{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T03:21:45Z","timestamp":1786591305335,"version":"build-2736575974"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T00:00:00Z","timestamp":1632960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T00:00:00Z","timestamp":1632960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s00521-021-06467-9","type":"journal-article","created":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T19:08:25Z","timestamp":1633028905000},"page":"2413-2423","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["(2+1)D-SLR: an efficient network for video sign language recognition"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8296-8039","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guorui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"6467_CR1","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1142\/S0218001400000386","volume":"14","author":"W Gao","year":"2000","unstructured":"Gao W, \u00a0Jiyong MA, Jiangqin WU (2000) Sign language recognition based on hmm\/ann\/dp. Int J Pattern Recogn Artif Intell 14(5):587-602","journal-title":"Int J Pattern Recogn Artif Intell"},{"key":"6467_CR2","unstructured":"Feris R, Turk M, Raskar R, Tan K, Ohashi G (2005) Exploiting depth discontinuities for vision-based fingerspelling recognition. In: 2004 Conference on computer vision and pattern recognition workshop"},{"issue":"3","key":"6467_CR3","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1109\/TSMCA.2004.824852","volume":"34","author":"G Fang","year":"2004","unstructured":"Fang G, \u00a0Wen G, Zhao D (2003) Large vocabulary sign language recognition based on fuzzy decision trees. IEEE rans Syst Man Cybern Part A: Syst Hum 34(3):305\u2013314.","journal-title":"IEEE rans Syst Man Cybern Part A: Syst Hum"},{"issue":"5","key":"6467_CR4","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1109\/TCYB.2013.2265337","volume":"43","author":"C Sun","year":"2013","unstructured":"Sun C, Zhang T, Bao B-K, Xu C (2013) Discriminative exemplar coding for sign language recognition with Kinect. IEEE Trans Cybern 43(5):1418\u20131428","journal-title":"IEEE Trans Cybern"},{"key":"6467_CR5","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/978-3-319-16634-6_18","volume":"9010","author":"Y Lin","year":"2014","unstructured":"Lin Y, Chai X, Yu Z, Chen X (2014) Curve matching from the view of manifold for sign language recognition. Lect Notes Comput Sci 9010:233\u2013246","journal-title":"Lect Notes Comput Sci"},{"key":"6467_CR6","volume-title":"Chalearn looking at people challenge 2014: dataset and results","author":"S Escalera","year":"2004","unstructured":"Escalera S, Bar\u00f3 X, Gonz\u00e0lez J, Bautista MA, Guyon I (2004) Chalearn looking at people challenge 2014: dataset and results. Springer, Berlin"},{"key":"6467_CR7","volume-title":"Iterative reference driven metric learning for signer independent isolated sign language recognition","author":"Y Fang","year":"2016","unstructured":"Fang Y, Chai X, Chen X (2016) Iterative reference driven metric learning for signer independent isolated sign language recognition. Springer, Berlin"},{"issue":"1","key":"6467_CR8","first-page":"1","volume":"14","author":"G Dan","year":"2017","unstructured":"Dan G, Zhou W, Li H, Meng W (2017) Online early-late fusion based on adaptive hmm for sign language recognition. ACM Trans Multimed Comput Commun Appl 14(1):1\u201318","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"6467_CR9","first-page":"1","volume":"PP","author":"J Huang","year":"2018","unstructured":"Huang J, Zhou W, Li H, Li W (2018) Attention-based 3d-cnns for large-vocabulary sign language recognition. IEEE Trans Circuits Syst Video Technol PP:1\u20131","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6467_CR10","doi-asserted-by":"crossref","unstructured":"Zhang J, Zhou W, Li H (2014) A threshold-based HMM-DTW approach for continuous sign language recognition. In: Proceedings of international conference on internet multimedia computing and service, ser. ICIMCS \u201914. Association for Computing Machinery, New York, NY, USA, pp 237\u2013240","DOI":"10.1145\/2632856.2632931"},{"key":"6467_CR11","doi-asserted-by":"crossref","unstructured":"Koller O, Zargaran S, Ney H (2017) Re-sign: Re-aligned end-to-end sequence modelling with deep recurrent CNN-HMMS. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.364"},{"key":"6467_CR12","first-page":"1","volume":"8","author":"Z Zhou","year":"2016","unstructured":"ZHENGYU, ZHOU, KEHUANG, LI, CHIN-HUI, & LEE. (2016). Sign transition modeling and a scalable solution to continuous sign language recognition for real-world applications. Acm Transactions on Accessible Computing.","journal-title":"ACM Trans Access Comput"},{"key":"6467_CR13","doi-asserted-by":"crossref","unstructured":"Huang J, Zhou W, Zhang Q, Li H, Li W (2018) Video-based sign language recognition without temporal segmentation. In: 32nd AAAI conference on artificial intelligence (AAAI-18)","DOI":"10.1609\/aaai.v32i1.11903"},{"key":"6467_CR14","doi-asserted-by":"crossref","unstructured":"Wang S, Guo D, Zhou W-G, Zha Z-J, Wang M (2018) Connectionist temporal fusion for sign language translation. In: Proceedings of the 26th ACM international conference on multimedia, pp 1483\u20131491","DOI":"10.1145\/3240508.3240671"},{"key":"6467_CR15","doi-asserted-by":"crossref","unstructured":"Pu J, Zhou W, Li H (2018) Dilated convolutional network with iterative optimization for continuous sign language recognition. In: Twenty-seventh international joint conference on artificial intelligence IJCAI-18","DOI":"10.24963\/ijcai.2018\/123"},{"key":"6467_CR16","first-page":"1","volume":"PP 7","author":"R Cui","year":"2019","unstructured":"Cui R, Liu H, Zhang C (2019) A deep neural framework for continuous sign language recognition by iterative training. IEEE Trans Multimedia PP 7:1\u20131","journal-title":"IEEE Trans Multimedia"},{"issue":"9","key":"6467_CR17","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.1109\/TPAMI.2019.2911077","volume":"42","author":"O Koller","year":"2020","unstructured":"Koller O, Camgoz NC, Ney H, Bowden R (2020) Weakly supervised learning with multi-stream CNN-LSTM-HMMS to discover sequential parallelism in sign language videos. IEEE Trans Pattern Anal Mach Intell 42(9):2306\u20132320","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6467_CR18","doi-asserted-by":"crossref","unstructured":"Pu J, Zhou W, Li H (2019) Iterative alignment network for continuous sign language recognition. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00429"},{"key":"6467_CR19","unstructured":"Sagawa H, Takeuchi M (2000) A method for recognizing a sequence of sign language words represented in a japanese sign language sentence. In: 4th IEEE international conference on automatic face and gesture recognition (FG 2000), Grenoble, France"},{"key":"6467_CR20","unstructured":"Hernandez-Rebollar JL, Kyriakopoulos N, Lindeman RW (2004) A new instrumented approach for translating American sign language into sound and text. In: IEEE international conference on automatic face and gesture recognition"},{"key":"6467_CR21","doi-asserted-by":"crossref","unstructured":"Gao W, Ma JY, Shan SG, Chen XL, Wu JQ (2000) Handtalker: A multimodal dialog system using sign language and 3-d virtual human. In: International conference on advances in multimodal interfaces","DOI":"10.1007\/3-540-40063-X_74"},{"key":"6467_CR22","doi-asserted-by":"crossref","unstructured":"Hu H, Zhou W, Pu J, Li H (2021) Global-local enhancement network for nmf-aware sign language recognition. In: ACM transactions on multimedia computing, communications, and applications (TOMM)","DOI":"10.1145\/3436754"},{"key":"6467_CR23","first-page":"2205","volume":"13","author":"H Cooper","year":"2012","unstructured":"Cooper H, Ong E, Pugeault N, Bowden R (2012) Sign language recognition using sub-units. J Mach Learn Res 13:2205\u20132231","journal-title":"J Mach Learn Res"},{"key":"6467_CR24","unstructured":"Kapuci\u0144ski T, Oszust M, Wysocki M (2014) Recognition of dynamic hand gesture observed by depth cameras. In: Workshop on real-time gesture recognition for human robot interaction"},{"key":"6467_CR25","unstructured":"Ronchetti F, Quiroga F, Estrebou C, Lanzarini L, Rosete A (2016) Lsa64: a dataset of argentinian sign language. XX II Congreso Argentino de Ciencias de la Computaci\u00f3n (CACIC)"},{"key":"6467_CR26","unstructured":"Neidle C, Thangali A, Sclaroff S (2012) Challenges in development of the American sign language lexicon video dataset (ASLLVD) corpus. https:\/\/open.bu.edu\/handle\/2144\/31899"},{"key":"6467_CR27","doi-asserted-by":"crossref","unstructured":"Pugeault N, Bowden (2012) Spelling it out: real-time ASL fingerspelling recognition. In: IEEE international conference on computer vision workshops, ICCV 2011 Workshops, Barcelona, Spain, 2011","DOI":"10.1109\/ICCVW.2011.6130290"},{"key":"6467_CR28","doi-asserted-by":"crossref","unstructured":"Koller O, Ney H, Bowden R (2016) Automatic alignment of Hamnosys subunits for continuous sign language recognition In: LREC workshop on the representation and processing of sign languages: corpus mining","DOI":"10.5244\/C.30.136"},{"key":"6467_CR29","doi-asserted-by":"crossref","unstructured":"Ji Y, Kim S, Lee KB (2017) Sign language learning system with image sampling and convolutional neural network. In: IEEE international conference on robotic computing","DOI":"10.1109\/IRC.2017.40"},{"key":"6467_CR30","doi-asserted-by":"crossref","unstructured":"Kim S, Ji Y, Lee KB (2018) An effective sign language learning with object detection based ROI segmentation. In: IEEE international conference on robotic computing","DOI":"10.1109\/IRC.2018.00069"},{"key":"6467_CR31","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fck\u00fc O, K\u00f6se N, Rigoll G (2018) Motion fused frames: data level fusion strategy for hand gesture recognition. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW)","DOI":"10.1109\/CVPRW.2018.00284"},{"key":"6467_CR32","doi-asserted-by":"crossref","unstructured":"Konstantinidis D, Dimitropoulos K, Daras P (2018) Sign language recognition based on hand and body skeletal data. In: 3DTV conference","DOI":"10.1109\/3DTV.2018.8478467"},{"key":"6467_CR33","doi-asserted-by":"crossref","unstructured":"Devineau G, Moutarde F, Xi W, Yang J (2018) Deep learning for hand gesture recognition on skeletal data. In: 2018 13th IEEE international conference on automatic face and gesture recognition (FG). IEEE, 2018, pp 106\u2013113","DOI":"10.1109\/FG.2018.00025"},{"key":"6467_CR34","doi-asserted-by":"crossref","unstructured":"Molchanov P, Gupta S, Kim K, Kautz J (2015) Hand gesture recognition with 3d convolutional neural networks. In: Computer vision and pattern recognition workshops","DOI":"10.1109\/CVPRW.2015.7301342"},{"issue":"8","key":"6467_CR35","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1109\/TPAMI.2016.2537340","volume":"38","author":"D Wu","year":"2016","unstructured":"Wu D, Pigou L, Kindermans PJ, Le DH, Shao L, Dambre J, Odobez JM (2016) Deep dynamic neural networks for multimodal gesture segmentation and recognition. IEEE Trans Pattern Anal Mach Intell 38(8):1583\u20131597","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6467_CR36","unstructured":"Huang J, Zhou W, Li H, Li W (2015) Sign language recognition using 3d convolutional neural networks. In: 2015 IEEE international conference on multimedia and expo (ICME)"},{"key":"6467_CR37","unstructured":"Li Y, Miao Q, Tian K, Fan Y, Song J (2016) Large-scale gesture recognition with a fusion of RGB-D data based on the c3d model. In: 2016 23rd international conference on pattern recognition (ICPR)"},{"key":"6467_CR38","unstructured":"Li Y, \u00a0Miao Q, \u00a0Tian K, \u00a0Fan Y, Song J (2016) Large-scale gesture recognition with a fusion of RGB-D data based on the C3D model. 2016 23rd international conference on pattern recognition (ICPR). IEEE"},{"key":"6467_CR39","doi-asserted-by":"crossref","unstructured":"Elbadawy M, Elons AS, Shedeed HA, Tolba MF (2017) Arabic sign language recognition with 3d convolutional neural networks. In: 2017 eighth international conference on intelligent computing and information systems (ICICIS)","DOI":"10.1109\/INTELCIS.2017.8260028"},{"key":"6467_CR40","first-page":"1725","volume":"11","author":"L Zhi-Jie","year":"2018","unstructured":"Zhi-Jie L, Sheng-Bin L, Bing-Zhang H (2018) 3d convolutional neural networks for dynamic sign language recognition. Comput J 11:1725\u20131736","journal-title":"Comput J"},{"key":"6467_CR41","unstructured":"Lee C, Xu Y (2002) Online, interactive learning of gestures for human\/robot interfaces. In: IEEE international conference on robotics and automation"},{"issue":"1","key":"6467_CR42","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/72.182690","volume":"4","author":"SS Fels","year":"1993","unstructured":"Fels SS, Hinton GE (1993) Glove-talk: a neural network interface between a data-glove and a speech synthesizer. IEEE Trans Neural Netw 4(1):2\u20138","journal-title":"IEEE Trans Neural Netw"},{"key":"6467_CR43","doi-asserted-by":"publisher","first-page":"1","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 32:1\u201312","journal-title":"Neural Comput Appl"},{"key":"6467_CR44","first-page":"1","volume":"2","author":"A Sharma","year":"2020","unstructured":"Sharma A, Sharma N, Saxena Y, Singh A, Sadhya D (2020) Benchmarking deep neural network approaches for Indian sign language recognition. Neural Comput Appl 2:1\u201312","journal-title":"Neural Comput Appl"},{"issue":"1 Supplement","key":"6467_CR45","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s00521-012-0818-4","volume":"22","author":"AS Elons","year":"2013","unstructured":"Elons AS, Abull-Ela M, Tolba MF (2013) Neutralizing lighting non-homogeneity and background size in PCNN image signature for Arabic sign language recognition. Neural Comput Appl 22(1 Supplement):47\u201353","journal-title":"Neural Comput Appl"},{"issue":"12","key":"6467_CR46","doi-asserted-by":"publisher","first-page":"8955","DOI":"10.1007\/s00521-019-04427-y","volume":"31","author":"T Ozcan","year":"2019","unstructured":"Ozcan T, Basturk A (2019) Transfer learning-based convolutional neural networks with heuristic optimization for hand gesture recognition. Neural Comput Appl 31(12):8955\u20138970","journal-title":"Neural Comput Appl"},{"key":"6467_CR47","unstructured":"Du T, Wang H, Torresani L, Ray J, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"},{"key":"6467_CR48","unstructured":"Diba A, Fayyaz M, Sharma V, Karami AH, Arzani MM, Yousefzadeh R, Van Gool L (2017) Temporal 3d convnets: New architecture and transfer learning for video classification. arXiv:1711.08200"},{"key":"6467_CR49","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":"6467_CR50","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision. pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"6467_CR51","doi-asserted-by":"crossref","unstructured":"Diba A, Sharma V, Van Gool L, Stiefelhagen R (2019) Dynamonet: Dynamic action and motion network. arXiv:1904.11407","DOI":"10.1109\/ICCV.2019.00629"},{"key":"6467_CR52","doi-asserted-by":"crossref","unstructured":"Girdhar R, Tran D, Torresani L, Ramanan D (2019) Distinit: learning video representations without a single labeled video. arXiv:1901.09244","DOI":"10.1109\/ICCV.2019.00094"},{"key":"6467_CR53","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yao T, Mei T (2017) Learning spatio-temporal representation with pseudo-3d residual networks. In: 2017 IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.590"},{"key":"6467_CR54","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.90"},{"key":"6467_CR55","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.1, 4"},{"key":"6467_CR56","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos, in: Advances in neural information processing systems, pp 568\u2013576"},{"key":"6467_CR57","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2016) Temporal segment networks: towards good practices for deep action recognition. In: European conference on computer vision. Springer, Berlin, pp 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"6467_CR58","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6450\u20136459","DOI":"10.1109\/CVPR.2018.00675"},{"key":"6467_CR59","doi-asserted-by":"crossref","unstructured":"Lin W, Zhang C, Lu K, Sheng B, Wu J, Ni B, Liu X, Xiong H (2018) Action recognition with coarse-to-fine deep feature integration and asynchronous fusion. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12232"},{"key":"6467_CR60","doi-asserted-by":"crossref","unstructured":"Xie S, Sun C, Huang J, Tu Z, Murphy K (2018) Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European conference on computer vision (ECCV), pp 305\u2013321","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"6467_CR61","doi-asserted-by":"crossref","unstructured":"Chen Y, Kalantidis Y, Li J, Yan S, Feng J (2018) Multi-fiber networks for video recognition. In: Proceedings of the European conference on computer vision (ECCV), pp 352\u2013367","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"6467_CR62","doi-asserted-by":"crossref","unstructured":"Kar A, Rai N, Sikka K, Sharma G (2017) Adascan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3376\u20133385","DOI":"10.1109\/CVPR.2017.604"},{"key":"6467_CR63","unstructured":"Goyal P, Doll\u00e1r P, Girshick R, Noordhuis P, Wesolowski L, Kyrola A, Tulloch A, Jia Y, He K (2017) Accurate, large minibatch SGD: training imagenet in 1 hour. arXiv:1706.02677"},{"key":"6467_CR64","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) Slowfast networks for video recognition. In: IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"6467_CR65","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C (2020) X3d: Expanding architectures for efficient video recognition. In: Computer vision and pattern recognition, CVPR, pp 203\u2013213","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"6467_CR66","doi-asserted-by":"crossref","unstructured":"Hara K, Kataoka H, Satoh Y (2018) Can spatiotemporal 3d CNNS retrace the history of 2d CNNS and imagenet? In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 6546\u20136555","DOI":"10.1109\/CVPR.2018.00685"},{"issue":"2","key":"6467_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2735952","volume":"6","author":"A Tang","year":"2015","unstructured":"Tang A, Lu K, Wang Y, Huang J, Li H (2015) A real-time hand posture recognition system using deep neural networks. ACM Trans Intell Syst Technol 6(2):1\u201323","journal-title":"ACM Trans Intell Syst Technol"},{"key":"6467_CR68","doi-asserted-by":"crossref","unstructured":"Fan L, Huang W, Gan C, Ermon S, Huang J (2018) End-to-end learning of motion representation for video understanding. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00630"},{"key":"6467_CR69","doi-asserted-by":"crossref","unstructured":"Sun S, Kuang Z, Ouyang W, Sheng L, Zhang W (2017) Optical flow guided feature: a fast and robust motion representation for video action recognition. arXiv:1711.11152","DOI":"10.1109\/CVPR.2018.00151"},{"key":"6467_CR70","unstructured":"Xie S, Sun C, Huang J, Tu Z, Murphy K (2017) Rethinking spatiotemporal feature learning for video understanding. arXiv:1712.04851"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06467-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06467-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06467-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T21:20:15Z","timestamp":1673385615000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06467-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,30]]},"references-count":70,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["6467"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06467-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,30]]},"assertion":[{"value":"19 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2021","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"}}]}}