{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T11:26:58Z","timestamp":1793705218751,"version":"4.5.1"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T00:00:00Z","timestamp":1778716800000},"content-version":"vor","delay-in-days":133,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002862","name":"China University of Petroleum, Beijing","doi-asserted-by":"publisher","award":["RTX 4090"],"award-info":[{"award-number":["RTX 4090"]}],"id":[{"id":"10.13039\/501100002862","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Networks"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1016\/j.ijin.2026.05.004","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T23:26:10Z","timestamp":1779233170000},"page":"31-39","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Optimal transport enhanced text-assisted discriminative clustering for intelligent network images analytics"],"prefix":"10.1016","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5599-2764","authenticated-orcid":false,"given":"Chong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianyong","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.ijin.2026.05.004_b1","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.26599\/TST.2024.9010010","article-title":"Resilient TCP variant enabling smooth network updates for software-defined data center networks","volume":"29","author":"Dogar","year":"2024","journal-title":"Tsinghua Sci. Technol."},{"issue":"6","key":"10.1016\/j.ijin.2026.05.004_b2","doi-asserted-by":"crossref","first-page":"1728","DOI":"10.26599\/TST.2024.9010005","article-title":"Intelligent computational model for energy efficiency and AI automation of network devices in 5G communication environment","volume":"29","author":"Bagwari","year":"2024","journal-title":"Tsinghua Sci. Technol."},{"issue":"33","key":"10.1016\/j.ijin.2026.05.004_b3","doi-asserted-by":"crossref","first-page":"79985","DOI":"10.1007\/s11042-024-18598-x","article-title":"Data reweighting net for web fine-grained image classification","volume":"83","author":"Liu","year":"2024","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.ijin.2026.05.004_b4","series-title":"Data-driven meta-set based fine-grained visual classification","author":"Zhang","year":"2020"},{"key":"10.1016\/j.ijin.2026.05.004_b5","doi-asserted-by":"crossref","unstructured":"Z. Sun, Y. Yao, X.-S. Wei, Y. Zhang, F. Shen, J. Wu, J. Zhang, H.T. Shen, Webly supervised fine-grained recognition: Benchmark datasets and an approach, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10602\u201310611.","DOI":"10.1109\/ICCV48922.2021.01043"},{"key":"10.1016\/j.ijin.2026.05.004_b6","article-title":"Domain-specific self-supervised contrastive learning with contrast- aware pair refinement for pathological image analysis","author":"Li","year":"2025","journal-title":"Big Data Min. Anal."},{"issue":"8","key":"10.1016\/j.ijin.2026.05.004_b7","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: A survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.ijin.2026.05.004_b8","doi-asserted-by":"crossref","first-page":"45","DOI":"10.26599\/BDMA.2024.9020036","article-title":"GPT-NAS: Neural architecture search meets generative pre-trained transformer model","volume":"8","author":"Yu","year":"2025","journal-title":"Big Data Min. Anal."},{"key":"10.1016\/j.ijin.2026.05.004_b9","unstructured":"Y. Li, P. Hu, D. Peng, J. Lv, J. Fan, X. Peng, Image Clustering with External Guidance, in: Forty-First International Conference on Machine Learning, 2024."},{"issue":"11","key":"10.1016\/j.ijin.2026.05.004_b10","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","article-title":"WordNet: A lexical database for english","volume":"38","author":"Miller","year":"1995","journal-title":"Commun. ACM"},{"issue":"3","key":"10.1016\/j.ijin.2026.05.004_b11","doi-asserted-by":"crossref","first-page":"563","DOI":"10.26599\/BDMA.2024.9020062","article-title":"MFD-KD: Multi-scale frequency-driven knowledge distillation","volume":"8","author":"Dai","year":"2025","journal-title":"Big Data Min. Anal."},{"issue":"2","key":"10.1016\/j.ijin.2026.05.004_b12","doi-asserted-by":"crossref","first-page":"425","DOI":"10.26599\/BDMA.2025.9020090","article-title":"Vision-language model-driven human-vehicle interaction for autonomous driving: Status, challenge, and innovation","volume":"9","author":"Zhao","year":"2026","journal-title":"Big Data Min. Anal."},{"key":"10.1016\/j.ijin.2026.05.004_b13","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"9","key":"10.1016\/j.ijin.2026.05.004_b14","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.ijin.2026.05.004_b15","doi-asserted-by":"crossref","unstructured":"K. Zhou, J. Yang, C.C. Loy, Z. Liu, Conditional prompt learning for vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16816\u201316825.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"10.1016\/j.ijin.2026.05.004_b16","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.ijin.2026.05.004_b17","doi-asserted-by":"crossref","unstructured":"M.U. Khattak, H. Rasheed, M. Maaz, S. Khan, F.S. Khan, Maple: Multi-modal prompt learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19113\u201319122.","DOI":"10.1109\/CVPR52729.2023.01832"},{"issue":"1","key":"10.1016\/j.ijin.2026.05.004_b18","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1631\/FITEE.2300389","article-title":"Prompt learning in computer vision: A survey","volume":"25","author":"Lei","year":"2024","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"10.1016\/j.ijin.2026.05.004_b19","article-title":"Knowledge-driven reasoning for compatible and interpretable API recommendation via teacher LLM distillation","author":"Qi","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"issue":"4","key":"10.1016\/j.ijin.2026.05.004_b20","doi-asserted-by":"crossref","first-page":"1782","DOI":"10.26599\/TST.2024.9010065","article-title":"Social media-driven user community finding with privacy protection","volume":"30","author":"Xie","year":"2025","journal-title":"Tsinghua Sci. Technol."},{"key":"10.1016\/j.ijin.2026.05.004_b21","series-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","first-page":"1630","article-title":"Event detection as graph parsing","author":"Xie","year":"2021"},{"issue":"5","key":"10.1016\/j.ijin.2026.05.004_b22","doi-asserted-by":"crossref","first-page":"2353","DOI":"10.26599\/TST.2025.9010008","article-title":"Prototype-based feature representation learning for image deep clustering","volume":"31","author":"Zhang","year":"2026","journal-title":"Tsinghua Sci. Technol."},{"key":"10.1016\/j.ijin.2026.05.004_b23","doi-asserted-by":"crossref","unstructured":"J. Yang, D. Parikh, D. Batra, Joint unsupervised learning of deep representations and image clusters, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 5147\u20135156.","DOI":"10.1109\/CVPR.2016.556"},{"key":"10.1016\/j.ijin.2026.05.004_b24","series-title":"International Conference on Machine Learning","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","author":"Xie","year":"2016"},{"key":"10.1016\/j.ijin.2026.05.004_b25","doi-asserted-by":"crossref","unstructured":"K. Ghasedi Dizaji, A. Herandi, C. Deng, W. Cai, H. Huang, Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5736\u20135745.","DOI":"10.1109\/ICCV.2017.612"},{"key":"10.1016\/j.ijin.2026.05.004_b26","doi-asserted-by":"crossref","unstructured":"J. Xie, L. Qi, F. Wang, A. Wang, W. Gong, D. Wang, W. Dou, Y. Cao, S. Pei, X. Zhou, Retrieval-driven Reasoning for Deliberative Visual Classification, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 40, 2026, pp. 11060\u201311068.","DOI":"10.1609\/aaai.v40i13.38084"},{"key":"10.1016\/j.ijin.2026.05.004_b27","doi-asserted-by":"crossref","unstructured":"X. Ji, J.F. Henriques, A. Vedaldi, Invariant information clustering for unsupervised image classification and segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9865\u20139874.","DOI":"10.1109\/ICCV.2019.00996"},{"key":"10.1016\/j.ijin.2026.05.004_b28","series-title":"International Conference on Machine Learning","first-page":"5171","article-title":"On variational bounds of mutual information","author":"Poole","year":"2019"},{"key":"10.1016\/j.ijin.2026.05.004_b29","series-title":"Understanding the limitations of variational mutual information estimators","author":"Song","year":"2019"},{"issue":"12","key":"10.1016\/j.ijin.2026.05.004_b30","doi-asserted-by":"crossref","first-page":"4426","DOI":"10.1109\/TPAMI.2020.3002587","article-title":"Large graph clustering with simultaneous spectral embedding and discretization","volume":"43","author":"Wang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.ijin.2026.05.004_b31","doi-asserted-by":"crossref","unstructured":"S. Cai, L. Qiu, X. Chen, Q. Zhang, L. Chen, Semantic-enhanced image clustering, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 6869\u20136878.","DOI":"10.1609\/aaai.v37i6.25841"},{"key":"10.1016\/j.ijin.2026.05.004_b32","series-title":"Optimal Transport: Old and New","author":"Villani","year":"2009"},{"key":"10.1016\/j.ijin.2026.05.004_b33","series-title":"Computational Optimal Transport: with Applications to Data Science","author":"Peyr\u00e9","year":"2019"},{"issue":"314","key":"10.1016\/j.ijin.2026.05.004_b34","doi-asserted-by":"crossref","first-page":"2563","DOI":"10.1090\/mcom\/3303","article-title":"Scaling algorithms for unbalanced optimal transport problems","volume":"87","author":"Chizat","year":"2018","journal-title":"Math. Comp."},{"key":"10.1016\/j.ijin.2026.05.004_b35","doi-asserted-by":"crossref","first-page":"61777","DOI":"10.52202\/075280-2700","article-title":"Deep optimal transport: A practical algorithm for photo-realistic image restoration","volume":"36","author":"Adrai","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ijin.2026.05.004_b36","article-title":"Learning with a wasserstein loss","volume":"28","author":"Frogner","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ijin.2026.05.004_b37","article-title":"Improved training of wasserstein gans","volume":"30","author":"Gulrajani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ijin.2026.05.004_b38","series-title":"Self-labelling via simultaneous clustering and representation learning","author":"Asano","year":"2019"},{"issue":"9","key":"10.1016\/j.ijin.2026.05.004_b39","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1109\/TPAMI.2016.2615921","article-title":"Optimal transport for domain adaptation","volume":"39","author":"Courty","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.ijin.2026.05.004_b40","doi-asserted-by":"crossref","first-page":"29512","DOI":"10.52202\/068431-2140","article-title":"Unified optimal transport framework for universal domain adaptation","volume":"35","author":"Chang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ijin.2026.05.004_b41","series-title":"Prompt learning with optimal transport for vision-language models","author":"Chen","year":"2022"},{"key":"10.1016\/j.ijin.2026.05.004_b42","series-title":"2022 IEEE International Conference on Image Processing","first-page":"3465","article-title":"Fusing global and local features for generalized ai-synthesized image detection","author":"Ju","year":"2022"},{"key":"10.1016\/j.ijin.2026.05.004_b43","series-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"Coates","year":"2011"},{"key":"10.1016\/j.ijin.2026.05.004_b44","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.ijin.2026.05.004_b45","doi-asserted-by":"crossref","unstructured":"J. Chang, L. Wang, G. Meng, S. Xiang, C. Pan, Deep adaptive image clustering, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5879\u20135887.","DOI":"10.1109\/ICCV.2017.626"},{"key":"10.1016\/j.ijin.2026.05.004_b46","doi-asserted-by":"crossref","unstructured":"M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, A. Vedaldi, Describing textures in the wild, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 3606\u20133613.","DOI":"10.1109\/CVPR.2014.461"},{"key":"10.1016\/j.ijin.2026.05.004_b47","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.ijin.2026.05.004_b48","series-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.ijin.2026.05.004_b49","doi-asserted-by":"crossref","unstructured":"Y. Li, P. Hu, Z. Liu, D. Peng, J.T. Zhou, X. Peng, Contrastive clustering, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 8547\u20138555.","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"10.1016\/j.ijin.2026.05.004_b50","series-title":"Clustering-friendly representation learning via instance discrimination and feature decorrelation","author":"Tao","year":"2021"},{"key":"10.1016\/j.ijin.2026.05.004_b51","series-title":"European Conference on Computer Vision","first-page":"268","article-title":"Scan: Learning to classify images without labels","author":"Van Gansbeke","year":"2020"},{"key":"10.1016\/j.ijin.2026.05.004_b52","unstructured":"T.W. Tsai, C. Li, J. Zhu, Mice: Mixture of contrastive experts for unsupervised image clustering, in: International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.ijin.2026.05.004_b53","doi-asserted-by":"crossref","unstructured":"H. Zhong, J. Wu, C. Chen, J. Huang, M. Deng, L. Nie, Z. Lin, X.-S. Hua, Graph contrastive clustering, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 9224\u20139233.","DOI":"10.1109\/ICCV48922.2021.00909"},{"key":"10.1016\/j.ijin.2026.05.004_b54","doi-asserted-by":"crossref","unstructured":"Z. Dang, C. Deng, X. Yang, K. Wei, H. Huang, Nearest neighbor matching for deep clustering, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13693\u201313702.","DOI":"10.1109\/CVPR46437.2021.01348"},{"key":"10.1016\/j.ijin.2026.05.004_b55","first-page":"27734","article-title":"You never cluster alone","volume":"34","author":"Shen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ijin.2026.05.004_b56","doi-asserted-by":"crossref","first-page":"7264","DOI":"10.1109\/TIP.2022.3221290","article-title":"Spice: Semantic pseudo-labeling for image clustering","volume":"31","author":"Niu","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.ijin.2026.05.004_b57","series-title":"Exploring the limits of deep image clustering using pretrained models","author":"Adaloglou","year":"2023"},{"key":"10.1016\/j.ijin.2026.05.004_b58","series-title":"Image Clustering Via the Principle of Rate Reduction in the Age of Pretrained Models","author":"Chu","year":"2024"}],"updated-by":[{"DOI":"10.1016\/j.ijin.2026.08.001","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000}},{"DOI":"10.1016\/j.ijin.2026.08.001","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000}}],"container-title":["International Journal of Intelligent Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666603026000114?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666603026000114?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T10:43:41Z","timestamp":1793702621000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666603026000114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"alternative-id":["S2666603026000114"],"URL":"https:\/\/doi.org\/10.1016\/j.ijin.2026.05.004","relation":{},"ISSN":["2666-6030"],"issn-type":[{"value":"2666-6030","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Optimal transport enhanced text-assisted discriminative clustering for intelligent network images analytics","name":"articletitle","label":"Article Title"},{"value":"International Journal of Intelligent Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ijin.2026.05.004","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Publishing services by Elsevier B.V. on behalf of Higher Education Press and KeAi Communications Co. Ltd.","name":"copyright","label":"Copyright"}]}}