{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:25:37Z","timestamp":1771698337292,"version":"3.50.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9891959","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T15:56:04Z","timestamp":1664553364000},"page":"1-8","source":"Crossref","is-referenced-by-count":89,"title":["STIP-GCN: Space-time interest points graph convolutional network for action recognition"],"prefix":"10.1109","author":[{"given":"Sravani","family":"Yenduri","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Hyderabad,Kandi,India"}]},{"given":"Vishnu","family":"Chalavadi","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Hyderabad,Kandi,India"}]},{"given":"C Krishna","family":"Mohan","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Hyderabad,Kandi,India"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref38","first-page":"6299","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"joao","year":"0","journal-title":"Proc IEEE Conf Computer Vision and Pattern Recognition"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref32","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume":"402","author":"khurram","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref31","first-page":"491","article-title":"Big transfer (bit): General visual representation learning","author":"alexander","year":"2020","journal-title":"Computer Vision-ECCV 2020 16th European Conference"},{"key":"ref30","first-page":"3","article-title":"Group normalization","author":"yuxin","year":"0","journal-title":"In Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref37","first-page":"6450","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"du","year":"0","journal-title":"Proc IEEE Conf Computer Vision and Pattern Recognition"},{"key":"ref36","first-page":"1933","article-title":"Convolutional two-stream network fusion for video action recognition","author":"christoph","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref35","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"du","year":"0","journal-title":"In Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref34","first-page":"5842","article-title":"The something something","author":"raghav","year":"0","journal-title":"video database for learning and evalu-ating visual common sense ” In Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref10","first-page":"305","article-title":"Action Recognition Using Attention-Joints Graph Convolutional Neural Networks","volume":"8","author":"tasweer","year":"2019","journal-title":"IEEE Access"},{"key":"ref40","first-page":"2000","article-title":"Stm: Spatiotemporal and motion encoding for action recognition","author":"boyuan","year":"0","journal-title":"In Proceedings of the International Conference on Computer Vision"},{"key":"ref11","first-page":"7094","article-title":"Graph convolutional networks for temporal action localization","author":"runhao","year":"0","journal-title":"In Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref12","first-page":"71","article-title":"Representation learning on visual-symbolic graphs for video understanding","author":"effrosyni","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref13","first-page":"10","article-title":"A combined corner and edge detector","volume":"15","author":"chris","year":"0","journal-title":"Alvey Vision Conference"},{"key":"ref14","article-title":"Semi-supervised classification with graph convolutional networks","volume":"2907","author":"thomas n","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref15","first-page":"107","article-title":"On space-time interest points","volume":"2","author":"ivan","year":"2005","journal-title":"Int J Comput Vision 64"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00077"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2778011"},{"key":"ref18","first-page":"5167","article-title":"Multi-cue based 3D residual network for action recognition","volume":"10","author":"ming","year":"2021","journal-title":"Neural Computing and Applications 33"},{"key":"ref19","first-page":"275","article-title":"Directional temporal mod-eling for action recognition","author":"xinyu","year":"2020","journal-title":"in European Conference on Computer Vision"},{"key":"ref28","volume":"8427","author":"iulia","year":"2009","journal-title":"Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks"},{"key":"ref4","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"2199","author":"karen","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref27","first-page":"183","article-title":"Skeleton-based action recognition with shift graph convolutional network","author":"ke","year":"0","journal-title":"Proc IEEE Conf Computer Vision and Pattern Recognition"},{"key":"ref3","first-page":"289","article-title":"Semi-supervised multiple feature analysis for action recognition","volume":"2","author":"sen","year":"2013","journal-title":"IEEE Transactions on Multimedia 16"},{"key":"ref6","first-page":"2740","article-title":"Temporal segment networks for action recognition in videos","volume":"11","author":"limin","year":"2018","journal-title":"IEEE Trans Pattern Analysis an Machine Intelligence"},{"key":"ref29","first-page":"10236","article-title":"Action genome: Actions as compositions of spatio-temporal scene graphs","author":"jingwei","year":"0","journal-title":"Proc IEEE Conf Computer Vision and Pattern Recognition"},{"key":"ref5","first-page":"3154","article-title":"Learning spatio-temporal features with 3d residual networks for action recognition","author":"kensho","year":"0","journal-title":"In Proceedings of the IEEE International Conference on Computer Vision Workshops"},{"key":"ref8","first-page":"670","article-title":"Graph r-cnn for scene graph generation","author":"jianwei","year":"0","journal-title":"In Proceedings of the Euro-pean Conference on Computer Vision (ECCV)"},{"key":"ref7","first-page":"399","article-title":"Videos as space-time region graphs","author":"xiaolong","year":"0","journal-title":"In Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref2","first-page":"1951","article-title":"Vlad3: Encoding dynamics of deep features for action recognition","author":"yingwei","year":"0","journal-title":"Proc IEEE Conf Computer Vision and Pattern Recognition"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref1","first-page":"3551","article-title":"Action recognition with improved trajectories","author":"heng","year":"0","journal-title":"In Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref46","first-page":"6202","article-title":"Slowfast networks for video recognition","author":"christoph","year":"0","journal-title":"In Proceedings of the International Conference on Computer Vision"},{"key":"ref20","first-page":"1","article-title":"Asymmetric 3d convolutional neural networks for action recognition","author":"hao","year":"2019","journal-title":"Pattern Recognition 85"},{"key":"ref45","first-page":"284","article-title":"Spatio-temporal channel correlation networks for action classification","author":"ali","year":"0","journal-title":"In Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref22","volume":"8822","author":"bo","year":"1907","journal-title":"PH-GCN Person re-identification with part-based hierarchical graph convolutional network"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_48"},{"key":"ref21","first-page":"13278","article-title":"Object relational graph with teacher-recommended learning for video captioning","author":"ziqi","year":"0","journal-title":"Proc IEEE Conf Computer Vision and Pattern Recognition"},{"key":"ref42","first-page":"7083","article-title":"Tsm: Temporal shift module for efficient video understanding","author":"ji","year":"0","journal-title":"In Proceedings of the International Conference on Computer Vision"},{"key":"ref24","first-page":"2122","article-title":"Spatio-temporal inception graph convolutional networks for skeleton-based action recognition","author":"zhen","year":"0","journal-title":"ACM international conference on Multimedia"},{"key":"ref41","first-page":"5533","article-title":"Learning spatio-temporal representation with pseudo-3d residual networks","author":"zhaofan","year":"0","journal-title":"In Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.neucom.2021.05.004","article-title":"Re-thinking the ST-GCNs for 3D skeleton-based human action recognition","volume":"454","author":"wei","year":"2021","journal-title":"Neurocomputing"},{"key":"ref44","article-title":"Multiscale vision transformers","volume":"11227","author":"haoqi","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.patrec.2020.05.005","article-title":"Topology-learnable graph convolution for skeleton-based action recognition","volume":"135","author":"guangming","year":"2020","journal-title":"Pattern Recognition Letters"},{"key":"ref43","article-title":"Vivit: A video vision transformer","volume":"15691","author":"anurag","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Spatial-temporal graph attention networks for skeleton-based action recognition","volume":"5","author":"qingqing","year":"2020","journal-title":"Journal of Electronic Imaging 29"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09891959.pdf?arnumber=9891959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T18:57:12Z","timestamp":1667501832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9891959","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}