{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T21:17:52Z","timestamp":1775510272822,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T00:00:00Z","timestamp":1687392000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T00:00:00Z","timestamp":1687392000000},"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":["Pattern Anal Applic"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s10044-023-01179-3","type":"journal-article","created":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T04:26:42Z","timestamp":1687408002000},"page":"929-939","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Spatial\u2013Temporal gated graph attention network for skeleton-based action recognition"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0551-9229","authenticated-orcid":false,"given":"Mrugendrasinh","family":"Rahevar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit","family":"Ganatra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,22]]},"reference":[{"issue":"1","key":"1179_CR1","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"},{"key":"1179_CR2","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, pp 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"issue":"12","key":"1179_CR3","doi-asserted-by":"publisher","first-page":"9904","DOI":"10.1109\/TPAMI.2021.3132068","volume":"44","author":"Z Li","year":"2021","unstructured":"Li Z, Sun Y, Zhang L, Tang J (2021) Ctnet: context-based tandem network for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 44(12):9904\u20139917","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"1179_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1922649.1922653","volume":"43","author":"JK Aggarwal","year":"2011","unstructured":"Aggarwal JK, Ryoo MS (2011) Human activity analysis: a review. ACM Comput Surv (Csur) 43(3):1\u201343","journal-title":"ACM Comput Surv (Csur)"},{"issue":"7","key":"1179_CR5","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1109\/JPROC.2002.801449","volume":"90","author":"Z Duric","year":"2002","unstructured":"Duric Z, Gray WD, Heishman R, Li F, Rosenfeld A, Schoelles MJ, Schunn C, Wechsler H (2002) Integrating perceptual and cognitive modeling for adaptive and intelligent human-computer interaction. Proc IEEE 90(7):1272\u20131289","journal-title":"Proc IEEE"},{"key":"1179_CR6","doi-asserted-by":"crossref","unstructured":"Rezazadegan F, Shirazi S, Upcrofit B, Milford M (2017) Action recognition: from static datasets to moving robots. In: 2017 IEEE International conference on robotics and automation (ICRA), pp 3185\u20133191. IEEE","DOI":"10.1109\/ICRA.2017.7989361"},{"key":"1179_CR7","doi-asserted-by":"crossref","unstructured":"Shu T, Gao X, Ryoo MS, Zhu S-C (2017) Learning social affordance grammar from videos: transferring human interactions to human-robot interactions. In: 2017 IEEE international conference on robotics and automation (ICRA), pp. 1669\u20131676. IEEE","DOI":"10.1109\/ICRA.2017.7989197"},{"key":"1179_CR8","unstructured":"Jin L, Li Z, Tang J (2020) Deep semantic multimodal hashing network for scalable image-text and video-text retrievals. IEEE Trans Neural Netw Learn Syst"},{"issue":"9","key":"1179_CR9","doi-asserted-by":"publisher","first-page":"2070","DOI":"10.1109\/TPAMI.2018.2852750","volume":"41","author":"Z Li","year":"2018","unstructured":"Li Z, Tang J, Mei T (2018) Deep collaborative embedding for social image understanding. IEEE Trans Pattern Anal Mach Intell 41(9):2070\u20132083","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1179_CR10","doi-asserted-by":"crossref","unstructured":"Fan L, Huang W, Gan C, Ermon S, Gong B, Huang J (2018) End-to-end learning of motion representation for video understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6016\u20136025","DOI":"10.1109\/CVPR.2018.00630"},{"key":"1179_CR11","doi-asserted-by":"crossref","unstructured":"Wang L, Li W, Li W, Van\u00a0Gool L (2018) Appearance-and-relation networks for video classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1430\u20131439","DOI":"10.1109\/CVPR.2018.00155"},{"key":"1179_CR12","doi-asserted-by":"crossref","unstructured":"Zhou B, Andonian A, Oliva A, Torralba A (2018) Temporal relational reasoning in videos. In: Proceedings of the european conference on computer vision (ECCV), pp. 803\u2013818","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"1179_CR13","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, pp. 3288\u20133297","DOI":"10.1109\/CVPR.2017.486"},{"key":"1179_CR14","unstructured":"Chaolong L, Zhen C, Wenming Z, Chunyan X, Jian Y (2018) Spatio-temporal graph convolution for skeleton based action recognition. In: Thirty-second AAAI conference on artificial intelligence"},{"key":"1179_CR15","doi-asserted-by":"crossref","unstructured":"Yan Y, Xu J, Ni B, Zhang W, Yang X (2017) Skeleton-aided articulated motion generation. In: Proceedings of the 25th ACM international conference on multimedia, pp. 199\u2013207","DOI":"10.1145\/3123266.3123277"},{"key":"1179_CR16","doi-asserted-by":"crossref","unstructured":"Du Y, Fu Y, Wang L (2015) Skeleton based action recognition with convolutional neural network. In: 2015 3rd IAPR Asian conference on pattern recognition (ACPR), pp 579\u2013583. IEEE","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"1179_CR17","unstructured":"Hussein ME, Torki M, Gowayyed MA, El-Saban M (2013) Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations. In: Twenty-third international joint conference on artificial intelligence"},{"key":"1179_CR18","doi-asserted-by":"crossref","unstructured":"Vemulapalli R, Arrate F, Chellappa R (2014) Human action recognition by representing 3d skeletons as points in a lie group. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 588\u2013595","DOI":"10.1109\/CVPR.2014.82"},{"key":"1179_CR19","doi-asserted-by":"crossref","unstructured":"Li M, Chen S, Chen X, Zhang Y, Wang Y, Tian Q (2019) Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3595\u20133603","DOI":"10.1109\/CVPR.2019.00371"},{"key":"1179_CR20","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":"1179_CR21","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv preprint arXiv:1710.10903"},{"key":"1179_CR22","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"1179_CR23","doi-asserted-by":"crossref","unstructured":"Soo\u00a0Kim T, Reiter A (2017) Interpretable 3d human action analysis with temporal convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 20\u201328","DOI":"10.1109\/CVPRW.2017.207"},{"key":"1179_CR24","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","volume":"68","author":"M Liu","year":"2017","unstructured":"Liu M, Liu H, Chen C (2017) Enhanced skeleton visualization for view invariant human action recognition. Pattern Recog 68:346\u2013362","journal-title":"Pattern Recog"},{"key":"1179_CR25","doi-asserted-by":"crossref","unstructured":"Liu J, Shahroudy A, Xu D, Wang G (2016) Spatio-temporal lstm with trust gates for 3d human action recognition. In: European conference on computer vision, pp 816\u2013833. Springer","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"1179_CR26","unstructured":"Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1110\u20131118"},{"key":"1179_CR27","unstructured":"Duvenaud DK, Maclaurin D, Iparraguirre J, Bombarell R, Hirzel T, Aspuru-Guzik A, Adams RP (2015) Convolutional networks on graphs for learning molecular fingerprints. Adv Neural Inf Process Syst 28"},{"key":"1179_CR28","unstructured":"Henaff M, Bruna J, LeCun Y (2015) Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163"},{"key":"1179_CR29","unstructured":"Bruna J, Zaremba W, Szlam A, LeCun Y (2013) Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203"},{"key":"1179_CR30","unstructured":"Thakkar K, Narayanan P (2018) Part-based graph convolutional network for action recognition. arXiv preprint arXiv:1809.04983"},{"key":"1179_CR31","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, pp 7912\u20137921","DOI":"10.1109\/CVPR.2019.00810"},{"issue":"1","key":"1179_CR32","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2020","unstructured":"Wu Z, Pan S, Chen F, Long G, Zhang C, Philip SY (2020) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst 32(1):4\u201324","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1179_CR33","unstructured":"Seo M, Kembhavi A, Farhadi A, Hajishirzi H (2016) Bidirectional attention flow for machine comprehension. arXiv preprint arXiv:1611.01603"},{"key":"1179_CR34","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning, pp. 2048\u20132057. PMLR"},{"key":"1179_CR35","doi-asserted-by":"crossref","unstructured":"Li C, Xie C, Zhang B, Han J, Zhen X, Chen J (2021) Memory attention networks for skeleton-based action recognition. In: IEEE transactions on neural networks and learning systems","DOI":"10.1109\/TNNLS.2021.3061115"},{"key":"1179_CR36","doi-asserted-by":"crossref","unstructured":"Song S, Lan C, Xing J, Zeng W, Liu J (2017) An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Proceedings of the AAAI conference on artificial intelligence, vol 31","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"1179_CR37","doi-asserted-by":"crossref","unstructured":"Li S, Bak S, Carr P, Wang X (2018) Diversity regularized spatiotemporal attention for video-based person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 369\u2013378","DOI":"10.1109\/CVPR.2018.00046"},{"key":"1179_CR38","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng T-T, Wang G (2016) Ntu rgb+ d: a large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1010\u20131019","DOI":"10.1109\/CVPR.2016.115"},{"issue":"10","key":"1179_CR39","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 L-Y, 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":"1179_CR40","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, Viola F, Green T, Back T, Natsev P, et al (2017) The kinetics human action video dataset. arXiv preprint arXiv:1705.06950"},{"key":"1179_CR41","doi-asserted-by":"crossref","unstructured":"Cao Z, Simon T, Wei S-E, Sheikh Y (2017) Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7291\u20137299","DOI":"10.1109\/CVPR.2017.143"},{"key":"1179_CR42","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et al (2019) Pytorch: An imperative style, high-performance deep learning library. Adv Neural Inf Process Syst 32"},{"key":"1179_CR43","unstructured":"Zehui L, Liu P, Huang L, Chen J, Qiu X, Huang X (2019) DropAttention: a regularization method for fully-connected self-attention networks. arXiv preprint arXiv:1907.11065"},{"key":"1179_CR44","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, vol 35, pp 1113\u20131122","DOI":"10.1609\/aaai.v35i2.16197"},{"key":"1179_CR45","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 499\u2013508","DOI":"10.1109\/CVPR.2017.387"},{"key":"1179_CR46","doi-asserted-by":"crossref","unstructured":"Zhang P, Lan C, Xing J, Zeng W, Xue J, Zheng N (2017) View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: Proceedings of the IEEE international conference on computer vision, pp 2117\u20132126","DOI":"10.1109\/ICCV.2017.233"},{"key":"1179_CR47","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: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1227\u20131236","DOI":"10.1109\/CVPR.2019.00132"},{"key":"1179_CR48","doi-asserted-by":"crossref","unstructured":"Wen Y-H, Gao L, Fu H, Zhang F-L, Xia S (2019) Graph CNNs with motif and variable temporal block for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 8989\u20138996","DOI":"10.1609\/aaai.v33i01.33018989"},{"key":"1179_CR49","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":"1179_CR50","doi-asserted-by":"publisher","first-page":"127010","DOI":"10.1109\/ACCESS.2021.3111633","volume":"9","author":"J Gang","year":"2021","unstructured":"Gang J, Xiao Y, Liu S, Lu Y (2021) Skeleton-based action recognition with low-level features of adaptive graph convolutional networks. IEEE Access 9:127010\u2013127018","journal-title":"IEEE Access"},{"issue":"4","key":"1179_CR51","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/TIP.2017.2785279","volume":"27","author":"J Liu","year":"2017","unstructured":"Liu J, Wang G, Duan L-Y, Abdiyeva K, Kot AC (2017) Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Trans Image Process 27(4):1586\u20131599","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"1179_CR52","doi-asserted-by":"publisher","first-page":"2842","DOI":"10.1109\/TIP.2018.2812099","volume":"27","author":"Q Ke","year":"2018","unstructured":"Ke Q, Bennamoun M, An S, Sohel F, Boussaid F (2018) Learning clip representations for skeleton-based 3d action recognition. IEEE Trans Image Process 27(6):2842\u20132855","journal-title":"IEEE Trans Image Process"},{"key":"1179_CR53","doi-asserted-by":"crossref","unstructured":"Cho S, Maqbool M, Liu F, Foroosh H (2020) Self-attention network for skeleton-based human action recognition. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 635\u2013644","DOI":"10.1109\/WACV45572.2020.9093639"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-023-01179-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-023-01179-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-023-01179-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,22]],"date-time":"2023-07-22T14:11:03Z","timestamp":1690035063000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-023-01179-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,22]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["1179"],"URL":"https:\/\/doi.org\/10.1007\/s10044-023-01179-3","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,22]]},"assertion":[{"value":"17 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 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":"No potential conflict of interest was reported by the author(s).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}