{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T16:20:57Z","timestamp":1773937257657,"version":"3.50.1"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC2811500"],"award-info":[{"award-number":["2023YFC2811500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272300"],"award-info":[{"award-number":["62272300"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.neunet.2025.108474","type":"journal-article","created":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T23:34:27Z","timestamp":1765668867000},"page":"108474","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Align then clip: Refining graph for face clustering"],"prefix":"10.1016","volume":"197","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3632-5339","authenticated-orcid":false,"given":"Yanlun","family":"Tu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0083-2566","authenticated-orcid":false,"given":"Guoliang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7475-5770","authenticated-orcid":false,"given":"Jialiang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0196-5766","authenticated-orcid":false,"given":"Yuyang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3946-7439","authenticated-orcid":false,"given":"Min","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6587-9878","authenticated-orcid":false,"given":"Wentao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-5563","authenticated-orcid":false,"given":"Chen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5720-773X","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.neunet.2025.108474_bib0001","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1007\/s10791-008-9066-8","article-title":"A comparison of extrinsic clustering evaluation metrics based on formal constraints","volume":"12","author":"Amig\u00f3","year":"2009","journal-title":"Information Retrieval"},{"key":"10.1016\/j.neunet.2025.108474_bib0002","series-title":"International conference on machine learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2025.108474_bib0003","series-title":"European conference on computer vision","first-page":"529","article-title":"On mitigating hard clusters for face clustering","author":"Chen","year":"2022"},{"issue":"8","key":"10.1016\/j.neunet.2025.108474_bib0004","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1109\/34.400568","article-title":"Mean shift, mode seeking, and clustering","volume":"17","author":"Cheng","year":"1995","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108474_bib0005","first-page":"146","article-title":"I-Divergence geometry of probability distributions and minimization problems","author":"Csisz\u00e1r","year":"1975","journal-title":"The Annals of Probability"},{"key":"10.1016\/j.neunet.2025.108474_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4690","article-title":"Arcface: Additive angular margin loss for deep face recognition","author":"Deng","year":"2019"},{"issue":"Nov","key":"10.1016\/j.neunet.2025.108474_bib0007","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der","year":"2008","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"10.1016\/j.neunet.2025.108474_bib0008","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.neunet.2009.08.007","article-title":"Clustering: A neural network approach","volume":"23","author":"Du","year":"2010","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108474_bib0009","series-title":"Kdd","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume":"vol. 96","author":"Ester","year":"1996"},{"key":"10.1016\/j.neunet.2025.108474_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6698","article-title":"Density-aware feature embedding for face clustering","author":"Guo","year":"2020"},{"key":"10.1016\/j.neunet.2025.108474_bib0011","series-title":"European conference on computer vision","first-page":"87","article-title":"Ms-celeb-1m: A dataset and benchmark for large-scale face recognition","author":"Guo","year":"2016"},{"key":"10.1016\/j.neunet.2025.108474_bib0012","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108474_bib0013","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.neunet.2025.108474_bib0014","series-title":"2003 IEEE Computer society conference on computer vision and pattern recognition, 2003. proceedings.","article-title":"Clustering appearances of objects under varying illumination conditions","volume":"vol. 1","author":"Ho","year":"2003"},{"key":"10.1016\/j.neunet.2025.108474_bib0015","series-title":"International conference on learning representations","article-title":"Measuring and improving the use of graph information in graph neural networks","author":"Hou","year":"2019"},{"key":"10.1016\/j.neunet.2025.108474_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18750","article-title":"Adaface: Quality adaptive margin for face recognition","author":"Kim","year":"2022"},{"key":"10.1016\/j.neunet.2025.108474_bib0017","series-title":"International conference on learning representations (ICLR)","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"issue":"6","key":"10.1016\/j.neunet.2025.108474_bib0018","first-page":"5879","article-title":"Graph self-supervised learning: A survey","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2025.108474_bib0019","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1096","article-title":"Deepfashion: Powering robust clothes recognition and retrieval with rich annotations","author":"Liu","year":"2016"},{"issue":"2","key":"10.1016\/j.neunet.2025.108474_bib0020","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Transactions on Information Theory"},{"key":"10.1016\/j.neunet.2025.108474_bib0021","first-page":"1","article-title":"Sdst: Self-supervised double-structure transformer for hyperspectral images clustering","volume":"62","author":"Luo","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.108474_bib0022","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10847","article-title":"Clusformer: A transformer based clustering approach to unsupervised large-scale face and visual landmark recognition","author":"Nguyen","year":"2021"},{"key":"10.1016\/j.neunet.2025.108474_bib0023","series-title":"2024 IEEE International conference on quantum computing and engineering (QCE)","first-page":"347","article-title":"Qclusformer: A quantum transformer-based framework for unsupervised visual clustering","volume":"vol. 2","author":"Nguyen","year":"2024"},{"issue":"2","key":"10.1016\/j.neunet.2025.108474_bib0024","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TPAMI.2017.2679100","article-title":"Clustering millions of faces by identity","volume":"40","author":"Otto","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10.1016\/j.neunet.2025.108474_bib0025","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/0031-3203(92)90007-6","article-title":"Automatic recognition and analysis of human faces and facial expressions: A survey","volume":"25","author":"Samal","year":"1992","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108474_bib0026","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"20786","article-title":"Clip-cluster: Clip-guided attribute hallucination for face clustering","author":"Shen","year":"2023"},{"key":"10.1016\/j.neunet.2025.108474_bib0027","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","article-title":"Structure-aware face clustering on a large-scale graph with 107 nodes","author":"Shen","year":"2021"},{"issue":"11","key":"10.1016\/j.neunet.2025.108474_bib0028","first-page":"14005","article-title":"Star-fc: Structure-aware face clustering on ultra-large-scale graphs","volume":"45","author":"Shen","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10.1016\/j.neunet.2025.108474_bib0029","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1093\/comjnl\/16.1.30","article-title":"Slink: An optimally efficient algorithm for the single-link cluster method","volume":"16","author":"Sibson","year":"1973","journal-title":"The Computer Journal"},{"issue":"9","key":"10.1016\/j.neunet.2025.108474_bib0030","doi-asserted-by":"crossref","first-page":"1725","DOI":"10.1016\/j.patcog.2006.03.013","article-title":"Face recognition from a single image per person: A survey","volume":"39","author":"Tan","year":"2006","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108474_bib0031","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.neunet.2023.11.033","article-title":"Hierarchical attention network with progressive feature fusion for facial expression recognition","volume":"170","author":"Tao","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108474_bib0032","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.neunet.2025.108474_bib0033","series-title":"International conference on learning representations","article-title":"Deep graph infomax","author":"Veli\u010dkovi\u0107","year":"2019"},{"key":"10.1016\/j.neunet.2025.108474_bib0034","series-title":"International conference on learning representations (ICLR)","article-title":"Ada-NETS: Face clustering via adaptive neighbour discovery in the structure space","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108474_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1117","article-title":"Linkage based face clustering via graph convolution network","author":"Wang","year":"2019"},{"key":"10.1016\/j.neunet.2025.108474_bib0036","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"79","article-title":"Person transfer gan to bridge domain gap for person re-identification","author":"Wei","year":"2018"},{"key":"10.1016\/j.neunet.2025.108474_bib0037","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.patcog.2016.10.022","article-title":"A coupled hidden markov random field model for simultaneous face clustering and tracking in videos","volume":"64","author":"Wu","year":"2017","journal-title":"Pattern Recognition"},{"issue":"1","key":"10.1016\/j.neunet.2025.108474_bib0038","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.108474_bib0039","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"3467","article-title":"Learning hierarchical graph neural networks for image clustering","author":"Xing","year":"2021"},{"key":"10.1016\/j.neunet.2025.108474_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13369","article-title":"Learning to cluster faces via confidence and connectivity estimation","author":"Yang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108474_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2298","article-title":"Learning to cluster faces on an affinity graph","author":"Yang","year":"2019"},{"key":"10.1016\/j.neunet.2025.108474_bib0042","series-title":"Proceedings of the 33rd international conference on neural information processing systems","first-page":"5812","article-title":"Graph contrastive learning with augmentations","author":"You","year":"2020"},{"key":"10.1016\/j.neunet.2025.108474_bib0043","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Accelerated training for massive classification via dynamic class selection","volume":"vol. 32","author":"Zhang","year":"2018"},{"issue":"3","key":"10.1016\/j.neunet.2025.108474_bib0044","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1093\/bioinformatics\/btab718","article-title":"Accurate inference of gene regulatory interactions from spatial gene expression with deep contrastive learning","volume":"38","author":"Zheng","year":"2022","journal-title":"Bioinformatics"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025013553?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025013553?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:39:07Z","timestamp":1773931147000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025013553"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":44,"alternative-id":["S0893608025013553"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108474","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Align then clip: Refining graph for face clustering","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108474","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":"108474"}}