han N, Yang X, Lim E P, et al. Efficient cross-modal video retrieval with meta-optimized frames. IEEE Trans Multimedia, 2024, 26: 10924\u201310936","journal-title":"IEEE Trans Multimedia"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4696-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4696-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4696-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T02:02:35Z","timestamp":1769479355000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4696-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["4696"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4696-2","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]},"assertion":[{"value":"31 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"132107"}}