{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:47:59Z","timestamp":1791686879395,"version":"4.3.4"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"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":["62571346"],"award-info":[{"award-number":["62571346"]}],"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":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109517","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:08:42Z","timestamp":1787008122000},"page":"109517","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["MEMC: Masked modeling with efficient and minimal contrastive learning for self-supervised skeleton-based action recognition"],"prefix":"10.1016","volume":"205","author":[{"given":"Yingfei","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenming","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7310-7488","authenticated-orcid":false,"given":"Xinpeng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109517_bib0001","series-title":"Milcom 2025-2025 IEEE military communications conference (MILCOM)","first-page":"1","article-title":"Joint scheduling and resource allocation in mmwave IAB networks using deep RL","author":"Abbasalizadeh","year":"2025"},{"issue":"6","key":"10.1016\/j.neunet.2026.109517_bib0002","doi-asserted-by":"crossref","first-page":"4067","DOI":"10.1007\/s00371-024-03646-2","article-title":"Mfinet: A multi-scale feature interaction network for point cloud registration","volume":"41","author":"Cao","year":"2025","journal-title":"The Visual Computer"},{"issue":"6","key":"10.1016\/j.neunet.2026.109517_bib0003","doi-asserted-by":"crossref","first-page":"5939","DOI":"10.1109\/TCSVT.2025.3529989","article-title":"Asymmetric context-guided adaptive alignment network for skeleton-based action recognition","volume":"35","author":"Cao","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109517_bib0004","unstructured":"Chen, X., Fan, H., Girshick, R. B., & He, K. (2020). Improved baselines with momentum contrastive learning. arXiv: abs\/2003.04297."},{"key":"10.1016\/j.neunet.2026.109517_bib0005","series-title":"2021\u202fIEEE\/CVF International conference on computer vision (ICCV)","first-page":"9640","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2026.109517_bib0006","unstructured":"Chen, Z., Liu, H., Guo, T., Chen, Z., Song, P., & Tang, H. (2022). Contrastive learning from spatio-temporal mixed skeleton sequences for self-supervised skeleton-based action recognition. arXiv: 2207.03065."},{"key":"10.1016\/j.neunet.2026.109517_bib0007","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"525","article-title":"Hierarchical contrast for unsupervised skeleton-based action representation learning","author":"Dong","year":"2023"},{"key":"10.1016\/j.neunet.2026.109517_bib0008","series-title":"The Ninth International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.neunet.2026.109517_bib0009","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9588","article-title":"With a little help from my friends: Nearest-neighbor contrastive learning of visual representations","author":"Dwibedi","year":"2021"},{"key":"10.1016\/j.neunet.2026.109517_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6075","article-title":"Beyond binary contrast: Modeling continuous skeleton action spaces with transitional anchors","author":"Feng","year":"2026"},{"key":"10.1016\/j.neunet.2026.109517_bib0011","series-title":"The eleventh international conference on learning representations","article-title":"Hyperbolic self-paced learning for self-supervised skeleton-based action representations","author":"Franco","year":"2023"},{"key":"10.1016\/j.neunet.2026.109517_bib0012","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1016\/j.neunet.2023.07.051","article-title":"Glimpse and focus: Global and local-scale graph convolution network for skeleton-based action recognition","volume":"167","author":"Gao","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109517_bib0013","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109517_bib0014","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"762","article-title":"Contrastive learning from extremely augmented skeleton sequences for self-supervised action recognition","author":"Guo","year":"2022"},{"key":"10.1016\/j.neunet.2026.109517_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110333","article-title":"Improving self-supervised action recognition from extremely augmented skeleton sequences","volume":"150","author":"Guo","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109517_bib0016","series-title":"2022\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"15979","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021"},{"key":"10.1016\/j.neunet.2026.109517_bib0017","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.2026.109517_bib0018","series-title":"Proceedings of the thirty-second international joint conference on artificial intelligence","article-title":"Part aware contrastive learning for self-supervised action recognition","author":"Hua","year":"2023"},{"key":"10.1016\/j.neunet.2026.109517_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113852","article-title":"Dpa-mvsnet: Dynamic context perception multi-view stereo with transformers and data augmentation","volume":"325","author":"Ji","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109517_bib0020","series-title":"The eleventh international conference on learning representations","article-title":"Layer grafted pre-training: Bridging contrastive learning and masked image modeling for label-efficient representations","author":"Jiang","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.109517_bib0021","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1109\/TCSVT.2023.3284493","article-title":"SSRL: Self-supervised spatial-temporal representation learning for 3d action recognition","volume":"34","author":"Jin","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109517_bib0022","first-page":"84","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"7","key":"10.1016\/j.neunet.2026.109517_bib0023","doi-asserted-by":"crossref","first-page":"7116","DOI":"10.1109\/TCSVT.2025.3540292","article-title":"Unsupervised feature enrichment and fidelity preservation learning framework for skeleton-based action recognition","volume":"35","author":"Li","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109517_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4741","article-title":"3D human action representation learning via cross-view consistency pursuit","author":"Li","year":"2021"},{"key":"10.1016\/j.neunet.2026.109517_bib0025","series-title":"Proceedings of the 28th ACM international conference on multimedia","first-page":"2490","article-title":"Ms2l: Multi-task self-supervised learning for skeleton based action recognition","author":"Lin","year":"2020"},{"key":"10.1016\/j.neunet.2026.109517_bib0026","series-title":"2023\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"2363","article-title":"ActionLet-dependent contrastive learning for unsupervised skeleton-based action recognition","author":"Lin","year":"2023"},{"key":"10.1016\/j.neunet.2026.109517_bib0027","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.1109\/TIP.2024.3372451","article-title":"Mutual information driven equivariant contrastive learning for 3d action representation learning","volume":"33","author":"Lin","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"issue":"10","key":"10.1016\/j.neunet.2026.109517_bib0028","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","article-title":"NTU RGB+ D 120: A large-scale benchmark for 3D human activity understanding","volume":"42","author":"Liu","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"10.1016\/j.neunet.2026.109517_bib0029","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3365212","article-title":"A benchmark dataset and comparison study for multi-modal human action analytics","volume":"16","author":"Liu","year":"2020","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"10.1016\/j.neunet.2026.109517_bib0030","series-title":"2023\u202fIEEE\/CVF International conference on computer vision (ICCV)","first-page":"10147","article-title":"Masked motion predictors are strong 3d action representation learners","author":"Mao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109517_bib0031","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"2858","article-title":"Stars: Self-supervised tuning for 3d action recognition in skeleton sequences","author":"Mehraban","year":"2026"},{"key":"10.1016\/j.neunet.2026.109517_bib0032","series-title":"Advances in neural information processing systems","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019"},{"key":"10.1016\/j.neunet.2026.109517_bib0033","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1010","article-title":"NTU RGB+ d: A large scale dataset for 3D human activity analysis","author":"Shahroudy","year":"2016"},{"key":"10.1016\/j.neunet.2026.109517_bib0034","series-title":"2020\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"9628","article-title":"Predict & cluster: Unsupervised skeleton based action recognition","author":"Su","year":"2020"},{"key":"10.1016\/j.neunet.2026.109517_bib0035","series-title":"Proceedings of the 29th ACM international conference on multimedia","first-page":"1655","article-title":"Skeleton-contrastive 3d action representation learning","author":"Thoker","year":"2021"},{"key":"10.1016\/j.neunet.2026.109517_bib0036","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109517_bib0037","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"588","article-title":"Human action recognition by representing 3d skeletons as points in a lie group","author":"Vemulapalli","year":"2014"},{"key":"10.1016\/j.neunet.2026.109517_bib0038","doi-asserted-by":"crossref","first-page":"6224","DOI":"10.1109\/TIP.2022.3207577","article-title":"Contrast-reconstruction representation learning for self-supervised skeleton-based action recognition","volume":"31","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109517_bib0039","doi-asserted-by":"crossref","first-page":"5257","DOI":"10.1109\/TIP.2022.3192706","article-title":"Extendable multiple nodes recurrent tracking framework with RTU++","volume":"31","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"issue":"4","key":"10.1016\/j.neunet.2026.109517_bib0040","doi-asserted-by":"crossref","DOI":"10.1002\/aisy.202200131","article-title":"Tasta: Text-assisted spatial and temporal attention network for video question answering","volume":"5","author":"Wang","year":"2023","journal-title":"Advanced Intelligent Systems"},{"key":"10.1016\/j.neunet.2026.109517_bib0041","doi-asserted-by":"crossref","first-page":"8923","DOI":"10.1109\/TPAMI.2025.3582518","article-title":"Evidence-based multi-feature fusion for adversarial robustness","volume":"47","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"8","key":"10.1016\/j.neunet.2026.109517_bib0042","doi-asserted-by":"crossref","first-page":"8332","DOI":"10.1609\/aaai.v39i8.32899","article-title":"USDRL: Unified skeleton-based dense representation learning with multi-grained feature decorrelation","volume":"39","author":"Weng","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109517_bib0043","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5949","article-title":"SCD-Net: Spatiotemporal clues disentanglement network for self-supervised skeleton-based action recognition","volume":"38","author":"Wu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109517_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107615","article-title":"Adaptive pooling with dual-stage fusion for skeleton-based action recognition","volume":"190","author":"Wu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109517_bib0045","series-title":"2023\u202fIEEE International conference on multimedia and expo workshops (ICMEW)","first-page":"224","article-title":"SkeletonMAE: Spatial-temporal masked autoencoders for self-supervised skeleton action recognition","author":"Wu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109517_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.108508","article-title":"ASR-GCN: Adaptive spatial information reconstruction GCN for skeleton-based action recognition","volume":"197","author":"Wu","year":"2026","journal-title":"Neural Networks"},{"issue":"1","key":"10.1016\/j.neunet.2026.109517_bib0047","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1109\/TPAMI.2023.3325463","article-title":"Self-supervised 3D action representation learning with skeleton cloud colorization","volume":"46","author":"Yang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109517_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110262","article-title":"Spatiotemporal progressive inward-outward aggregation network for skeleton-based action recognition","volume":"150","author":"Yin","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109517_bib0049","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"14963","article-title":"Co-evolution of pose and mesh for 3d human body estimation from video","author":"You","year":"2023"},{"key":"10.1016\/j.neunet.2026.109517_bib0050","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.neunet.2026.109517_bib0051","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.36922\/jcau.1635","article-title":"Ruixue multi-hall-human machine collaboration in reciprocal structures","volume":"6","author":"Yuan","year":"2024","journal-title":"Journal of Chinese Architecture and Urbanism"},{"key":"10.1016\/j.neunet.2026.109517_bib0052","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"7175","article-title":"Prompted contrast with masked motion modeling: Towards versatile 3D action representation learning","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109517_bib0053","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Unsupervised representation learning with long-term dynamics for skeleton based action recognition","volume":"32","author":"Zheng","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2026.109517_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.omtn.2023.102103","article-title":"Joint masking and self-supervised strategies for inferring small molecule-miRNA associations","volume":"35","author":"Zhou","year":"2024","journal-title":"Molecular Therapy Nucleic Acids"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009755?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009755?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:27:55Z","timestamp":1791685675000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026009755"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":54,"alternative-id":["S0893608026009755"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109517","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MEMC: Masked modeling with efficient and minimal contrastive learning for self-supervised skeleton-based action recognition","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109517","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109517"}}