{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T22:22:38Z","timestamp":1751840558137,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s00521-023-08380-9","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T12:03:12Z","timestamp":1677672192000},"page":"12481-12493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Sign language recognition via dimensional global\u2013local shift and cross-scale aggregation"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8917-1102","authenticated-orcid":false,"given":"Zihui","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghong","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,1]]},"reference":[{"issue":"12","key":"8380_CR1","doi-asserted-by":"publisher","first-page":"7957","DOI":"10.1007\/s00521-019-04691-y","volume":"32","author":"A Wadhawan","year":"2020","unstructured":"Wadhawan A, Kumar P (2020) Deep learning-based sign language recognition system for static signs. Neural Comput Appl 32(12):7957\u20137968","journal-title":"Neural Comput Appl"},{"issue":"16","key":"8380_CR2","doi-asserted-by":"publisher","first-page":"10449","DOI":"10.1007\/s00521-021-05802-4","volume":"33","author":"TM Rezende","year":"2021","unstructured":"Rezende TM, Almeida SGM, Guimar\u00e3es FG (2021) Development and validation of a Brazilian sign language database for human gesture recognition. Neural Comput Appl 33(16):10449\u201310467","journal-title":"Neural Comput Appl"},{"key":"8380_CR3","first-page":"1","volume":"34","author":"S G\u00fcney","year":"2021","unstructured":"G\u00fcney S, Erku\u015f M (2021) A real-time approach to recognition of Turkish sign language by using convolutional neural networks. Neural Comput Appl 34:1\u201311","journal-title":"Neural Comput Appl"},{"key":"8380_CR4","doi-asserted-by":"crossref","unstructured":"Wang H, Wang P, Song Z, Li W (2017) Large-scale multimodal gesture segmentation and recognition based on convolutional neural networks. In: Proceedings of the IEEE international conference on computer vision workshops, pp 3138\u20133146","DOI":"10.1109\/ICCVW.2017.371"},{"key":"8380_CR5","doi-asserted-by":"crossref","unstructured":"Wang P, Li W, Liu S, Gao Z, Tang C, Ogunbona P (2016) Large-scale isolated gesture recognition using convolutional neural networks. In: 2016 23rd international conference on pattern recognition (ICPR). IEEE, pp 7\u201312","DOI":"10.1109\/ICPR.2016.7899599"},{"key":"8380_CR6","doi-asserted-by":"crossref","unstructured":"Jiang S, Sun B, Wang L, Bai Y, Li K, Fu Y (2021) Skeleton aware multi-modal sign language recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3413\u20133423","DOI":"10.1109\/CVPRW53098.2021.00380"},{"key":"8380_CR7","doi-asserted-by":"crossref","unstructured":"Maruyama M, Ghose S, Inoue K, Roy PP, Iwamura M, Yoshioka M (2021) Word-level sign language recognition with multi-stream neural networks focusing on local regions. arXiv preprint arXiv:2106.15989","DOI":"10.2139\/ssrn.4263878"},{"key":"8380_CR8","doi-asserted-by":"crossref","unstructured":"Hosain AA, Santhalingam PS, Pathak P, Rangwala H, Kosecka J (2021) Hand pose guided 3d pooling for word-level sign language recognition. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 3429\u20133439","DOI":"10.1109\/WACV48630.2021.00347"},{"issue":"3","key":"8380_CR9","first-page":"1","volume":"17","author":"H Hezhen","year":"2021","unstructured":"Hezhen H, Zhou W, Junfu P, Li H (2021) Global-local enhancement network for NMF-aware sign language recognition. ACM Trans Multimed Comput Commun Appl TOMM 17(3):1\u201319","journal-title":"ACM Trans Multimed Comput Commun Appl TOMM"},{"key":"8380_CR10","doi-asserted-by":"crossref","unstructured":"Li D, Rodriguez C, Yu X, Li H (2020) Word-level deep sign language recognition from video: a new large-scale dataset and methods comparison. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1459\u20131469","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"8380_CR11","doi-asserted-by":"crossref","unstructured":"Sridhar A, Ganesan RG, Kumar P, Khapra M (2020) Include: a large scale dataset for Indian sign language recognition. In: Proceedings of the 28th ACM international conference on multimedia, pp 1366\u20131375","DOI":"10.1145\/3394171.3413528"},{"key":"8380_CR12","unstructured":"Ronchetti F, Quiroga F, Estrebou CA, Lanzarini LC, Rosete A (2016) Lsa64: an Argentinian sign language dataset. In: XXII congreso argentino de ciencias de la computaci\u00f3n (CACIC) (2016)"},{"issue":"6","key":"8380_CR13","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1007\/s00371-019-01725-3","volume":"36","author":"J Imran","year":"2020","unstructured":"Imran J, Raman B (2020) Deep motion templates and extreme learning machine for sign language recognition. Vis Comput 36(6):1233\u20131246","journal-title":"Vis Comput"},{"key":"8380_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115601","volume":"185","author":"A Venugopalan","year":"2021","unstructured":"Venugopalan A, Reghunadhan R (2021) Applying deep neural networks for the automatic recognition of sign language words: a communication aid to deaf agriculturists. Expert Syst Appl 185:115601","journal-title":"Expert Syst Appl"},{"key":"8380_CR15","doi-asserted-by":"crossref","unstructured":"Li D, Yu X, Xu C, Petersson L, Li H (2020) Transferring cross-domain knowledge for video sign language recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6205\u20136214","DOI":"10.1109\/CVPR42600.2020.00624"},{"issue":"4","key":"8380_CR16","doi-asserted-by":"publisher","first-page":"91","DOI":"10.3390\/fi11040091","volume":"11","author":"X Zhang","year":"2019","unstructured":"Zhang X, Li X (2019) Dynamic gesture recognition based on MEMP network. Future Internet 11(4):91","journal-title":"Future Internet"},{"issue":"3","key":"8380_CR17","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1007\/s00521-021-06467-9","volume":"34","author":"F Wang","year":"2022","unstructured":"Wang F, Yuxuan D, Wang G, Zeng Z, Zhao L (2022) (2+ 1) D-SLR: an efficient network for video sign language recognition. Neural Comput Appl 34(3):2413\u20132423","journal-title":"Neural Comput Appl"},{"key":"8380_CR18","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"8380_CR19","unstructured":"Joze HRV, Koller O (2018) Ms-asl: A large-scale data set and benchmark for understanding American sign language. arXiv preprint arXiv:1812.01053"},{"key":"8380_CR20","doi-asserted-by":"crossref","unstructured":"Zhou Z, Lui K-S, Tam VWL, Lam EY (2021) Applying (3+ 2+ 1) D residual neural network with frame selection for Hong Kong sign language recognition. In: 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 4296\u20134302","DOI":"10.1109\/ICPR48806.2021.9412075"},{"key":"8380_CR21","doi-asserted-by":"crossref","unstructured":"Tunga A, Nuthalapati SV, Wachs J (2021) Pose-based sign language recognition using GCN and BERT. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 31\u201340","DOI":"10.1109\/WACVW52041.2021.00008"},{"key":"8380_CR22","doi-asserted-by":"crossref","unstructured":"Boh\u00e1\u010dek M, Hr\u00faz M (2022) Sign pose-based transformer for word-level sign language recognition. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 182\u2013191","DOI":"10.1109\/WACVW54805.2022.00024"},{"key":"8380_CR23","doi-asserted-by":"publisher","first-page":"1594","DOI":"10.1109\/TCDS.2021.3126637","volume":"14","author":"C Li","year":"2021","unstructured":"Li C, Li S, Gao Y, Zhang X, Li W (2021) A two-stream neural network for pose-based hand gesture recognition. IEEE Trans Cogn Dev Syst 14:1594\u20131603","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"8380_CR24","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"8380_CR25","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, vol 30"},{"key":"8380_CR26","doi-asserted-by":"crossref","unstructured":"Konstantinidis D, Dimitropoulos K, Daras P (2018) A deep learning approach for analyzing video and skeletal features in sign language recognition. In: 2018 IEEE international conference on imaging systems and techniques (IST). IEEE, pp 1\u20136","DOI":"10.1109\/IST.2018.8577085"},{"key":"8380_CR27","doi-asserted-by":"crossref","unstructured":"Konstantinidis D, Dimitropoulos K, Daras P (2018) Sign language recognition based on hand and body skeletal data. In: 2018-3DTV-conference: the true vision-capture, transmission and display of 3D video (3DTV-CON). IEEE, pp 1\u20134","DOI":"10.1109\/3DTV.2018.8478467"},{"key":"8380_CR28","doi-asserted-by":"crossref","unstructured":"Hezhen H, Zhou W, Li H (2021) Hand-model-aware sign language recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 1558\u20131566","DOI":"10.1609\/aaai.v35i2.16247"},{"key":"8380_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103280","volume":"80","author":"S Zhang","year":"2021","unstructured":"Zhang S, Zhang Q (2021) Sign language recognition based on global\u2013local attention. J Vis Commun Image Represent 80:103280","journal-title":"J Vis Commun Image Represent"},{"key":"8380_CR30","doi-asserted-by":"crossref","unstructured":"Moryossef A, Tsochantaridis I, Dinn J, Camgoz NC, Bowden R, Jiang T, Rios A, Muller M, Ebling S (2021) Evaluating the immediate applicability of pose estimation for sign language recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3434\u20133440","DOI":"10.1109\/CVPRW53098.2021.00382"},{"key":"8380_CR31","doi-asserted-by":"crossref","unstructured":"V\u00e1zquez-Enr\u00edquez M, Alba-Castro JL, Doc\u00edo-Fern\u00e1ndez L, Rodr\u00edguez-Banga E (2021) Isolated sign language recognition with multi-scale spatial-temporal graph convolutional networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3462\u20133471","DOI":"10.1109\/CVPRW53098.2021.00385"},{"key":"8380_CR32","doi-asserted-by":"crossref","unstructured":"Hu H, Zhao W, Zhou W, Wang Y, Li H (2021) Signbert: pre-training of hand-model-aware representation for sign language recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 11087\u201311096","DOI":"10.1109\/ICCV48922.2021.01090"},{"key":"8380_CR33","doi-asserted-by":"crossref","unstructured":"De Coster M, Van Herreweghe M, Dambre J (2021) Isolated sign recognition from RGB video using pose flow and self-attention. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3441\u20133450","DOI":"10.1109\/CVPRW53098.2021.00383"},{"key":"8380_CR34","doi-asserted-by":"crossref","unstructured":"Xiao S, Fang Y, Ni L (2021) Multi-modal sign language recognition with enhanced spatiotemporal representation. In: 2021 International joint conference on neural networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN52387.2021.9533707"},{"key":"8380_CR35","doi-asserted-by":"crossref","unstructured":"Wu B, Wan A, Yue X, Jin P, Zhao S, Golmant N, Gholaminejad A, Gonzalez J, Keutzer K (2018) Shift: a zero flop, zero parameter alternative to spatial convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9127\u20139135","DOI":"10.1109\/CVPR.2018.00951"},{"key":"8380_CR36","unstructured":"Jeon Y, Kim J (2018) Constructing fast network through deconstruction of convolution. arXiv preprint arXiv:1806.07370"},{"issue":"7","key":"8380_CR37","doi-asserted-by":"publisher","first-page":"5938","DOI":"10.1109\/TGRS.2020.3024730","volume":"59","author":"ME Paoletti","year":"2020","unstructured":"Paoletti ME, Haut JM, Tao X, Plaza J, Plaza A (2020) Flop-reduction through memory allocations within CNN for hyperspectral image classification. IEEE Trans Geosci Remote Sens 59(7):5938\u20135952","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"8380_CR38","doi-asserted-by":"crossref","unstructured":"Yang J, He Y, Huang X, Xu J, Ye X, Tao G, Ni B (2020) Alignshift: bridging the gap of imaging thickness in 3D anisotropic volumes. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 562\u2013572","DOI":"10.1007\/978-3-030-59719-1_55"},{"key":"8380_CR39","doi-asserted-by":"crossref","unstructured":"Brown A, Mettes P, Worring M (2019) 4-Connected shift residual networks. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops","DOI":"10.1109\/ICCVW.2019.00248"},{"key":"8380_CR40","doi-asserted-by":"crossref","unstructured":"Lin J, Gan C, Han S (2019) Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7083\u20137093","DOI":"10.1109\/ICCV.2019.00718"},{"key":"8380_CR41","doi-asserted-by":"crossref","unstructured":"Sudhakaran S, Escalera S, Lanz O (2020) Gate-shift networks for video action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1102\u20131111","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"8380_CR42","doi-asserted-by":"crossref","unstructured":"Chen W, Xie D, Zhang Y, Pu S (2019) All you need is a few shifts: designing efficient convolutional neural networks for image classification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7241\u20137250","DOI":"10.1109\/CVPR.2019.00741"},{"key":"8380_CR43","unstructured":"Jeon Y, Kim J (2018) Constructing fast network through deconstruction of convolution. In: Advances in neural information processing systems, vol 31"},{"key":"8380_CR44","doi-asserted-by":"crossref","unstructured":"Li Y, Song S, Li Y, Liu J (2019) Temporal bilinear networks for video action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 8674\u20138681","DOI":"10.1609\/aaai.v33i01.33018674"},{"key":"8380_CR45","doi-asserted-by":"crossref","unstructured":"Cheng K, Zhang Y, He X, Chen W, Cheng J, Lu H (2020) Skeleton-based action recognition with shift graph convolutional network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 183\u2013192","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"8380_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108419","volume":"117","author":"M Li","year":"2022","unstructured":"Li M, Zhou G, Cai W, Li J, Li M, He M, Yahui H, Li L (2022) Multi-scale sparse network with cross-attention mechanism for image-based butterflies fine-grained classification. Appl Soft Comput 117:108419","journal-title":"Appl Soft Comput"},{"key":"8380_CR47","first-page":"1","volume":"60","author":"R Shang","year":"2022","unstructured":"Shang R, Chang H, Zhang W, Feng J, Li Y, Jiao L (2022) Hyperspectral image classification based on multiscale cross-branch response and second-order channel attention. IEEE Trans Geosci Remote Sens 60:1\u201316","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"8380_CR48","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2021.3131615","author":"J-Y Yang","year":"2022","unstructured":"Yang J-Y, Li H-C, Hu W-S, Pan L, Du Q (2022) Adaptive cross-attention-driven spatial-spectral graph convolutional network for hyperspectral image classification. IEEE Geosci Remote Sens Lett. https:\/\/doi.org\/10.1109\/lgrs.2021.3131615","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"8380_CR49","doi-asserted-by":"crossref","unstructured":"Praveen RG, de Melo WC, Ullah N, Aslam H, Zeeshan O, Denorme T, Pedersoli M, Koerich AL, Bacon S, Cardinal P et al (2022) A joint cross-attention model for audio-visual fusion in dimensional emotion recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2486\u20132495","DOI":"10.1109\/CVPRW56347.2022.00278"},{"issue":"7","key":"8380_CR50","doi-asserted-by":"publisher","first-page":"5397","DOI":"10.1007\/s00521-021-06696-y","volume":"34","author":"W Jiagao","year":"2022","unstructured":"Jiagao W, Weng W, Junxia F, Liu L, Bin H (2022) Deep semantic hashing with dual attention for cross-modal retrieval. Neural Comput Appl 34(7):5397\u20135416","journal-title":"Neural Comput Appl"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08380-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08380-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08380-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T17:32:45Z","timestamp":1683826365000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08380-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":50,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["8380"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08380-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2023,3,1]]},"assertion":[{"value":"4 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2023","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}