{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T16:33:55Z","timestamp":1767026035969,"version":"3.48.0"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"DOI":"10.1007\/s44163-025-00653-7","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T16:30:28Z","timestamp":1767025828000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Gesture recognition method integrating multimodal inter-frame motion and shared attention weights"],"prefix":"10.1007","volume":"5","author":[{"given":"Qiyuan","family":"Lu","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,29]]},"reference":[{"key":"653_CR1","doi-asserted-by":"publisher","first-page":"103268","DOI":"10.1016\/j.inffus.2025.103268","volume":"123","author":"X Zhu","year":"2025","unstructured":"Zhu X, Wang Y, Cambria E, Zhu X, Rida I. RMER-DT: Robust multimodal emotion recognition in conversational contexts based on diffusion and transformers. Inf Fusion. 2025;123:103268.","journal-title":"Inf Fusion"},{"key":"653_CR2","doi-asserted-by":"publisher","first-page":"1004445","DOI":"10.1016\/j.array.2025.100445","volume":"27","author":"R Wang","year":"2025","unstructured":"Wang R, Xu D, Cascone L, Wang Y, Chen H, Zheng J, et al. RAFT: robust adversarial fusion transformer for multimodal sentiment analysis. Array. 2025;27:1004445.","journal-title":"Array"},{"issue":"May","key":"653_CR3","first-page":"11","volume":"158","author":"M Gao","year":"2025","unstructured":"Gao M, Sun J, Li Q, Khan MA, Shagn J, Zhu X, et al. Towards trustworthy image super-resolution via symmetrical and recursive artificial neural network. Image Vis Comput. 2025;158(May):11\u2013110.","journal-title":"Image Vis Comput"},{"key":"653_CR4","doi-asserted-by":"crossref","unstructured":"Cheng L, Zhang H, Di B, Niyato D, Song L. Large language models empower multimodal integrated sensing and communication. IEEE Commun Mag. 2025;63(5):190-7.","DOI":"10.1109\/MCOM.004.2400281"},{"issue":"3","key":"653_CR5","doi-asserted-by":"publisher","first-page":"2285","DOI":"10.1109\/TIV.2022.3221767","volume":"8","author":"R Song","year":"2022","unstructured":"Song R, Ai Y, Tian B, Chen L, Zhu F. Msfanet: a light weight object detector based on context aggregation and attention mechanism for autonomous mining truck. IEEE Trans Intell Veh. 2022;8(3):2285\u201395.","journal-title":"IEEE Trans Intell Veh"},{"issue":"1","key":"653_CR6","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.neucom.2022.12.022","volume":"523","author":"C Xu","year":"2023","unstructured":"Xu C, Wu X, Wang M, Qiu F, Liu Y. Improving dynamic gesture recognition in untrimmed videos by an online lightweight framework and a new gesture dataset ZJUGesture. Neurocomputing. 2023;523(1):58\u201368.","journal-title":"Neurocomputing"},{"issue":"2","key":"653_CR7","first-page":"749","volume":"17","author":"Y Srinivas","year":"2025","unstructured":"Srinivas Y, Ganivada A. A modified inter-frame difference method for detection of moving objects in videos. Int J Inf Technol. 2025;17(2):749\u201354.","journal-title":"Int J Inf Technol"},{"issue":"3","key":"653_CR8","doi-asserted-by":"publisher","first-page":"1647","DOI":"10.1007\/s12652-021-03386-4","volume":"14","author":"JL Zhong","year":"2023","unstructured":"Zhong JL, Gan YF, Yang JX. A fast forgery frame detection method for video copy-move inter\/intra-frame identification. J Ambient Intell Humaniz Comput. 2023;14(3):1647\u201358.","journal-title":"J Ambient Intell Humaniz Comput"},{"issue":"2","key":"653_CR9","doi-asserted-by":"publisher","first-page":"2718","DOI":"10.1007\/s11227-023-05580-x","volume":"80","author":"PG Arepalli","year":"2024","unstructured":"Arepalli PG, Naik KJ. A deep learning-enabled IoT framework for early hypoxia detection in aqua water using light weight spatially shared attention-LSTM network. J Supercomput. 2024;80(2):2718\u201347.","journal-title":"J Supercomput"},{"issue":"8","key":"653_CR10","doi-asserted-by":"publisher","first-page":"82456","DOI":"10.1109\/ACCESS.2022.3196381","volume":"10","author":"MAR Suleman","year":"2022","unstructured":"Suleman MAR, Shridevi S. Short-term weather forecasting using spatial feature attention based LSTM model. IEEE Access. 2022;10(8):82456\u201368.","journal-title":"IEEE Access"},{"issue":"4","key":"653_CR11","doi-asserted-by":"publisher","first-page":"1991","DOI":"10.1109\/JBHI.2023.3241439","volume":"27","author":"Q Zhou","year":"2023","unstructured":"Zhou Q, Huang Z, Ding M, et al. Medical image classification using light-weight CNN with spiking cortical model based attention module. IEEE J Biomed Health Inform. 2023;27(4):1991\u20132002.","journal-title":"IEEE J Biomed Health Inform"},{"issue":"5","key":"653_CR12","doi-asserted-by":"publisher","first-page":"87135","DOI":"10.1109\/ACCESS.2022.3199358","volume":"10","author":"JJ Ojeda-Castelo","year":"2022","unstructured":"Ojeda-Castelo JJ, Capobianco-Uriarte MLM, Piedra-Fernandez JA, Ayala R. A survey on intelligent gesture recognition techniques. IEEE Access. 2022;10(5):87135\u201356.","journal-title":"IEEE Access"},{"issue":"6","key":"653_CR13","doi-asserted-by":"publisher","first-page":"153","DOI":"10.3390\/jimaging8060153","volume":"8","author":"F Al Farid","year":"2022","unstructured":"Al Farid F, Hashim N, Abdullah J, Bhuiyan MR, Shahida Mohd Isa WN. A structured and methodological review on vision-based hand gesture recognition system. J Imag. 2022;8(6):153\u201372.","journal-title":"J Imag"},{"issue":"2","key":"653_CR14","doi-asserted-by":"publisher","first-page":"2741","DOI":"10.1109\/JIOT.2023.3293092","volume":"11","author":"B Jin","year":"2023","unstructured":"Jin B, Ma X, Zhang Z, Lian Z, Wang B. Interference-robust millimeter-wave radar-based dynamic hand gesture recognition using 2-D CNN-transformer networks. IEEE Internet Things J. 2023;11(2):2741\u201352.","journal-title":"IEEE Internet Things J"},{"issue":"4","key":"653_CR15","doi-asserted-by":"publisher","first-page":"1280","DOI":"10.1049\/ipr2.12712","volume":"17","author":"Y Sun","year":"2023","unstructured":"Sun Y, Weng Y, Luo B, Li G, Tao B. Gesture recognition algorithm based on multi-scale feature fusion in RGB-D images. IET Image Process. 2023;17(4):1280\u201390.","journal-title":"IET Image Process"},{"key":"653_CR16","doi-asserted-by":"publisher","first-page":"105582","DOI":"10.1016\/j.imavis.2025.105582","volume":"160","author":"S Guo","year":"2025","unstructured":"Guo S, Li Q, Gao M, Zhu X, Rida I. Generalizable deepfake detection via spatial kernel selection and halo attention network. Image Vis Comput. 2025;160:105582.","journal-title":"Image Vis Comput"},{"issue":"1","key":"653_CR17","doi-asserted-by":"publisher","first-page":"11","DOI":"10.47852\/bonviewAAES32021220","volume":"1","author":"J Purohit","year":"2023","unstructured":"Purohit J, Dave R. Leveraging deep learning techniques to obtain efficacious segmentation results. Arch Adv Eng Sci. 2023;1(1):11\u201326.","journal-title":"Arch Adv Eng Sci"},{"issue":"3","key":"653_CR18","doi-asserted-by":"publisher","first-page":"115732","DOI":"10.1109\/ACCESS.2022.3219094","volume":"10","author":"J Santoso","year":"2022","unstructured":"Santoso J, Yamada T, Ishizuka K, Hashimoto T, Makino S. Speech emotion recognition based on self-attention weight correction for acoustic and text features. IEEE Access. 2022;10(3):115732\u201343.","journal-title":"IEEE Access"},{"issue":"4","key":"653_CR19","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1038\/s42256-023-00624-6","volume":"5","author":"Y Ektefaie","year":"2023","unstructured":"Ektefaie Y, Dasoulas G, Noori A, Farhat M, Zitnik M. Multimodal learning with graphs. Nat Mach Intell. 2023;5(4):340\u201350.","journal-title":"Nat Mach Intell"},{"issue":"6","key":"653_CR20","doi-asserted-by":"publisher","first-page":"12033","DOI":"10.48084\/etasr.6377","volume":"13","author":"R Rajamohanan","year":"2023","unstructured":"Rajamohanan R, Latha BC. An optimized YOLO v5 model for tomato leaf disease classification with field dataset. Eng Technol Appl Sci Res. 2023;13(6):12033\u20138.","journal-title":"Eng Technol Appl Sci Res"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00653-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-025-00653-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00653-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T16:30:30Z","timestamp":1767025830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-025-00653-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,29]]},"references-count":20,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["653"],"URL":"https:\/\/doi.org\/10.1007\/s44163-025-00653-7","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,29]]},"assertion":[{"value":"29 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics, consent to participate, and consent to publish"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical trial number"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"405"}}