{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:08:55Z","timestamp":1778800135024,"version":"3.51.4"},"reference-count":47,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.cviu.2026.104750","type":"journal-article","created":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T13:10:08Z","timestamp":1775308208000},"page":"104750","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Hierarchical contrastive distillation: Bridging multi-level semantics for enhanced knowledge transfer"],"prefix":"10.1016","volume":"268","author":[{"given":"Haoda","family":"Zou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1164-7534","authenticated-orcid":false,"given":"Wentao","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104750_b1","doi-asserted-by":"crossref","unstructured":"Ahn,\u00a0S., Hu,\u00a0S.X., Damianou,\u00a0A., Lawrence,\u00a0N.D., Dai,\u00a0Z., 2019. Variational information distillation for knowledge transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9163\u20139171.","DOI":"10.1109\/CVPR.2019.00938"},{"key":"10.1016\/j.cviu.2026.104750_b2","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.cviu.2026.104750_b3","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0P., Liu,\u00a0S., Zhao,\u00a0H., Jia,\u00a0J., 2021. Distilling knowledge via knowledge review. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5008\u20135017.","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"10.1016\/j.cviu.2026.104750_b4","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0D., Mei,\u00a0J.-P., Zhang,\u00a0H., Wang,\u00a0C., Feng,\u00a0Y., Chen,\u00a0C., 2022. Knowledge distillation with the reused teacher classifier. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11933\u201311942.","DOI":"10.1109\/CVPR52688.2022.01163"},{"key":"10.1016\/j.cviu.2026.104750_b5","article-title":"Sinkd: Sinkhorn distance minimization for knowledge distillation","author":"Cui","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.cviu.2026.104750_b6","series-title":"2024 IEEE International Conference on Edge Computing and Communications","first-page":"121","article-title":"Classifier reuse-based contrastive knowledge distillation","author":"Gao","year":"2024"},{"issue":"4","key":"10.1016\/j.cviu.2026.104750_b7","doi-asserted-by":"crossref","first-page":"2051","DOI":"10.1109\/TIP.2018.2883743","article-title":"Low-resolution face recognition in the wild via selective knowledge distillation","volume":"28","author":"Ge","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104750_b8","series-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018"},{"key":"10.1016\/j.cviu.2026.104750_b9","doi-asserted-by":"crossref","unstructured":"Guo,\u00a0Z., Yan,\u00a0H., Li,\u00a0H., Lin,\u00a0X., 2023. Class attention transfer based knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11868\u201311877.","DOI":"10.1109\/CVPR52729.2023.01142"},{"key":"10.1016\/j.cviu.2026.104750_b10","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Chen,\u00a0X., Xie,\u00a0S., Li,\u00a0Y., Doll\u00e1r,\u00a0P., Girshick,\u00a0R., 2022. Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.cviu.2026.104750_b11","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Fan,\u00a0H., Wu,\u00a0Y., Xie,\u00a0S., Girshick,\u00a0R., 2020. Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10.1016\/j.cviu.2026.104750_b12","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3779","article-title":"Knowledge transfer via distillation of activation boundaries formed by hidden neurons","volume":"vol. 33","author":"Heo","year":"2019"},{"key":"10.1016\/j.cviu.2026.104750_b13","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"10.1016\/j.cviu.2026.104750_b14","series-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"10.1016\/j.cviu.2026.104750_b15","series-title":"Multi-scale dense networks for resource efficient image classification","author":"Huang","year":"2017"},{"issue":"2","key":"10.1016\/j.cviu.2026.104750_b16","doi-asserted-by":"crossref","first-page":"935","DOI":"10.3390\/app13020935","article-title":"Face mask detection on photo and real-time video images using caffe-MobileNetV2 transfer learning","volume":"13","author":"Kumar","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.cviu.2026.104750_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123179","article-title":"Masked face age and gender identification using CAFFE-modified MobileNetV2 on photo and real-time video images by transfer learning and deep learning techniques","volume":"246","author":"Kumar","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cviu.2026.104750_b18","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1504","article-title":"Curriculum temperature for knowledge distillation","volume":"vol. 37","author":"Li","year":"2023"},{"issue":"1","key":"10.1016\/j.cviu.2026.104750_b19","first-page":"857","article-title":"Self-supervised learning: Generative or contrastive","volume":"35","author":"Liu","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.cviu.2026.104750_b20","series-title":"European Conference on Computer Vision","first-page":"69","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"Noroozi","year":"2016"},{"key":"10.1016\/j.cviu.2026.104750_b21","doi-asserted-by":"crossref","unstructured":"Park,\u00a0W., Kim,\u00a0D., Lu,\u00a0Y., Cho,\u00a0M., 2019. Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3967\u20133976.","DOI":"10.1109\/CVPR.2019.00409"},{"key":"10.1016\/j.cviu.2026.104750_b22","doi-asserted-by":"crossref","unstructured":"Passalis,\u00a0N., Tefas,\u00a0A., 2018. Learning deep representations with probabilistic knowledge transfer. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 268\u2013284.","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"10.1016\/j.cviu.2026.104750_b23","doi-asserted-by":"crossref","unstructured":"Peng,\u00a0B., Jin,\u00a0X., Liu,\u00a0J., Li,\u00a0D., Wu,\u00a0Y., Liu,\u00a0Y., Zhou,\u00a0S., Zhang,\u00a0Z., 2019. Correlation congruence for knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 5007\u20135016.","DOI":"10.1109\/ICCV.2019.00511"},{"key":"10.1016\/j.cviu.2026.104750_b24","series-title":"Contrastive learning with hard negative samples","author":"Robinson","year":"2020"},{"key":"10.1016\/j.cviu.2026.104750_b25","series-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"10.1016\/j.cviu.2026.104750_b26","doi-asserted-by":"crossref","unstructured":"Shu,\u00a0C., Liu,\u00a0Y., Gao,\u00a0J., Yan,\u00a0Z., Shen,\u00a0C., 2021. Channel-wise knowledge distillation for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 5311\u20135320.","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"10.1016\/j.cviu.2026.104750_b27","doi-asserted-by":"crossref","unstructured":"Sun,\u00a0S., Ren,\u00a0W., Li,\u00a0J., Wang,\u00a0R., Cao,\u00a0X., 2024. Logit standardization in knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15731\u201315740.","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"10.1016\/j.cviu.2026.104750_b28","doi-asserted-by":"crossref","unstructured":"Sun,\u00a0K., Xiao,\u00a0B., Liu,\u00a0D., Wang,\u00a0J., 2019. Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5693\u20135703.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"10.1016\/j.cviu.2026.104750_b29","series-title":"Contrastive representation distillation","author":"Tian","year":"2019"},{"key":"10.1016\/j.cviu.2026.104750_b30","doi-asserted-by":"crossref","unstructured":"Tung,\u00a0F., Mori,\u00a0G., 2019. Similarity-preserving knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1365\u20131374.","DOI":"10.1109\/ICCV.2019.00145"},{"key":"10.1016\/j.cviu.2026.104750_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103902","article-title":"Global key knowledge distillation framework","volume":"239","author":"Wang","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104750_b32","series-title":"Contrastive learning rivals masked image modeling in fine-tuning via feature distillation","author":"Wei","year":"2022"},{"key":"10.1016\/j.cviu.2026.104750_b33","series-title":"European Conference on Computer Vision","first-page":"588","article-title":"Knowledge distillation meets self-supervision","author":"Xu","year":"2020"},{"key":"10.1016\/j.cviu.2026.104750_b34","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0Y., Yang,\u00a0Y., Zhang,\u00a0L., 2023. Multi-task learning with knowledge distillation for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 21550\u201321559.","DOI":"10.1109\/ICCV51070.2023.01970"},{"key":"10.1016\/j.cviu.2026.104750_b35","series-title":"2021 IEEE International Conference on Image Processing","first-page":"489","article-title":"Image enhanced rotation prediction for self-supervised learning","author":"Yamaguchi","year":"2021"},{"issue":"2","key":"10.1016\/j.cviu.2026.104750_b36","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1109\/TNNLS.2022.3186807","article-title":"Knowledge distillation using hierarchical self-supervision augmented distribution","volume":"35","author":"Yang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"1","key":"10.1016\/j.cviu.2026.104750_b37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3472393","article-title":"RD-IOD: Two-level residual-distillation-based triple-network for incremental object detection","volume":"18","author":"Yang","year":"2022","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"10.1016\/j.cviu.2026.104750_b38","doi-asserted-by":"crossref","unstructured":"Yim,\u00a0J., Joo,\u00a0D., Bae,\u00a0J., Kim,\u00a0J., 2017. A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4133\u20134141.","DOI":"10.1109\/CVPR.2017.754"},{"key":"10.1016\/j.cviu.2026.104750_b39","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"Yosinski","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104750_b40","doi-asserted-by":"crossref","unstructured":"Yu,\u00a0Z., Xu,\u00a0Q., Jiang,\u00a0Y., Qin,\u00a0H., Huang,\u00a0Q., 2022. Pay attention to your positive pairs: Positive pair aware contrastive knowledge distillation. In: Proceedings of the 30th ACM International Conference on Multimedia. pp. 5862\u20135870.","DOI":"10.1145\/3503161.3548256"},{"key":"10.1016\/j.cviu.2026.104750_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111915","article-title":"Student-friendly knowledge distillation","volume":"296","author":"Yuan","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.cviu.2026.104750_b42","series-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016"},{"issue":"4","key":"10.1016\/j.cviu.2026.104750_b43","doi-asserted-by":"crossref","first-page":"2251","DOI":"10.1109\/TCSVT.2021.3090902","article-title":"Student network learning via evolutionary knowledge distillation","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2026.104750_b44","doi-asserted-by":"crossref","unstructured":"Zhao,\u00a0B., Cui,\u00a0Q., Song,\u00a0R., Qiu,\u00a0Y., Liang,\u00a0J., 2022. Decoupled knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11953\u201311962.","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"10.1016\/j.cviu.2026.104750_b45","series-title":"Knowledge distillation based on transformed teacher matching","author":"Zheng","year":"2024"},{"key":"10.1016\/j.cviu.2026.104750_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2025.104359","article-title":"Extensions in channel and class dimensions for attention-based knowledge distillation","volume":"257","author":"Zhou","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104750_b47","doi-asserted-by":"crossref","unstructured":"Zhu,\u00a0J., Tang,\u00a0S., Chen,\u00a0D., Yu,\u00a0S., Liu,\u00a0Y., Rong,\u00a0M., Yang,\u00a0A., Wang,\u00a0X., 2021. Complementary relation contrastive distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9260\u20139269.","DOI":"10.1109\/CVPR46437.2021.00914"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001177?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001177?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T22:30:30Z","timestamp":1778797830000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226001177"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":47,"alternative-id":["S1077314226001177"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104750","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical contrastive distillation: Bridging multi-level semantics for enhanced knowledge transfer","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104750","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":"104750"}}