{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:07:16Z","timestamp":1783926436085,"version":"3.55.0"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100008081","name":"Southeast University","doi-asserted-by":"publisher","award":["KP202402"],"award-info":[{"award-number":["KP202402"]}],"id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372104"],"award-info":[{"award-number":["62372104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114399","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:45:01Z","timestamp":1783061101000},"page":"114399","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Feature-constrained consistency learning for multi-view online action detection"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7350-3238","authenticated-orcid":false,"given":"Yufeng","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0986-9760","authenticated-orcid":false,"given":"Liping","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9107-1056","authenticated-orcid":false,"given":"Yang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0920-7037","authenticated-orcid":false,"given":"Jiajie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9794-3221","authenticated-orcid":false,"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114399_b1","doi-asserted-by":"crossref","first-page":"2364","DOI":"10.1016\/j.procs.2022.09.295","article-title":"A novel spatial\u2013temporal analysis approach to pedestrian groups detection","volume":"207","author":"Cavallaro","year":"2022","journal-title":"Procedia Comput. Sci."},{"issue":"1","key":"10.1016\/j.patcog.2026.114399_b2","first-page":"397","article-title":"A review of supervised and unsupervised machine learning techniques for suspicious behavior recognition in intelligent surveillance system","volume":"14","author":"Verma","year":"2022","journal-title":"Int. J. Inf. Technol."},{"issue":"3","key":"10.1016\/j.patcog.2026.114399_b3","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1109\/TCYB.2021.3108143","article-title":"Graph regularized structured output SVM for early expression detection with online extension","volume":"53","author":"Xie","year":"2023","journal-title":"IEEE Trans. Cybern."},{"issue":"2","key":"10.1016\/j.patcog.2026.114399_b4","first-page":"2325","article-title":"Monitoring and analysis of athletes\u2019 local body movement status based on BP neural network","volume":"40","author":"Zhang","year":"2021","journal-title":"J. Intell. Fuzzy Systems"},{"key":"10.1016\/j.patcog.2026.114399_b5","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.neucom.2022.04.087","article-title":"Multi-object tracking in traffic environments: A systematic literature review","volume":"494","author":"Jim\u00e9nez-Bravo","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114399_b6","doi-asserted-by":"crossref","unstructured":"M. Tayyab, A. Jalal, Disabled rehabilitation monitoring and patients healthcare recognition using machine learning, in: International Conference on Advancements in Computational Sciences, 2025, pp. 1\u20137.","DOI":"10.1109\/ICACS64902.2025.10937871"},{"key":"10.1016\/j.patcog.2026.114399_b7","doi-asserted-by":"crossref","unstructured":"P. Sivalakshmi, U. Kavitha, R. Usha, O. Pattanaik, S. Maniraj, C. Srinivasan, Smart retail store surveillance and security with cloud-powered video analytics and transfer learning algorithms, in: International Conference on Intelligent Cyber Physical Systems and Internet of Things, 2024, pp. 242\u2013247.","DOI":"10.1109\/ICoICI62503.2024.10696050"},{"key":"10.1016\/j.patcog.2026.114399_b8","doi-asserted-by":"crossref","unstructured":"K. Shah, A. Shah, C.P. Lau, C.M. de Melo, R. Chellappa, Multi-View Action Recognition Using Contrastive Learning, in: Winter Conference on Applications of Computer Vision, 2023, pp. 3381\u20133391.","DOI":"10.1109\/WACV56688.2023.00338"},{"key":"10.1016\/j.patcog.2026.114399_b9","article-title":"From temporal thumbnail to semantics: Debiasing multi-view action recognition","author":"Feng","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114399_b10","doi-asserted-by":"crossref","unstructured":"S. Vyas, Y.S. Rawat, M. Shah, Multi-view Action Recognition Using Cross-View Video Prediction, in: European Conference on Computer Vision, 2020, pp. 427\u2013444.","DOI":"10.1007\/978-3-030-58583-9_26"},{"key":"10.1016\/j.patcog.2026.114399_b11","series-title":"MV-GMN: State space model for multi-view action recognition","author":"Lin","year":"2025"},{"key":"10.1016\/j.patcog.2026.114399_b12","doi-asserted-by":"crossref","unstructured":"R. Ghoddoosian, I. Dwivedi, N. Agarwal, C. Choi, B. Dariush, Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos, in: Computer Vision and Pattern Recognition, 2022, pp. 13780\u201313790.","DOI":"10.1109\/CVPR52688.2022.01341"},{"key":"10.1016\/j.patcog.2026.114399_b13","doi-asserted-by":"crossref","unstructured":"R. De Geest, E. Gavves, A. Ghodrati, Z. Li, C. Snoek, T. Tuytelaars, Online Action Detection, in: European Conference on Computer Vision, 2016, pp. 269\u2013284.","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"10.1016\/j.patcog.2026.114399_b14","doi-asserted-by":"crossref","unstructured":"J. An, H. Kang, S.H. Han, M.-H. Yang, S.J. Kim, MiniROAD: Minimal RNN Framework for Online Action Detection, in: International Conference on Computer Vision, 2023, pp. 10341\u201310350.","DOI":"10.1109\/ICCV51070.2023.00949"},{"issue":"6","key":"10.1016\/j.patcog.2026.114399_b15","doi-asserted-by":"crossref","first-page":"8605","DOI":"10.1109\/TII.2024.3369671","article-title":"A novel hybrid transformer-based framework for solar irradiance forecasting under incomplete data scenarios","volume":"20","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.patcog.2026.114399_b16","doi-asserted-by":"crossref","unstructured":"X. Wang, S. Zhang, Z. Qing, Y. Shao, Z. Zuo, C. Gao, N. Sang, OadTR: Online Action Detection with Transformers, in: International Conference on Computer Vision, 2021, pp. 7565\u20137575.","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"10.1016\/j.patcog.2026.114399_b17","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume":"34","author":"Xu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114399_b18","doi-asserted-by":"crossref","unstructured":"Y. Zhao, P. Kr\u00e4henb\u00fchl, Real-Time Online Video Detection with Temporal Smoothing Transformers, in: European Conference on Computer Vision, 2022, pp. 485\u2013502.","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"10.1016\/j.patcog.2026.114399_b19","doi-asserted-by":"crossref","unstructured":"J. Chen, G. Mittal, Y. Yu, Y. Kong, M. Chen, GateHUB: Gated History Unit with Background Suppression for Online Action Detection, in: Computer Vision and Pattern Recognition, 2022, pp. 19925\u201319934.","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"10.1016\/j.patcog.2026.114399_b20","doi-asserted-by":"crossref","unstructured":"J. Wang, G. Chen, Y. Huang, L. Wang, T. Lu, Memory-and-Anticipation Transformer for Online Action Understanding, in: International Conference on Computer Vision, 2023, pp. 13824\u201313835.","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"10.1016\/j.patcog.2026.114399_b21","doi-asserted-by":"crossref","unstructured":"S. Cao, W. Luo, B. Wang, W. Zhang, L. Ma, E2E-LOAD: End-to-End Long-form Online Action Detection, in: International Conference on Computer Vision, 2023, pp. 10422\u201310432.","DOI":"10.1109\/ICCV51070.2023.00956"},{"key":"10.1016\/j.patcog.2026.114399_b22","doi-asserted-by":"crossref","unstructured":"Z. Pang, F. Sener, A. Yao, Context-Enhanced Memory-Refined Transformer for Online Action Detection, in: Computer Vision and Pattern Recognition, 2025, pp. 8700\u20138710.","DOI":"10.1109\/CVPR52734.2025.00813"},{"key":"10.1016\/j.patcog.2026.114399_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111773","article-title":"Long and short-term collaborative decision-making transformer for online action detection and anticipation","volume":"168","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.patcog.2026.114399_b24","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1177\/10692509241308069","article-title":"Text-driven online action detection","volume":"32","author":"Benavent-Lledo","year":"2025","journal-title":"Integr. Comput.-Aided Eng."},{"key":"10.1016\/j.patcog.2026.114399_b25","first-page":"11559","article-title":"Backtrace mamba: Reviving critical temporal contexts via hierarchical memory compression for online action detection","volume":"vol. 40","author":"Yan","year":"2026"},{"key":"10.1016\/j.patcog.2026.114399_b26","doi-asserted-by":"crossref","first-page":"9700","DOI":"10.1109\/TMM.2025.3618551","article-title":"Probabilistic temporal masked attention for cross-view online action detection","volume":"27","author":"Xie","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114399_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112523","article-title":"Annealing temporal\u2013spatial contrastive learning for multi-view online action detection","volume":"304","author":"Tan","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.114399_b28","series-title":"Collaborative attention mechanism for multi-view action recognition","author":"Bai","year":"2020"},{"key":"10.1016\/j.patcog.2026.114399_b29","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1016\/j.neucom.2021.05.077","article-title":"Cross-modality online distillation for multi-view action recognition","volume":"456","author":"Xu","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114399_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2021.104357","article-title":"View knowledge transfer network for multi-view action recognition","volume":"118","author":"Liang","year":"2022","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.patcog.2026.114399_b31","first-page":"4873","article-title":"DVANet: Disentangling view and action features for multi-view action recognition","volume":"vol. 38","author":"Siddiqui","year":"2024"},{"key":"10.1016\/j.patcog.2026.114399_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111923","article-title":"Trunk-branch contrastive network with multi-view deformable aggregation for multi-view action recognition","volume":"169","author":"Yang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114399_b33","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum Contrast for Unsupervised Visual Representation Learning, in: Computer Vision and Pattern Recognition, 2020, pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10.1016\/j.patcog.2026.114399_b34","unstructured":"T. Chen, S. Kornblith, M. Norouzi, G. Hinton, A Simple Framework for Contrastive Learning of Visual Representations, in: International Conference on Machine Learning, 2020, pp. 1597\u20131607."},{"key":"10.1016\/j.patcog.2026.114399_b35","first-page":"21271","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114399_b36","doi-asserted-by":"crossref","unstructured":"X. Chen, K. He, Exploring Simple Siamese Representation Learning, in: Computer Vision and Pattern Recognition, 2021, pp. 15750\u201315758.","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"10.1016\/j.patcog.2026.114399_b37","doi-asserted-by":"crossref","unstructured":"R. Qian, T. Meng, B. Gong, M.-H. Yang, H. Wang, S. Belongie, Y. Cui, Spatiotemporal Contrastive Video Representation Learning, in: Computer Vision and Pattern Recognition, 2021, pp. 6964\u20136974.","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"10.1016\/j.patcog.2026.114399_b38","doi-asserted-by":"crossref","unstructured":"J. Park, J. Lee, I.-J. Kim, K. Sohn, Probabilistic Representations for Video Contrastive Learning, in: Computer Vision and Pattern Recognition, 2022, pp. 14711\u201314721.","DOI":"10.1109\/CVPR52688.2022.01430"},{"key":"10.1016\/j.patcog.2026.114399_b39","doi-asserted-by":"crossref","unstructured":"M. Abdelfattah, M. Hassan, A. Alahi, MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning, in: Computer Vision and Pattern Recognition, 2024, pp. 18678\u201318687.","DOI":"10.1109\/CVPR52733.2024.01767"},{"key":"10.1016\/j.patcog.2026.114399_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129694","article-title":"STCLR: Sparse temporal contrastive learning for video representation","volume":"630","author":"Altabrawee","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114399_b41","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollar, Focal Loss for Dense Object Detection, in: International Conference on Computer Vision, 2017, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.patcog.2026.114399_b42","doi-asserted-by":"crossref","unstructured":"Y. Ben-Shabat, X. Yu, F. Saleh, D. Campbell, C. Rodriguez-Opazo, H. Li, S. Gould, The IKEA ASM Dataset: Understanding People Assembling Furniture Through Actions, Objects and Pose, in: Winter Conference on Applications of Computer Vision, 2021, pp. 847\u2013859.","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"10.1016\/j.patcog.2026.114399_b43","doi-asserted-by":"crossref","unstructured":"G. Vaquette, A. Orcesi, L. Lucat, C. Achard, The DAily Home LIfe Activity Dataset: A High Semantic Activity Dataset for Online Recognition, in: Automatic Face & Gesture Recognition, 2017, pp. 497\u2013504.","DOI":"10.1109\/FG.2017.67"},{"key":"10.1016\/j.patcog.2026.114399_b44","doi-asserted-by":"crossref","unstructured":"H. Kuehne, A. Arslan, T. Serre, The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities, in: Computer Vision and Pattern Recognition, 2014, pp. 780\u2013787.","DOI":"10.1109\/CVPR.2014.105"},{"key":"10.1016\/j.patcog.2026.114399_b45","doi-asserted-by":"crossref","unstructured":"L. Wang, Y. Xiong, Z. Wang, Y. Qiao, D. Lin, X. Tang, L. Van Gool, Temporal Segment Networks: Towards Good Practices for Deep Action Recognition, in: European Conference on Computer Vision, 2016, pp. 20\u201336.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"10.1016\/j.patcog.2026.114399_b46","doi-asserted-by":"crossref","unstructured":"J. Carreira, A. Zisserman, Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset, in: Computer Vision and Pattern Recognition, 2017, pp. 6299\u20136308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.patcog.2026.114399_b47","series-title":"OpenMMLab\u2019s next generation video understanding toolbox and benchmark","author":"MMAction2 Contributors","year":"2020"},{"key":"10.1016\/j.patcog.2026.114399_b48","unstructured":"I. Loshchilov, F. Hutter, Decoupled Weight Decay Regularization, in: International Conference on Learning Representations, 2019."},{"key":"10.1016\/j.patcog.2026.114399_b49","unstructured":"T. Dao, A. Gu, Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality, in: International Conference on Machine Learning, 2024."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013646?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013646?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T06:24:05Z","timestamp":1783923845000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326013646"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":49,"alternative-id":["S0031320326013646"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114399","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Feature-constrained consistency learning for multi-view online action detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114399","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":"114399"}}