{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T11:57:23Z","timestamp":1774699043188,"version":"3.50.1"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276073"],"award-info":[{"award-number":["62276073"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1016\/j.engappai.2025.112383","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T04:25:50Z","timestamp":1758774350000},"page":"112383","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PA","title":["Clean-sample guided cross-modal retrieval with adaptive weighted contrastive learning"],"prefix":"10.1016","volume":"162","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5758-2703","authenticated-orcid":false,"given":"Shuni","family":"Jiang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5313-6134","authenticated-orcid":false,"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2025.112383_b1","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"233","article-title":"A closer look at memorization in deep networks","author":"Arpit","year":"2017"},{"key":"10.1016\/j.engappai.2025.112383_b2","series-title":"Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"3594","article-title":"Data fusion through cross-modality metric learning using similarity-sensitive hashing","author":"Bronstein","year":"2010"},{"key":"10.1016\/j.engappai.2025.112383_b3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3226371","article-title":"On the effects of different types of label noise in multi-label remote sensing image classification","volume":"60","author":"Burgert","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.engappai.2025.112383_b4","doi-asserted-by":"crossref","first-page":"9479","DOI":"10.1109\/TMM.2023.3253391","article-title":"Refining noisy labels with label reliability perception for person re-identification","volume":"25","author":"Chen","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2025.112383_b5","series-title":"Learning with instance-dependent label noise: A sample sieve approach","author":"Cheng","year":"2020"},{"key":"10.1016\/j.engappai.2025.112383_b6","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, J., Yu, G., Yan, Z., Domeniconi, C., Zhang, J., 2023. Long-tail cross modal hashing. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 37, pp. 7642\u20137650.","DOI":"10.1609\/aaai.v37i6.25927"},{"key":"10.1016\/j.engappai.2025.112383_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109891","article-title":"Multiple instance relation graph reasoning for cross-modal hash retrieval","volume":"256","author":"Hou","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.engappai.2025.112383_b8","doi-asserted-by":"crossref","unstructured":"Hu, P., Peng, X., Zhu, H., Zhen, L., Lin, J., 2021. Learning cross-modal retrieval with noisy labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5403\u20135413.","DOI":"10.1109\/CVPR46437.2021.00536"},{"issue":"3","key":"10.1016\/j.engappai.2025.112383_b9","first-page":"3877","article-title":"Unsupervised contrastive cross-modal hashing","volume":"45","author":"Hu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2025.112383_b10","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume":"34","author":"Huang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2025.112383_b11","doi-asserted-by":"crossref","unstructured":"Huiskes, M.J., Lew, M.S., 2008. The mir flickr retrieval evaluation. In: Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval. pp. 39\u201343.","DOI":"10.1145\/1460096.1460104"},{"key":"10.1016\/j.engappai.2025.112383_b12","doi-asserted-by":"crossref","unstructured":"Jiang, Q.-Y., Li, W.-J., 2017. Deep cross-modal hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3232\u20133240.","DOI":"10.1109\/CVPR.2017.348"},{"key":"10.1016\/j.engappai.2025.112383_b13","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"2304","article-title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels","author":"Jiang","year":"2018"},{"key":"10.1016\/j.engappai.2025.112383_b14","doi-asserted-by":"crossref","unstructured":"Karim, N., Rizve, M.N., Rahnavard, N., Mian, A., Shah, M., 2022. Unicon: Combating label noise through uniform selection and contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9676\u20139686.","DOI":"10.1109\/CVPR52688.2022.00945"},{"key":"10.1016\/j.engappai.2025.112383_b15","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2025.112383_b16","series-title":"An empirical evaluation of doc2vec with practical insights into document embedding generation","author":"Lau","year":"2016"},{"key":"10.1016\/j.engappai.2025.112383_b17","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, L., Huang, Y., Zhang, Z., Zhang, S., Xiao, J., 2022. The devil is in the labels: Noisy label correction for robust scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18869\u201318878.","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"10.1016\/j.engappai.2025.112383_b18","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/j.neunet.2023.12.018","article-title":"Large-scale cross-modal hashing with unified learning and multi-object regional correlation reasoning","volume":"171","author":"Li","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.engappai.2025.112383_b19","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1109\/TMM.2021.3137752","article-title":"Trustable co-label learning from multiple noisy annotators","volume":"25","author":"Li","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2025.112383_b20","series-title":"Dividemix: Learning with noisy labels as semi-supervised learning","author":"Li","year":"2020"},{"key":"10.1016\/j.engappai.2025.112383_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2023.102489","article-title":"RICH: A rapid method for image-text cross-modal hash retrieval","volume":"79","author":"Li","year":"2023","journal-title":"Displays"},{"key":"10.1016\/j.engappai.2025.112383_b22","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2025.112383_b23","series-title":"Proceedings of the 13th European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.engappai.2025.112383_b24","doi-asserted-by":"crossref","unstructured":"Liu, S., Qian, S., Guan, Y., Zhan, J., Ying, L., 2020. Joint-modal distribution-based similarity hashing for large-scale unsupervised deep cross-modal retrieval. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 1379\u20131388.","DOI":"10.1145\/3397271.3401086"},{"key":"10.1016\/j.engappai.2025.112383_b25","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"6543","article-title":"Normalized loss functions for deep learning with noisy labels","author":"Ma","year":"2020"},{"issue":"11","key":"10.1016\/j.engappai.2025.112383_b26","doi-asserted-by":"crossref","first-page":"6275","DOI":"10.1109\/TNNLS.2021.3073248","article-title":"Learning with noisy labels via self-reweighting from class centroids","volume":"33","author":"Ma","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"10.1016\/j.engappai.2025.112383_b27","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1016\/j.patcog.2005.10.028","article-title":"A study of Gaussian mixture models of color and texture features for image classification and segmentation","volume":"39","author":"Permuter","year":"2006","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.engappai.2025.112383_b28","series-title":"Proceedings of the Chinese Conference on Pattern Recognition and Computer Vision","first-page":"304","article-title":"Deep noisy multi-label learning for robust cross-modal retrieval","author":"Pu","year":"2024"},{"key":"10.1016\/j.engappai.2025.112383_b29","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","author":"Ren","year":"2018"},{"key":"10.1016\/j.engappai.2025.112383_b30","doi-asserted-by":"crossref","unstructured":"Shen, F., Shen, C., Liu, W., Tao Shen, H., 2015. Supervised discrete hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 37\u201345.","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"10.1016\/j.engappai.2025.112383_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109367","article-title":"Online hashing with partially known labels for cross-modal retrieval","volume":"138","author":"Shu","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2025.112383_b32","first-page":"1","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","volume":"32","author":"Shu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2025.112383_b33","doi-asserted-by":"crossref","unstructured":"Su, S., Zhong, Z., Zhang, C., 2019. Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3027\u20133035.","DOI":"10.1109\/ICCV.2019.00312"},{"key":"10.1016\/j.engappai.2025.112383_b34","doi-asserted-by":"crossref","unstructured":"Sun, C., Latapie, H., Liu, G., Yan, Y., 2022a. Deep normalized cross-modal hashing with bi-direction relation reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4941\u20134949.","DOI":"10.1109\/CVPRW56347.2022.00541"},{"key":"10.1016\/j.engappai.2025.112383_b35","doi-asserted-by":"crossref","unstructured":"Sun, Z., Shen, F., Huang, D., Wang, Q., Shu, X., Yao, Y., Tang, J., 2022b. Pnp: Robust learning from noisy labels by probabilistic noise prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5311\u20135320.","DOI":"10.1109\/CVPR52688.2022.00524"},{"issue":"2","key":"10.1016\/j.engappai.2025.112383_b36","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1109\/TKDE.2020.2987312","article-title":"Deep cross-modal hashing with hashing functions and unified hash codes jointly learning","volume":"34","author":"Tu","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.engappai.2025.112383_b37","doi-asserted-by":"crossref","unstructured":"Wang, F., Liu, H., 2021. Understanding the behaviour of contrastive loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2495\u20132504.","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"10.1016\/j.engappai.2025.112383_b38","doi-asserted-by":"crossref","unstructured":"Wang, L., Qin, Y., Sun, Y., Peng, D., Peng, X., Hu, P., 2024. Robust Contrastive Cross-modal Hashing with Noisy Labels. In: Proceedings of the 32nd ACM International Conference on Multimedia. pp. 5752\u20135760.","DOI":"10.1145\/3664647.3680564"},{"key":"10.1016\/j.engappai.2025.112383_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108944","article-title":"Deep cross-modal hashing with multi-task latent space learning","volume":"136","author":"Wu","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2025.112383_b40","doi-asserted-by":"crossref","first-page":"3626","DOI":"10.1109\/TIP.2020.2963957","article-title":"Multi-task consistency-preserving adversarial hashing for cross-modal retrieval","volume":"29","author":"Xie","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.engappai.2025.112383_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108969","article-title":"Unsupervised cross-modal hashing retrieval via dynamic contrast and optimization","volume":"136","author":"Xie","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2025.112383_b42","doi-asserted-by":"crossref","unstructured":"Xu, T., Liu, X., Huang, Z., Guo, D., Hong, R., Wang, M., 2022. Early-learning regularized contrastive learning for cross-modal retrieval with noisy labels. In: Proceedings of the 30th ACM International Conference on Multimedia. pp. 629\u2013637.","DOI":"10.1145\/3503161.3548066"},{"key":"10.1016\/j.engappai.2025.112383_b43","doi-asserted-by":"crossref","unstructured":"Yang, E., Deng, C., Liu, W., Liu, X., Tao, D., Gao, X., 2017. Pairwise relationship guided deep hashing for cross-modal retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 31, pp. 1\u20138.","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"10.1016\/j.engappai.2025.112383_b44","doi-asserted-by":"crossref","unstructured":"Yang, E., Yao, D., Liu, T., Deng, C., 2022. Mutual quantization for cross-modal search with noisy labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7551\u20137560.","DOI":"10.1109\/CVPR52688.2022.00740"},{"key":"10.1016\/j.engappai.2025.112383_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121516","article-title":"Similarity graph-correlation reconstruction network for unsupervised cross-modal hashing","volume":"237","author":"Yao","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2025.112383_b46","doi-asserted-by":"crossref","unstructured":"Yu, J., Zhou, H., Zhan, Y., Tao, D., 2021. Deep graph-neighbor coherence preserving network for unsupervised cross-modal hashing. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 35, pp. 4626\u20134634.","DOI":"10.1609\/aaai.v35i5.16592"},{"issue":"3","key":"10.1016\/j.engappai.2025.112383_b47","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3446776","article-title":"Understanding deep learning (still) requires rethinking generalization","volume":"64","author":"Zhang","year":"2021","journal-title":"Commun. ACM"},{"key":"10.1016\/j.engappai.2025.112383_b48","doi-asserted-by":"crossref","unstructured":"Zhang, X., Lai, H., Feng, J., 2018. Attention-aware deep adversarial hashing for cross-modal retrieval. In: Proceedings of the European Conference on Computer Vision. pp. 591\u2013606.","DOI":"10.1007\/978-3-030-01267-0_36"},{"key":"10.1016\/j.engappai.2025.112383_b49","doi-asserted-by":"crossref","unstructured":"Zhang, P.-F., Li, Y., Huang, Z., Yin, H., 2021b. Privacy protection in deep multi-modal retrieval. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 634\u2013643.","DOI":"10.1145\/3404835.3462837"},{"issue":"5","key":"10.1016\/j.engappai.2025.112383_b50","first-page":"5091","article-title":"Modality-invariant asymmetric networks for cross-modal hashing","volume":"35","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.engappai.2025.112383_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108949","article-title":"Parallel weight control based on policy gradient of relation refinement for cross-modal retrieval","volume":"136","author":"Zhang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2025.112383_b52","doi-asserted-by":"crossref","unstructured":"Zheng, G., Awadallah, A.H., Dumais, S., 2021. Meta label correction for noisy label learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 35, pp. 11053\u201311061.","DOI":"10.1609\/aaai.v35i12.17319"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197625023917?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197625023917?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T01:30:41Z","timestamp":1761442241000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197625023917"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":52,"alternative-id":["S0952197625023917"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2025.112383","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Clean-sample guided cross-modal retrieval with adaptive weighted contrastive learning","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2025.112383","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112383"}}