{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T07:19:21Z","timestamp":1760080761275,"version":"3.37.3"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:00:00Z","timestamp":1664928000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:00:00Z","timestamp":1664928000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Changchun Municipal Science and Technology Bureau","award":["21ZY31"],"award-info":[{"award-number":["21ZY31"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s00521-022-07763-8","type":"journal-article","created":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T11:10:10Z","timestamp":1664968210000},"page":"1835-1848","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["3\u00a0s-STNet: three-stream spatial\u2013temporal network with appearance and skeleton information learning for action recognition"],"prefix":"10.1007","volume":"35","author":[{"given":"Ming","family":"Fang","sequence":"first","affiliation":[]},{"given":"Siyu","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Haibo","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Chih-Cheng","family":"Hung","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5133-329X","authenticated-orcid":false,"given":"Shuhua","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,5]]},"reference":[{"key":"7763_CR1","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) April. Spatial temporal graph convolutional networks for skeleton-based action recognition. In:\u00a0Proceedings of the AAAI conference on artificial intelligence\u00a0(Vol. 32, No. 1).","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"7763_CR2","doi-asserted-by":"crossref","unstructured":"Peng W, Hong X, Chen H, Zhao G (2020) Learning graph convolutional network for skeleton-based human action recognition by neural searching. In:\u00a0Proceedings of the AAAI Conference on Artificial Intelligence, vol 34, No. 03, pp. 2669\u20132676.","DOI":"10.1609\/aaai.v34i03.5652"},{"issue":"8","key":"7763_CR3","doi-asserted-by":"publisher","first-page":"1963","DOI":"10.1109\/TPAMI.2019.2896631","volume":"41","author":"P Zhang","year":"2019","unstructured":"Zhang P, Lan C, Xing J, Zeng W, Xue J, Zheng N (2019) View adaptive neural networks for high performance skeleton-based human action recognition. IEEE Trans Pattern Anal Mach Intell 41(8):1963\u20131978","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7763_CR4","doi-asserted-by":"crossref","unstructured":"Li Y, Ji B, Shi X, Zhang J, Kang B, Wang L (2020) Tea: Temporal excitation and aggregation for action recognition. In:\u00a0Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition,\u00a0pp. 909\u2013918.","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"7763_CR5","doi-asserted-by":"crossref","unstructured":"Sudhakaran S, Escalera S, Lanz O (2020) Gate-shift networks for video action recognition. In:\u00a0Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1102\u20131111.","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"7763_CR6","doi-asserted-by":"crossref","unstructured":"Abdelbaky A,, Aly S (2020) Human action recognition using short-time motion energy template images and PCANet features. Neural Comput Appl, 1\u201314.","DOI":"10.1007\/s00521-020-04712-1"},{"key":"7763_CR7","doi-asserted-by":"crossref","unstructured":"Li Y, Xia R, Liu X, Huang Q (2019) Learning shape-motion representations from geometric algebra spatio-temporal model for skeleton-based action recognition. In: 2019 IEEE international conference on multimedia and Expo (ICME)\u00a0(pp. 1066\u20131071). IEEE, New York.","DOI":"10.1109\/ICME.2019.00187"},{"key":"7763_CR8","doi-asserted-by":"crossref","unstructured":"Caetano C, Sena J, Br\u00e9mond F, Dos Santos JA, Schwartz WR (2019) Skelemotion: a new representation of skeleton joint sequences based on motion information for 3d action recognition. In: 2019 16th IEEE international conference on advanced video and signal based surveillance (AVSS)\u00a0(pp. 1\u20138). IEEE, New York.","DOI":"10.1109\/AVSS.2019.8909840"},{"key":"7763_CR9","doi-asserted-by":"crossref","unstructured":"Caetano C, Br\u00e9mond F, Schwartz WR (2019) Skeleton image representation for 3d action recognition based on tree structure and reference joints. In: 2019 32nd SIBGRAPI conference on graphics, patterns and images (SIBGRAPI)\u00a0(pp. 16\u201323). IEEE, New York.","DOI":"10.1109\/SIBGRAPI.2019.00011"},{"issue":"12","key":"7763_CR10","doi-asserted-by":"publisher","first-page":"8533","DOI":"10.1007\/s00521-018-3719-3","volume":"31","author":"L Fang","year":"2019","unstructured":"Fang L, Wu G, Kang W et al (2019) Feature covariance matrix-based dynamic hand gesture recognition[J]. Neural Comput Appl 31(12):8533\u20138546","journal-title":"Neural Comput Appl"},{"key":"7763_CR11","doi-asserted-by":"crossref","unstructured":"Zheng W, Li L, Zhang Z, Huang Y, Wang L (2019) Relational network for skeleton-based action recognition. In:\u00a02019 IEEE International conference on multimedia and Expo (ICME)\u00a0(pp. 826\u2013831). IEEE, New York","DOI":"10.1109\/ICME.2019.00147"},{"key":"7763_CR12","doi-asserted-by":"crossref","unstructured":"Li S, Li W, Cook C, Zhu C, Gao Y (2018) Independently recurrent neural network (indrnn): Building a longer and deeper rnn. In:\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 5457\u20135466).","DOI":"10.1109\/CVPR.2018.00572"},{"issue":"2","key":"7763_CR13","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"SH Gao","year":"2019","unstructured":"Gao SH, Cheng MM, Zhao K, Zhang XY, Yang MH, Torr P (2019) Res2net: A new multi-scale backbone architecture.\u00a0IEEE Trans Pattern Anal Mach Intell 43(2):652\u2013662.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7763_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition\u00a0(pp. 1725\u20131732).","DOI":"10.1109\/CVPR.2014.223"},{"key":"7763_CR15","doi-asserted-by":"crossref","unstructured":"Gan C, Wang N, Yang Y et al (2015) Devnet: A deep event network for multimedia event detection and evidence recounting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2568\u20132577.","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"7763_CR16","doi-asserted-by":"crossref","unstructured":"Lin J, Gan C, Han S (2019) TSM: temporal shift module for efficient video understanding. In: Proceedings of the 17th IEEE International Conference on Computer Vision, Seoul, Oct 7\u2013Nov 2, 2019. Piscataway: IEEE, 2019: 7083\u20137093.","DOI":"10.1109\/ICCV.2019.00718"},{"issue":"1","key":"7763_CR17","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji S, Xu W, Yang M, Yu K (2012) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221\u2013231","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"7763_CR18","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/s11042-017-5251-3","volume":"78","author":"X Lu","year":"2019","unstructured":"Lu X, Yao H, Zhao S, Sun X, Zhang S (2019) Action recognition with multi-scale trajectory-pooled 3D convolutional descriptors. Multimedia Tools Appl 78(1):507\u2013523","journal-title":"Multimedia Tools Appl"},{"key":"7763_CR19","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C (2020) X3d: Expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern Recognition, pp 203\u2013213.","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"7763_CR20","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos.\u00a0arXiv preprint arXiv:1406.2199."},{"key":"7763_CR21","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J et al (2019) Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp  6202\u20136211.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"7763_CR22","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron G, Laptev I, Schmid C (2015) P-cnn: Pose-based cnn features for action recognition. In:\u00a0Proceedings of the IEEE international conference on computer vision,\u00a0pp. 3218\u20133226.","DOI":"10.1109\/ICCV.2015.368"},{"key":"7763_CR23","doi-asserted-by":"crossref","unstructured":"Wang H,  Wang L (2017) Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks. In:\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 499\u2013508).","DOI":"10.1109\/CVPR.2017.387"},{"issue":"12","key":"7763_CR24","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1109\/TPAMI.2017.2771306","volume":"40","author":"J Liu","year":"2017","unstructured":"Liu J, Shahroudy A, Xu D, Kot AC, Wang G (2017) Skeleton-based action recognition using spatio-temporal LSTM network with trust gates. IEEE Trans Pattern Anal Mach Intell 40(12):3007\u20133021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"7763_CR25","doi-asserted-by":"publisher","first-page":"4800","DOI":"10.1109\/TNNLS.2021.3061115","volume":"33","author":"C Li","year":"2021","unstructured":"Li C, Xie C, Zhang B, Han J, Zhen X, Chen J (2021) Memory attention networks for skeleton-based action recognition.\u00a0IEEE Trans Neural Netw Learn Syst 33(9):4800\u20134814. https:\/\/doi.org\/10.1109\/TNNLS.2021.3061115.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"7763_CR26","doi-asserted-by":"crossref","unstructured":"Si C, Chen W, Wang W, Wang L, Tan T (2019) An attention enhanced graph convolutional lstm network for skeleton-based action recognition. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0(pp. 1227\u20131236).","DOI":"10.1109\/CVPR.2019.00132"},{"key":"7763_CR27","doi-asserted-by":"crossref","unstructured":"Shi L, Zhang Y, Cheng J, Lu H (2019) Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0(pp. 12026\u201312035).","DOI":"10.1109\/CVPR.2019.01230"},{"key":"7763_CR28","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks.\u00a0arXiv preprint arXiv:1609.02907."},{"issue":"8","key":"7763_CR29","doi-asserted-by":"publisher","first-page":"2405","DOI":"10.1109\/TCSVT.2018.2864148","volume":"29","author":"Z Yang","year":"2018","unstructured":"Yang Z, Li Y, Yang J, Luo J (2018) Action recognition with spatio\u2013temporal visual attention on skeleton image sequences. IEEE Trans Circuits Syst Video Technol 29(8):2405\u20132415","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7763_CR30","doi-asserted-by":"crossref","unstructured":"Ke Q, Bennamoun M, An S, Sohel F, Boussaid F (2017) A new representation of skeleton sequences for 3d action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 3288\u20133297).","DOI":"10.1109\/CVPR.2017.486"},{"key":"7763_CR31","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng TT, Wang G (2016) Ntu rgb+ d: A large scale dataset for 3d human activity analysis. In:\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 1010\u20131019).","DOI":"10.1109\/CVPR.2016.115"},{"issue":"10","key":"7763_CR32","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu J, Shahroudy A, Perez M, Wang G, Duan LY, Kot AC (2019) Ntu rgb+ d 120: A large-scale benchmark for 3d human activity understanding. IEEE Trans Pattern Anal Mach Intell 42(10):2684\u20132701","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7763_CR33","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P et al  (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1492\u20131500.","DOI":"10.1109\/CVPR.2017.634"},{"key":"7763_CR34","doi-asserted-by":"crossref","unstructured":"Das S, Dai R, Yang D, Bremond F (2021) VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living.\u00a0arXiv preprint arXiv:2105.08141.","DOI":"10.1109\/TPAMI.2021.3127885"},{"key":"7763_CR35","doi-asserted-by":"crossref","unstructured":"Baradel F, Wolf C, Mille J (2017) Human action recognition: Pose-based attention draws focus to hands. In:\u00a0Proceedings of the IEEE International conference on computer vision workshops\u00a0(pp. 604\u2013613).","DOI":"10.1109\/ICCVW.2017.77"},{"key":"7763_CR36","unstructured":"Baradel F, Wolf C, Mille J (2018) Human activity recognition with pose-driven attention to rgb. In: BMVC 2018\u201329th British Machine Vision Conference\u00a0(pp. 1\u201314)."},{"key":"7763_CR37","doi-asserted-by":"crossref","unstructured":"Liu M, Yuan J (2018) Recognizing human actions as the evolution of pose estimation maps. In:\u00a0Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition\u00a0(pp. 1159\u20131168).","DOI":"10.1109\/CVPR.2018.00127"},{"key":"7763_CR38","doi-asserted-by":"crossref","unstructured":"Shi L, Zhang Y, Cheng J, Lu H (2019) Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0(pp. 7912\u20137921).","DOI":"10.1109\/CVPR.2019.00810"},{"key":"7763_CR39","doi-asserted-by":"crossref","unstructured":"Das S, Dai R, Koperski M, Minciullo L, Garattoni L Bremond F, Francesca G (2019) Toyota smarthome: Real-world activities of daily living. In:\u00a0Proceedings of the IEEE\/CVF international conference on computer vision\u00a0(pp. 833\u2013842).","DOI":"10.1109\/ICCV.2019.00092"},{"key":"7763_CR40","doi-asserted-by":"crossref","unstructured":"Das S, Chaudhary A, Bremond F, Thonnat M (2019) Where to focus on for human action recognition? In:\u00a02019 IEEE Winter Conference on Applications of Computer Vision (WACV)\u00a0(pp. 71\u201380). IEEE, New York.","DOI":"10.1109\/WACV.2019.00015"},{"key":"7763_CR41","doi-asserted-by":"crossref","unstructured":"Liu Z, Zhang H, Chen Z, Wang Z, Ouyang W (2020) Disentangling and unifying graph convolutions for skeleton-based action recognition. In:\u00a0Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition\u00a0(pp. 143\u2013152).","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"7763_CR42","doi-asserted-by":"crossref","unstructured":"Das S, Sharma S, Dai R, Bremond F, Thonnat M (2020) Vpn: Learning video-pose embedding for activities of daily living. In:\u00a0European conference on computer vision\u00a0(pp. 72\u201390). Springer, Cham.","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"7763_CR43","doi-asserted-by":"crossref","unstructured":"Ziyu Liu, Hongwen Zhang, Zhenghao Chen, Zhiyong Wang, Wanli Ouyang (2020) Disentangling and unifying graph convo-lutions for skeleton-based action recognition. In: Proceedings ofthe IEEE\/CVF conference on computer vision and pattern recognition, p. 143\u2013152","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"7763_CR44","doi-asserted-by":"crossref","unstructured":"Liu J, Wang G, Hu P, Duan LY, Kot AC (2017) Global context-aware attention lstm networks for 3d action recognition. In:\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 1647\u20131656).","DOI":"10.1109\/CVPR.2017.391"},{"key":"7763_CR45","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In:\u00a0proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 6299\u20136308).","DOI":"10.1109\/CVPR.2017.502"},{"key":"7763_CR46","unstructured":"Yang H, Yan D, Zhang L, Li D, Sun Y, You S, Maybank SJ (2020) Feedback graph convolutional network for skeleton-based action recognition.\u00a0arXiv preprint arXiv:2003.07564."},{"key":"7763_CR47","doi-asserted-by":"crossref","unstructured":"Chen Z, Li S, Yang B, Li Q, Liu H (2021) Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence\u00a0(Vol. 35, No. 2, pp. 1113\u20131122).","DOI":"10.1609\/aaai.v35i2.16197"},{"key":"7763_CR48","doi-asserted-by":"crossref","unstructured":"Cheng K, Zhang Y, He X et al (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":"7763_CR49","doi-asserted-by":"crossref","unstructured":"Friji Rasha, Hassen Drira, Faten Chaieb, Hamza Kchok, Sebastian Kurtek (2021) Geometric deep neural network using rigid and non-rigid transformations for human action recognition. In:\u00a0Proceedings of the IEEE\/CVF international conference on computer vision, pp. 12611\u201312620.","DOI":"10.1109\/ICCV48922.2021.01238"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07763-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07763-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07763-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T17:24:56Z","timestamp":1673285096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07763-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,5]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["7763"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07763-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2022,10,5]]},"assertion":[{"value":"27 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}