{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:17:23Z","timestamp":1783351043810,"version":"3.54.6"},"reference-count":40,"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"}],"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.2026.114395","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:45:06Z","timestamp":1783061106000},"page":"114395","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Multi-scale spatiotemporal modeling with dual-branch fusion for dynamic gesture recognition"],"prefix":"10.1016","volume":"180","author":[{"given":"Jing","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songtao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8002-0241","authenticated-orcid":false,"given":"Mingzhou","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maogen","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.patcog.2026.114395_b1","doi-asserted-by":"crossref","first-page":"8818","DOI":"10.1109\/TII.2022.3152214","article-title":"Real-time gesture recognition in the view of repeating characteristics of sign languages","volume":"18","author":"Lee","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.patcog.2026.114395_b2","article-title":"Hand gesture recognition with focus on leap motion: An overview, real world challenges and future directions","volume":"226","author":"Bhiri","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114395_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107288","article-title":"Lightweight hybrid model based on MobileNet-v2 and vision transformer for human\u2013robot interaction","volume":"127","author":"Cheng","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"10","key":"10.1016\/j.patcog.2026.114395_b4","doi-asserted-by":"crossref","first-page":"14031","DOI":"10.1109\/TITS.2024.3394911","article-title":"MG-GCT: A motion-guided graph convolutional transformer for traffic gesture recognition","volume":"25","author":"Guo","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patcog.2026.114395_b5","doi-asserted-by":"crossref","unstructured":"D. Tran, L. Bourdev, R. Fergus, L. Torresani, M. Paluri, Learning spatiotemporal features with 3d convolutional networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 4489\u20134497.","DOI":"10.1109\/ICCV.2015.510"},{"key":"10.1016\/j.patcog.2026.114395_b6","doi-asserted-by":"crossref","unstructured":"Z. Liu, J. Ning, Y. Cao, Y. Wei, Z. Zhang, S. Lin, H. Hu, Video swin transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 3202\u20133211.","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"10.1016\/j.patcog.2026.114395_b7","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114395_b8","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1016\/j.future.2021.06.045","article-title":"Human action recognition using attention based LSTM network with dilated CNN features","volume":"125","author":"Muhammad","year":"2021","journal-title":"Future Gener. Comput. Syst."},{"issue":"12","key":"10.1016\/j.patcog.2026.114395_b9","doi-asserted-by":"crossref","first-page":"10968","DOI":"10.1002\/int.23029","article-title":"Human-centered attention-aware networks for action recognition","volume":"37","author":"Liu","year":"2022","journal-title":"Int. J. Intell. Syst."},{"key":"10.1016\/j.patcog.2026.114395_b10","doi-asserted-by":"crossref","unstructured":"A. Arnab, M. Dehghani, G. Heigold, C. Sun, M. Lu\u010di\u0107, C. Schmid, Vivit: A video vision transformer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 6836\u20136846.","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"10.1016\/j.patcog.2026.114395_b11","doi-asserted-by":"crossref","first-page":"4989","DOI":"10.1109\/TIP.2023.3308750","article-title":"B2c-afm: Bi-directional co-temporal and cross-spatial attention fusion model for human action recognition","volume":"32","author":"Guo","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"10.1016\/j.patcog.2026.114395_b12","doi-asserted-by":"crossref","first-page":"11035","DOI":"10.1109\/TNNLS.2023.3247103","article-title":"Spatiotemporal decouple-and-squeeze contrastive learning for semisupervised skeleton-based action recognition","volume":"35","author":"Xu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"7","key":"10.1016\/j.patcog.2026.114395_b13","first-page":"1","article-title":"Attention-based deep learning framework for action recognition in a dark environment","volume":"14","author":"Munsif","year":"2024","journal-title":"Hum. Centric Comput. Inf. Sci"},{"key":"10.1016\/j.patcog.2026.114395_b14","series-title":"2021 17th International Conference on Computational Intelligence and Security","first-page":"217","article-title":"Gesture recognition algorithm based on lightweight 3DCNN network","author":"Zhang","year":"2021"},{"key":"10.1016\/j.patcog.2026.114395_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2023.102388","article-title":"DeReFNet: Dual-stream dense residual fusion network for static hand gesture recognition","volume":"77","author":"Sahoo","year":"2023","journal-title":"Displays"},{"key":"10.1016\/j.patcog.2026.114395_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109901","article-title":"Mask-guided multiscale feature aggregation network for hand gesture recognition","volume":"145","author":"Liang","year":"2024","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.patcog.2026.114395_b17","doi-asserted-by":"crossref","first-page":"3076","DOI":"10.1109\/LRA.2024.3362144","article-title":"Fgdsnet: A lightweight hand gesture recognition network for human robot interaction","volume":"9","author":"Zhou","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"12","key":"10.1016\/j.patcog.2026.114395_b18","doi-asserted-by":"crossref","first-page":"12844","DOI":"10.1109\/LRA.2025.3625493","article-title":"DSTE-net: Dual-scale spatial-temporal excitation network for dynamic gesture recognition","volume":"10","author":"Tang","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"5","key":"10.1016\/j.patcog.2026.114395_b19","doi-asserted-by":"crossref","first-page":"981","DOI":"10.3390\/electronics14050981","article-title":"Mnv3-mfae: A lightweight network for video action recognition","volume":"14","author":"Liu","year":"2025","journal-title":"Electronics"},{"issue":"1","key":"10.1016\/j.patcog.2026.114395_b20","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/JAS.2020.1003465","article-title":"Dynamic hand gesture recognition based on short-term sampling neural networks","volume":"8","author":"Zhang","year":"2021","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.patcog.2026.114395_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114499","article-title":"Selective spatiotemporal features learning for dynamic gesture recognition","volume":"169","author":"Tang","year":"2021","journal-title":"Expert Syst. Appl."},{"issue":"4","key":"10.1016\/j.patcog.2026.114395_b22","doi-asserted-by":"crossref","first-page":"5315","DOI":"10.1109\/JSYST.2023.3306380","article-title":"Temporal segment neural networks-enabled dynamic hand-gesture recognition for industrial cyber-physical authentication systems","volume":"17","author":"Cao","year":"2023","journal-title":"IEEE Syst. J."},{"key":"10.1016\/j.patcog.2026.114395_b23","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.neucom.2022.12.022","article-title":"Improving dynamic gesture recognition in untrimmed videos by an online lightweight framework and a new gesture dataset zjugesture","volume":"523","author":"Xu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114395_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110536","article-title":"Decoupled and boosted learning for skeleton-based dynamic hand gesture recognition","volume":"153","author":"Li","year":"2024","journal-title":"Pattern Recognit."},{"issue":"2","key":"10.1016\/j.patcog.2026.114395_b25","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.1007\/s40747-022-00858-8","article-title":"Parallel temporal feature selection based on improved attention mechanism for dynamic gesture recognition","volume":"9","author":"Chen","year":"2023","journal-title":"Complex & Intell. Syst."},{"key":"10.1016\/j.patcog.2026.114395_b26","doi-asserted-by":"crossref","unstructured":"O. Kopuklu, N. Kose, A. Gunduz, G. Rigoll, Resource efficient 3d convolutional neural networks, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019.","DOI":"10.1109\/ICCVW.2019.00240"},{"key":"10.1016\/j.patcog.2026.114395_b27","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Self-attention convlstm for spatiotemporal prediction","author":"Zhihui Lin","year":"2020"},{"key":"10.1016\/j.patcog.2026.114395_b28","doi-asserted-by":"crossref","unstructured":"J. Materzynska, G. Berger, I. Bax, R. Memisevic, The jester dataset: A large-scale video dataset of human gestures, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019.","DOI":"10.1109\/ICCVW.2019.00349"},{"issue":"5","key":"10.1016\/j.patcog.2026.114395_b29","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1109\/TMM.2018.2808769","article-title":"EgoGesture: A new dataset and benchmark for egocentric hand gesture recognition","volume":"20","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114395_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111767","article-title":"ST-cgnet: A spatiotemporal gesture recognition network with triplet attention and dual feature fusion","author":"Hu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114395_b31","doi-asserted-by":"crossref","first-page":"5626","DOI":"10.1109\/TIP.2021.3087348","article-title":"Searching multi-rate and multi-modal temporal enhanced networks for gesture recognition","volume":"30","author":"Yu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114395_b32","doi-asserted-by":"crossref","unstructured":"J. Yang, X. Dong, L. Liu, C. Zhang, J. Shen, D. Yu, Recurring the transformer for video action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14063\u201314073.","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"10.1016\/j.patcog.2026.114395_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2021.103318","article-title":"Dissected 3d cnns: Temporal skip connections for efficient online video processing","volume":"215","author":"K\u00f6p\u00fckl\u00fc","year":"2022","journal-title":"Comput. Vis. Image Underst."},{"issue":"4","key":"10.1016\/j.patcog.2026.114395_b34","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1109\/THMS.2022.3144000","article-title":"Sign language recognition based on r (2+ 1) d with spatial\u2013temporal\u2013channel attention","volume":"52","author":"Han","year":"2022","journal-title":"IEEE Trans. Human-Machine Syst."},{"key":"10.1016\/j.patcog.2026.114395_b35","series-title":"Chinese Conference on Pattern Recognition and Computer Vision","first-page":"469","article-title":"Attention-based spatio-temporal modeling with 3D convolutional neural networks for dynamic gesture recognition","author":"Hu","year":"2024"},{"issue":"2","key":"10.1016\/j.patcog.2026.114395_b36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3561822","article-title":"Realtime recognition of dynamic hand gestures in practical applications","volume":"20","author":"Xiao","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"issue":"3","key":"10.1016\/j.patcog.2026.114395_b37","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s40747-024-01774-9","article-title":"Manet: motion-aware network for video action recognition","volume":"11","author":"Li","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.patcog.2026.114395_b38","article-title":"Multi-objective neural architecture search combining binary artificial bee colony algorithm for dynamic hand gesture recognition","author":"Ye","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114395_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108442","article-title":"XAI-deepnet: a novel interpretable deep learning framework for dynamic hand gesture recognition","volume":"112","author":"Karthikeyan","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.patcog.2026.114395_b40","doi-asserted-by":"crossref","DOI":"10.1145\/3797044","article-title":"MDRA: A motion-guided dual-stream recurrent attention framework for dynamic hand gesture recognition","author":"Liao","year":"2026","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013609?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013609?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T14:40:53Z","timestamp":1783348853000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326013609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":40,"alternative-id":["S0031320326013609"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114395","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":"Multi-scale spatiotemporal modeling with dual-branch fusion for dynamic gesture recognition","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114395","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":"114395"}}