{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:24Z","timestamp":1740122844369,"version":"3.37.3"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T00:00:00Z","timestamp":1671580800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T00:00:00Z","timestamp":1671580800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004480","name":"Natural Science Foundation of Shanxi Province","doi-asserted-by":"publisher","award":["No.202103021224285"],"award-info":[{"award-number":["No.202103021224285"]}],"id":[{"id":"10.13039\/501100004480","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11063-022-11110-2","type":"journal-article","created":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T11:02:43Z","timestamp":1671620563000},"page":"5763-5781","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-level Self-supervised Representation Learning via Triple-way Attention Fusion and Local Similarity Optimization"],"prefix":"10.1007","volume":"55","author":[{"given":"Sulan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jifu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aiqin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,21]]},"reference":[{"key":"11110_CR1","unstructured":"Bachman P, Hjelm RD, Buchwalter W (2019) Learning representations by maximizing mutual information across views. In: Proceedings of the 33rd international conference on neural information processing systems, 15,535\u201315,545"},{"key":"11110_CR2","unstructured":"Belghazi MI, Baratin A, Rajeshwar S et\u00a0al (2018) Mutual information neural estimation. In: Proceedings of the 35th international conference on machine learning, 531\u2013540"},{"key":"11110_CR3","doi-asserted-by":"crossref","unstructured":"Caron M, Bojanowski P, Joulin A et\u00a0al (2018) Deep clustering for unsupervised learning of visual features. In: Proceedings of the European conference on computer vision, 132\u2013149","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"11110_CR4","unstructured":"Caron M, Misra I, Mairal J et\u00a0al (2020) Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in neural information processing systems, 9912\u20139924"},{"key":"11110_CR5","doi-asserted-by":"crossref","unstructured":"Chen P, Liu S, Jia J (2021) Jigsaw clustering for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 11,526\u201311,535","DOI":"10.1109\/CVPR46437.2021.01136"},{"key":"11110_CR6","unstructured":"Chen T, Kornblith S, Norouzi M et\u00a0al (2020) A simple framework for contrastive learning of visual representations. In: Proceedings of the international conference on machine learning, PMLR, 1597\u20131607"},{"key":"11110_CR7","unstructured":"Chen T, Kornblith S, Swersky K et\u00a0al (2020) Big self-supervised models are strong semi-supervised learners. In: Advances in neural information processing systems, 22,243\u201322,255"},{"key":"11110_CR8","doi-asserted-by":"crossref","unstructured":"Chen X, He K (2021) Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 15,750\u201315,758","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"11110_CR9","unstructured":"Coates A, Ng A, Lee H (2011) An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the 14th international conference on artificial intelligence and statistics, 215\u2013223"},{"key":"11110_CR10","doi-asserted-by":"crossref","unstructured":"Dai Y, Gieseke F, Oehmcke S et\u00a0al (2021) Attentional feature fusion. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, 3560\u20133569","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"11110_CR11","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R et\u00a0al (2009) Imagenet: A large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition, 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11110_CR12","unstructured":"Devon Hjelm R, Fedorov A, Lavoie-Marchildon S et\u00a0al (2018) Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670. https:\/\/arxiv.org\/abs\/arXiv:1808.06670 [stat.ML]"},{"key":"11110_CR13","doi-asserted-by":"crossref","unstructured":"Doersch C, Gupta A, Efros AA (2015) Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE international conference on computer vision, 1422\u20131430","DOI":"10.1109\/ICCV.2015.167"},{"key":"11110_CR14","unstructured":"Donahue J, Kr\u00e4henb\u00fchl P, Darrell T (2016) Adversarial Feature Learning. arXiv preprint arXiv:1605.09782. https:\/\/arxiv.org\/abs\/arXiv:1605.09782"},{"key":"11110_CR15","unstructured":"Gidaris S, Singh P, Komodakis N (2018) Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728"},{"key":"11110_CR16","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M et\u00a0al (2014) Generative adversarial nets. Advances in neural information processing systems 27"},{"key":"11110_CR17","unstructured":"Grill JB, Strub F, Altch\u00e9 F et\u00a0al (2020) Bootstrap your own latent - a new approach to self-supervised learning. In: Advances in neural information processing systems, 21,271\u201321,284"},{"key":"11110_CR18","unstructured":"Gutmann M, Hyv\u00e4rinen A (2010) Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In: Proceedings of the 13th international conference on artificial intelligence and statistics, 297\u2013304"},{"key":"11110_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et\u00a0al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11110_CR20","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y et\u00a0al (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 9729\u20139738","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"11110_CR21","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"11110_CR22","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.neucom.2021.04.053","volume":"452","author":"Z Huang","year":"2021","unstructured":"Huang Z, Chen HX, Zhou T et al (2021) Multi-level cross-modal interaction network for rgb-d salient object detection. Neurocomputing 452:200\u2013211","journal-title":"Neurocomputing"},{"key":"11110_CR23","unstructured":"Kingma DP, Welling M (2013) Auto-Encoding Variational Bayes. arXiv preprint arXiv:1312.6114. https:\/\/arxiv.org\/abs\/arXiv:1312.6114"},{"key":"11110_CR24","unstructured":"Krizhevsky A, Hinton G et\u00a0al (2009) Learning multiple layers of features from tiny images. Handbook of Systemic Autoimmune Diseases"},{"key":"11110_CR25","unstructured":"Kullback S (1997) Information theory and statistics. Courier Corporation"},{"key":"11110_CR26","doi-asserted-by":"crossref","unstructured":"Larsson G, Maire M, Shakhnarovich G (2016) Learning representations for automatic colorization. In: Proceedings of the European conference on computer vision, 577\u2013593","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"11110_CR27","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R et\u00a0al (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"11110_CR28","unstructured":"Liu S, Huang D, Wang Y (2019) Learning spatial fusion for single-shot object detection. arXiv preprint arXiv:1911.09516"},{"key":"11110_CR29","doi-asserted-by":"crossref","unstructured":"Liu X, Zhang F, Hou Z et\u00a0al (2021) Self-supervised learning: generative or contrastive. IEEE transactions on knowledge and data engineering","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"11110_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2021.01.010","volume":"435","author":"Y Liu","year":"2021","unstructured":"Liu Y, Zhang Y, Bhanu B et al (2021) Multi-level cross-view consistent feature learning for person re-identification. Neurocomputing 435:1\u201314","journal-title":"Neurocomputing"},{"key":"11110_CR31","doi-asserted-by":"crossref","unstructured":"Maoshan Liu, Wang ZJYan, (2021) Self-supervised convolutional subspace clustering network with the block diagonal regularizer. Neural Processing Letters 53:3849\u20133875","DOI":"10.1007\/s11063-021-10563-1"},{"key":"11110_CR32","doi-asserted-by":"crossref","unstructured":"Misra I, Maaten Lvd (2020) Self-supervised learning of pretext-invariant representations. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 6707\u20136717","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"11110_CR33","doi-asserted-by":"crossref","unstructured":"Noroozi M, Favaro P (2016) Unsupervised learning of visual representations by solving jigsaw puzzles. In: Proceedings of the European conference on computer vision, 69\u201384","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"11110_CR34","unstructured":"O.\u00a0Pinheiro PO, Almahairi A, Benmalek R et\u00a0al (2020) Unsupervised learning of dense visual representations. In: Advances in neural information processing systems, 4489\u20134500"},{"key":"11110_CR35","unstructured":"Van\u00a0den Oord A, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv preprint pp arXiv\u20131807"},{"key":"11110_CR36","unstructured":"Oord AV, Kalchbrenner N, Kavukcuoglu K (2016) Pixel recurrent neural networks. In: Proceedings of The 33rd international conference on machine learning, 1747\u20131756"},{"key":"11110_CR37","doi-asserted-by":"crossref","unstructured":"Pathak D, Krahenbuhl P, Donahue J et\u00a0al (2016) Context encoders: Feature learning by inpainting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2536\u20132544","DOI":"10.1109\/CVPR.2016.278"},{"key":"11110_CR38","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.neucom.2021.03.129","volume":"450","author":"X Qi","year":"2021","unstructured":"Qi X, Zhang Y, Qi J et al (2021) Self-attention guided representation learning for image-text matching. Neurocomputing 450:143\u2013155","journal-title":"Neurocomputing"},{"key":"11110_CR39","doi-asserted-by":"crossref","unstructured":"Qian R, Li Y, Liu H et\u00a0al (2021) Enhancing self-supervised video representation learning via multi-level feature optimization. In: Proceedings of the IEEE\/CVF international conference on computer vision, 7990\u20138001","DOI":"10.1109\/ICCV48922.2021.00789"},{"key":"11110_CR40","doi-asserted-by":"crossref","unstructured":"Roh B, Shin W, Kim I et\u00a0al (2021) Spatially consistent representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 1144\u20131153","DOI":"10.1109\/CVPR46437.2021.00120"},{"key":"11110_CR41","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, Springer, 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11110_CR42","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A et\u00a0al (2017) Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"11110_CR43","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"11110_CR44","doi-asserted-by":"crossref","unstructured":"Tian Y, Krishnan D, Isola P (2020) Contrastive multiview coding. In: Proceedings of the European conference on computer vision, 776\u2013794","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"11110_CR45","doi-asserted-by":"crossref","unstructured":"Rao Tianrong,Li MXXiaoxu (2020) Learning multi-level deep representations for image emotion classification. Neural Processing Letters 51:2043\u20132061","DOI":"10.1007\/s11063-019-10033-9"},{"issue":"14","key":"11110_CR46","doi-asserted-by":"publisher","first-page":"3573","DOI":"10.1049\/ipr2.12232","volume":"15","author":"Z Wang","year":"2021","unstructured":"Wang Z, Abhadiomhen SE, Liu Z, Shen X, Gao W, Li S (2021) Multi-view intrinsic low-rank representation for robust face recognition and clustering. IET Image Processing 15(14):3573\u20133584","journal-title":"IET Image Processing"},{"key":"11110_CR47","doi-asserted-by":"crossref","unstructured":"Wu Z, Xiong Y, Yu SX t\u00a0al (2018) Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 3733\u20133742","DOI":"10.1109\/CVPR.2018.00393"},{"key":"11110_CR48","doi-asserted-by":"crossref","unstructured":"Xie Z, Lin Y, Zhang Z et\u00a0al (2021) Propagate yourself: Exploring pixel-level consistency for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 16,684\u201316,693","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"11110_CR49","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1007\/s11063-021-10449-2","volume":"53","author":"S Yang","year":"2021","unstructured":"Yang S, Zheng X, Ji C et al (2021) Multi-layer representation learning and its application to electronic health records. Neural Process Lett 53:1417\u20131433","journal-title":"Neural Process Lett"},{"key":"11110_CR50","doi-asserted-by":"crossref","unstructured":"Ye M, Zhang X, Yuen PC et\u00a0al (2019) Unsupervised embedding learning via invariant and spreading instance feature. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 6210\u20136219","DOI":"10.1109\/CVPR.2019.00637"},{"key":"11110_CR51","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA (2016) Colorful image colorization. In: Proceedings of the European conference on computer vision, 649\u2013666","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"11110_CR52","unstructured":"Zhao N, Wu Z, Lau RW et\u00a0al (2020) What makes instance discrimination good for transfer learning? arXiv preprint arXiv:2006.06606"},{"key":"11110_CR53","doi-asserted-by":"crossref","unstructured":"Zhuang C, Zhai AL, Yamins D (2019) Local aggregation for unsupervised learning of visual embeddings. In: Proceedings of the IEEE\/CVF international conference on computer vision, 6002\u20136012","DOI":"10.1109\/ICCV.2019.00610"},{"issue":"104","key":"11110_CR54","first-page":"699","volume":"136","author":"H Zunair","year":"2021","unstructured":"Zunair H, Ben Hamza A (2021) Sharp u-net: Depthwise convolutional network for biomedical image segmentation. Comput Biol Med 136(104):699","journal-title":"Comput Biol Med"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-11110-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-11110-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-11110-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T16:13:06Z","timestamp":1696003986000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-11110-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,21]]},"references-count":54,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["11110"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-11110-2","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2022,12,21]]},"assertion":[{"value":"10 December 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 December 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}