{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T11:47:15Z","timestamp":1785930435936,"version":"3.56.0"},"reference-count":68,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62577001"],"award-info":[{"award-number":["62577001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272435"],"award-info":[{"award-number":["62272435"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2094"],"award-info":[{"award-number":["U22A2094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106003"],"award-info":[{"award-number":["62106003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.jvcir.2026.104799","type":"journal-article","created":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T15:17:34Z","timestamp":1775315854000},"page":"104799","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Gradually Vanishing Gap in Prototypical Network for unsupervised domain adaptation"],"prefix":"10.1016","volume":"118","author":[{"given":"Shanshan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"ALuSi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104799_b1","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: CVPR, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.jvcir.2026.104799_b2","article-title":"A survey on transfer learning","author":"Pan","year":"2009","journal-title":"TKDE"},{"key":"10.1016\/j.jvcir.2026.104799_b3","doi-asserted-by":"crossref","unstructured":"S. Wang, L. Zhang, Self-adaptive re-weighted adversarial domain adaptation, in: IJCAI, 2021, pp. 3181\u20133187.","DOI":"10.24963\/ijcai.2020\/440"},{"key":"10.1016\/j.jvcir.2026.104799_b4","doi-asserted-by":"crossref","unstructured":"S. Wang, Y. Chen, Z. He, X. Yang, M. Wang, Q. You, X. Zhang, Disentangled Representation Learning with Causality for Unsupervised Domain Adaptation, in: ACM MM, 2023.","DOI":"10.1145\/3581783.3611725"},{"key":"10.1016\/j.jvcir.2026.104799_b5","unstructured":"S. Wang, L. Zhang, W. Zuo, B. Zhang, Class-specific reconstruction transfer learning for visual recognition across domains, TIP."},{"key":"10.1016\/j.jvcir.2026.104799_b6","article-title":"Manifold criterion guided transfer learning via intermediate domain generation","author":"Zhang","year":"2019","journal-title":"TNNLS"},{"key":"10.1016\/j.jvcir.2026.104799_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102862","article-title":"Multi-source multi-modal domain adaptation","volume":"117","author":"Zhao","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.jvcir.2026.104799_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102757","article-title":"Divide and augment: Supervised domain adaptation via sample-wise feature fusion","volume":"115","author":"Chen","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.jvcir.2026.104799_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111025","article-title":"Overcoming learning bias via prototypical feature compensation for source-free domain adaptation","volume":"158","author":"Pan","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104799_b10","series-title":"ICML","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks","author":"Long","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104799_b11","unstructured":"M. Long, Z. Cao, J. Wang, M.I. Jordan, Conditional adversarial domain adaptation, in: NIPS, 2018."},{"key":"10.1016\/j.jvcir.2026.104799_b12","series-title":"ICML","article-title":"Progressive graph learning for open-set domain adaptation","author":"Luo","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104799_b13","doi-asserted-by":"crossref","unstructured":"S. Roy, E. Krivosheev, Z. Zhong, N. Sebe, E. Ricci, Curriculum graph co-teaching for multi-target domain adaptation, in: CVPR, 2021.","DOI":"10.1109\/CVPR46437.2021.00531"},{"key":"10.1016\/j.jvcir.2026.104799_b14","doi-asserted-by":"crossref","unstructured":"Z. Wu, Y. Xiong, S.X. Yu, D. Lin, Unsupervised feature learning via non-parametric instance discrimination, in: CVPR, 2018.","DOI":"10.1109\/CVPR.2018.00393"},{"key":"10.1016\/j.jvcir.2026.104799_b15","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, in: CVPR, 2020.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10.1016\/j.jvcir.2026.104799_b16","series-title":"ICML","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104799_b17","article-title":"A co-training framework for heterogeneous heuristic domain adaptation","author":"Yang","year":"2022","journal-title":"TNNLS"},{"key":"10.1016\/j.jvcir.2026.104799_b18","article-title":"Entropy minimization versus diversity maximization for domain adaptation","author":"Wu","year":"2021","journal-title":"TNNLS"},{"key":"10.1016\/j.jvcir.2026.104799_b19","doi-asserted-by":"crossref","DOI":"10.1007\/s10994-009-5152-4","article-title":"A theory of learning from different domains","author":"Ben-David","year":"2010","journal-title":"Mach Learn."},{"key":"10.1016\/j.jvcir.2026.104799_b20","article-title":"Reducing bi-level feature redundancy for unsupervised domain adaptation","author":"Wang","year":"2023","journal-title":"PR"},{"key":"10.1016\/j.jvcir.2026.104799_b21","series-title":"Deep domain confusion: Maximizing for domain invariance","author":"Tzeng","year":"2014"},{"key":"10.1016\/j.jvcir.2026.104799_b22","series-title":"ICML","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"Long","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104799_b23","article-title":"Unsupervised domain adaptation with residual transfer networks","volume":"vol. 29","author":"Long","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104799_b24","series-title":"ECCV","article-title":"Deep coral: Correlation alignment for deep domain adaptation","author":"Sun","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104799_b25","unstructured":"F. Zhuang, X. Cheng, P. Luo, S.J. Pan, Q. He, Supervised representation learning: Transfer learning with deep autoencoders, in: IJCAI, 2015."},{"key":"10.1016\/j.jvcir.2026.104799_b26","doi-asserted-by":"crossref","unstructured":"J. Shen, Y. Qu, W. Zhang, Y. Yu, Wasserstein distance guided representation learning for domain adaptation, in: AAAI, 2018.","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"10.1016\/j.jvcir.2026.104799_b27","doi-asserted-by":"crossref","unstructured":"G. Kang, L. Jiang, Y. Yang, A.G. Hauptmann, Contrastive adaptation network for unsupervised domain adaptation, in: CVPR, 2019.","DOI":"10.1109\/CVPR.2019.00503"},{"key":"10.1016\/j.jvcir.2026.104799_b28","doi-asserted-by":"crossref","unstructured":"J. Na, H. Jung, H.J. Chang, W. Hwang, Fixbi: Bridging domain spaces for unsupervised domain adaptation, in: CVPR, 2021, pp. 1094\u20131103.","DOI":"10.1109\/CVPR46437.2021.00115"},{"key":"10.1016\/j.jvcir.2026.104799_b29","doi-asserted-by":"crossref","unstructured":"X. Ma, T. Zhang, C. Xu, Gcan: Graph convolutional adversarial network for unsupervised domain adaptation, in: CVPR, 2019.","DOI":"10.1109\/CVPR.2019.00846"},{"key":"10.1016\/j.jvcir.2026.104799_b30","article-title":"Domain-adversarial training of neural networks","author":"Ganin","year":"2016","journal-title":"JMLR"},{"key":"10.1016\/j.jvcir.2026.104799_b31","doi-asserted-by":"crossref","unstructured":"K. Saito, K. Watanabe, Y. Ushiku, T. Harada, Maximum classifier discrepancy for unsupervised domain adaptation, in: CVPR, 2018.","DOI":"10.1109\/CVPR.2018.00392"},{"key":"10.1016\/j.jvcir.2026.104799_b32","series-title":"ICML","article-title":"Learning semantic representations for unsupervised domain adaptation","author":"Xie","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104799_b33","doi-asserted-by":"crossref","unstructured":"A. Sharma, T. Kalluri, M. Chandraker, Instance level affinity-based transfer for unsupervised domain adaptation, in: CVPR, 2021.","DOI":"10.1109\/CVPR46437.2021.00532"},{"key":"10.1016\/j.jvcir.2026.104799_b34","article-title":"BP-triplet net for unsupervised domain adaptation: A Bayesian perspective","volume":"133","author":"Wang","year":"2023","journal-title":"PR"},{"key":"10.1016\/j.jvcir.2026.104799_b35","first-page":"238","article-title":"Informative pairs mining based adaptive metric learning for adversarial domain adaptation","volume":"151","author":"Wang","year":"2022","journal-title":"NN"},{"key":"10.1016\/j.jvcir.2026.104799_b36","doi-asserted-by":"crossref","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"10.1016\/j.jvcir.2026.104799_b37","article-title":"The graph neural network model","author":"Scarselli","year":"2008","journal-title":"Trans. Neural Netw."},{"key":"10.1016\/j.jvcir.2026.104799_b38","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104799_b39","unstructured":"W. Hamilton, Z. Ying, J. Leskovec, Inductive representation learning on large graphs, in: NIPS, 2017."},{"key":"10.1016\/j.jvcir.2026.104799_b40","article-title":"Graph attention networks","author":"Velickovic","year":"2017","journal-title":"Stat"},{"key":"10.1016\/j.jvcir.2026.104799_b41","series-title":"In defense of the triplet loss for person re-identification","author":"Hermans","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104799_b42","series-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104799_b43","doi-asserted-by":"crossref","unstructured":"S. Wang, ALuSi, X. Yang, K. Xu, H. Tan, X. Zhang, Dual-stream feature augmentation for domain generalization, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 1111\u20131119.","DOI":"10.1145\/3664647.3680652"},{"key":"10.1016\/j.jvcir.2026.104799_b44","doi-asserted-by":"crossref","unstructured":"M. Thota, G. Leontidis, Contrastive domain adaptation, in: CVPR, 2021.","DOI":"10.1109\/CVPRW53098.2021.00250"},{"key":"10.1016\/j.jvcir.2026.104799_b45","unstructured":"J. Huang, D. Guan, A. Xiao, S. Lu, Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data, in: NIPS, 2021."},{"key":"10.1016\/j.jvcir.2026.104799_b46","doi-asserted-by":"crossref","unstructured":"J. Huang, D. Guan, A. Xiao, S. Lu, L. Shao, Category contrast for unsupervised domain adaptation in visual tasks, in: CVPR, 2022.","DOI":"10.1109\/CVPR52688.2022.00127"},{"key":"10.1016\/j.jvcir.2026.104799_b47","doi-asserted-by":"crossref","unstructured":"S. Li, M. Xie, K. Gong, C.H. Liu, Y. Wang, W. Li, Transferable semantic augmentation for domain adaptation, in: CVPR, 2021, pp. 11516\u201311525.","DOI":"10.1109\/CVPR46437.2021.01135"},{"key":"10.1016\/j.jvcir.2026.104799_b48","series-title":"ECCV","article-title":"Adapting visual category models to new domains","author":"Saenko","year":"2010"},{"key":"10.1016\/j.jvcir.2026.104799_b49","doi-asserted-by":"crossref","unstructured":"B. Caputo, H. M\u00fcller, J. Martinez-Gomez, M. Villegas, B. Acar, N. Patricia, N. Marvasti, S. \u00dcsk\u00fcdarl\u0131, R. Paredes, M. Cazorla, et al., ImageCLEF 2014: Overview and Analysis of the Results, Inf. Access Eval..","DOI":"10.1007\/978-3-319-11382-1_18"},{"key":"10.1016\/j.jvcir.2026.104799_b50","doi-asserted-by":"crossref","unstructured":"H. Venkateswara, J. Eusebio, S. Chakraborty, S. Panchanathan, Deep hashing network for unsupervised domain adaptation, in: CVPR, 2017.","DOI":"10.1109\/CVPR.2017.572"},{"key":"10.1016\/j.jvcir.2026.104799_b51","series-title":"Visda: The visual domain adaptation challenge","author":"Peng","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104799_b52","doi-asserted-by":"crossref","unstructured":"X. Peng, Q. Bai, X. Xia, Z. Huang, K. Saenko, B. Wang, Moment matching for multi-source domain adaptation, in: ICCV, 2019.","DOI":"10.1109\/ICCV.2019.00149"},{"key":"10.1016\/j.jvcir.2026.104799_b53","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","author":"Russakovsky","year":"2015","journal-title":"IJCV"},{"key":"10.1016\/j.jvcir.2026.104799_b54","unstructured":"A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, et al., Pytorch: An imperative style, high-performance deep learning library, in: NIPS, 2019."},{"key":"10.1016\/j.jvcir.2026.104799_b55","article-title":"Cross-domain contrastive learning for unsupervised domain adaptation","author":"Wang","year":"2022","journal-title":"TMM"},{"key":"10.1016\/j.jvcir.2026.104799_b56","article-title":"Cross-domain graph convolutions for adversarial unsupervised domain adaptation","author":"Zhu","year":"2021","journal-title":"TNNLS"},{"key":"10.1016\/j.jvcir.2026.104799_b57","doi-asserted-by":"crossref","unstructured":"L. Chen, H. Chen, Z. Wei, X. Jin, X. Tan, Y. Jin, E. Chen, Reusing the task-specific classifier as a discriminator: Discriminator-free adversarial domain adaptation, in: CVPR, 2022.","DOI":"10.1109\/CVPR52688.2022.00704"},{"key":"10.1016\/j.jvcir.2026.104799_b58","series-title":"Free lunch for domain adversarial training: Environment label smoothing","author":"Zhang","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104799_b59","doi-asserted-by":"crossref","unstructured":"T. Westfechtel, H.-W. Yeh, Q. Meng, Y. Mukuta, T. Harada, Backprop Induced Feature Weighting for Adversarial Domain Adaptation with Iterative Label Distribution Alignment, in: WACV, 2023.","DOI":"10.1109\/WACV56688.2023.00047"},{"key":"10.1016\/j.jvcir.2026.104799_b60","doi-asserted-by":"crossref","unstructured":"X. Gu, J. Sun, Z. Xu, Spherical space domain adaptation with robust pseudo-label loss, in: CVPR, 2020.","DOI":"10.1109\/CVPR42600.2020.00912"},{"key":"10.1016\/j.jvcir.2026.104799_b61","doi-asserted-by":"crossref","unstructured":"T. Westfechtel, H.-W. Yeh, D. Zhang, T. Harada, Gradual Source Domain Expansion for Unsupervised Domain Adaptation, in: WACV, 2024.","DOI":"10.1109\/WACV57701.2024.00195"},{"key":"10.1016\/j.jvcir.2026.104799_b62","article-title":"Confidence regularized label propagation based domain adaptation","author":"Wang","year":"2021","journal-title":"TCSVT"},{"key":"10.1016\/j.jvcir.2026.104799_b63","doi-asserted-by":"crossref","unstructured":"S. Cui, S. Wang, J. Zhuo, L. Li, Q. Huang, Q. Tian, Towards discriminability and diversity: Batch nuclear-norm maximization under label insufficient situations, in: CVPR, 2020.","DOI":"10.1109\/CVPR42600.2020.00400"},{"key":"10.1016\/j.jvcir.2026.104799_b64","doi-asserted-by":"crossref","unstructured":"C.-Y. Lee, T. Batra, M.H. Baig, D. Ulbricht, Sliced wasserstein discrepancy for unsupervised domain adaptation, in: CVPR, 2019.","DOI":"10.1109\/CVPR.2019.01053"},{"key":"10.1016\/j.jvcir.2026.104799_b65","doi-asserted-by":"crossref","unstructured":"Z. Du, J. Li, H. Su, L. Zhu, K. Lu, Cross-domain gradient discrepancy minimization for unsupervised domain adaptation, in: CVPR, 2021.","DOI":"10.1109\/CVPR46437.2021.00393"},{"key":"10.1016\/j.jvcir.2026.104799_b66","first-page":"6622","article-title":"Adaptive mutual learning for unsupervised domain adaptation","volume":"33","author":"Zhou","year":"2023","journal-title":"TCSVT"},{"key":"10.1016\/j.jvcir.2026.104799_b67","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1109\/TMM.2023.3277275","article-title":"Unsupervised domain adaptation via risk-consistent estimators","volume":"26","author":"Ding","year":"2024","journal-title":"Trans. Multi."},{"key":"10.1016\/j.jvcir.2026.104799_b68","article-title":"Visualizing data using t-SNE","author":"Van der Maaten","year":"2008","journal-title":"JMLR"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000945?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000945?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T11:23:09Z","timestamp":1785928989000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326000945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":68,"alternative-id":["S1047320326000945"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104799","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Gradually Vanishing Gap in Prototypical Network for unsupervised domain adaptation","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104799","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104799"}}