{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T22:46:37Z","timestamp":1752101197205,"version":"3.38.0"},"reference-count":39,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIC"],"published-print":{"date-parts":[[2023,8,21]]},"abstract":"<jats:p>Graph Convolution Network (GCN) algorithms have greatly improved the accuracy of skeleton-based human action recognition. GCN can utilize the spatial information between skeletal joints in subsequent frames better than other deep learning algorithms, which is beneficial for achieving high accuracy. However, the traditional GCN algorithms consume lots of computation for the stack of multiple primary GCN layers. Aiming at solving the problem, we introduce a lightweight network, a Differential Learning and Parallel Convolutional Networks (DL-PCN), whose key modules are Differential Learning (DLM) and the Parallel Convolutional Network (PCN). DLM features a feedforward connection, which carries the error information of GCN modules with the same structure, where GCN and CNN modules directly extract the original information from the input data, making the spatiotemporal information extracted by these modules more complete than that of GCN and CNN tandem structure. PCN comprises GCN and Convolution Neural Network (CNN) in parallel. Our network achieves comparable performance on the NTU RGB+D 60 dataset, the NTU RGB+D 120 dataset and the Northwestern-UCLA dataset while considering both accuracy and calculation parameters.<\/jats:p>","DOI":"10.3233\/aic-220268","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T14:03:52Z","timestamp":1686319432000},"page":"235-249","source":"Crossref","is-referenced-by-count":1,"title":["DL-PCN: Differential learning and parallel convolutional network for action recognition"],"prefix":"10.1177","volume":"36","author":[{"given":"Qinyang","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tongji University, Shanghai 201804, China"}]},{"given":"Ronghao","family":"Dang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tongji University, Shanghai 201804, China"}]},{"given":"Qin","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tongji University, Shanghai 201804, China"}]},{"given":"Chengju","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tongji University, Shanghai 201804, China"},{"name":"Tongji Research Institute of Artificial Intelligence (Suzhou), Suzhou 215300, China"}]},{"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tongji University, Shanghai 201804, China"}]}],"member":"179","reference":[{"key":"10.3233\/AIC-220268_ref1","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Chen, Z.\u00a0Zhang, C.\u00a0Yuan et al., Channel-wise topology refinement graph convolution for skeleton-based action recognition, in: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021, pp.\u00a013339\u201313348.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"10.3233\/AIC-220268_ref2","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Chen, Z.\u00a0Zhang, C.\u00a0Yuan et al., Channel-wise topology refinement graph convolution for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp.\u00a013359\u201313368.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"10.3233\/AIC-220268_ref3","doi-asserted-by":"crossref","unstructured":"K.\u00a0Cheng, Y.\u00a0Zhang, C.\u00a0Cao et al., Decoupling GCN with dropgraph module for skeleton-based action recognition, in: European Conference on Computer Vision, Springer, 2020, pp.\u00a0536\u2013553.","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"10.3233\/AIC-220268_ref4","unstructured":"Y.\u00a0Du, W.\u00a0Wang, L.\u00a0Wang et al., Hierarchical recurrent neural network for skeleton based action recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp.\u00a01110\u20131118."},{"key":"10.3233\/AIC-220268_ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548546"},{"key":"10.3233\/AIC-220268_ref6","doi-asserted-by":"crossref","unstructured":"A.R.\u00a0Ebrahimy, A.R.\u00a0NaghshNilchi, A.H.\u00a0Monadjemi et al., IoT based smart surveillance monitoring by using model-based human action recognition design, in: 2021 5th International Conference on Internet of Things and Applications (IoT), IEEE, 2021, pp.\u00a01\u20136.","DOI":"10.1109\/IoT52625.2021.9469601"},{"key":"10.3233\/AIC-220268_ref7","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Huang, Y.\u00a0Guo, C.\u00a0Gao et al., Efficient parallel inflated 3D convolution architecture for action recognition, in: IEEE Access, Vol.\u00a08, 2020, pp.\u00a045753\u201345765.","DOI":"10.1109\/ACCESS.2020.2978223"},{"key":"10.3233\/AIC-220268_ref8","doi-asserted-by":"crossref","unstructured":"S.\u00a0Ji, W.\u00a0Xu, M.\u00a0Yang et al., 3D convolutional neural networks for human action recognition, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.\u00a035, 2012, pp.\u00a0221\u2013231.","DOI":"10.1109\/TPAMI.2012.59"},{"key":"10.3233\/AIC-220268_ref9","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Ji, Y.\u00a0Yang, F.\u00a0Shen et al., A survey of human action analysis in HRI applications, in: IEEE Transactions on Circuits and Systems for Video Technology, Vol.\u00a030, 2019, pp.\u00a02114\u20132128.","DOI":"10.1109\/TCSVT.2019.2912988"},{"key":"10.3233\/AIC-220268_ref10","doi-asserted-by":"crossref","unstructured":"M.\u00a0Li, S.\u00a0Chen, X.\u00a0Chen et al., Actional\u2013structural graph convolutional networks for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp.\u00a03595\u20133603.","DOI":"10.1109\/CVPR.2019.00371"},{"key":"10.3233\/AIC-220268_ref11","doi-asserted-by":"crossref","unstructured":"M.\u00a0Li, S.\u00a0Chen, X.\u00a0Chen et al., Symbiotic graph neural networks for 3D skeleton-based human action recognition and motion prediction, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.\u00a044, 2021, pp.\u00a03316\u20133333.","DOI":"10.1109\/TPAMI.2021.3053765"},{"key":"10.3233\/AIC-220268_ref12","doi-asserted-by":"crossref","unstructured":"W.\u00a0Li, L.\u00a0Wen, M.-C.\u00a0Chang et al., Adaptive RNN tree for large-scale human action recognition, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp.\u00a01444\u20131452.","DOI":"10.1109\/ICCV.2017.161"},{"key":"10.3233\/AIC-220268_ref13","doi-asserted-by":"crossref","unstructured":"J.\u00a0Liu, A.\u00a0Shahroudy, M.\u00a0Perez et al., NTU RGB+D 120: A large-scale benchmark for 3D human activity understanding, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.\u00a042, 2019, pp.\u00a02684\u20132701.","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"10.3233\/AIC-220268_ref14","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Liu, H.\u00a0Zhang, Z.\u00a0Chen et al., Disentangling and unifying graph convolutions for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp.\u00a0143\u2013152.","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"10.3233\/AIC-220268_ref15","doi-asserted-by":"crossref","unstructured":"S.\u00a0Lu et al., A distributed feedforward control method for power electronic transformers, in: CES Transactions on Electrical Machines and Systems, Vol.\u00a04, 2020, pp.\u00a0319\u2013328.","DOI":"10.30941\/CESTEMS.2020.00039"},{"key":"10.3233\/AIC-220268_ref16","doi-asserted-by":"crossref","unstructured":"R.\u00a0Morais, V.\u00a0Le, T.\u00a0Tran et al., Learning regularity in skeleton trajectories for anomaly detection in videos, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp.\u00a011996\u201312004.","DOI":"10.1109\/CVPR.2019.01227"},{"key":"10.3233\/AIC-220268_ref17","doi-asserted-by":"crossref","unstructured":"W.\u00a0Ng, M.\u00a0Zhang, T.\u00a0Wang et al., Multi-localized sensitive autoencoder-attention-LSTM for skeleton-based action recognition, in: IEEE Transactions on Multimedia, Vol.\u00a024, 2021, pp.\u00a01678\u20131690.","DOI":"10.1109\/TMM.2021.3070127"},{"key":"10.3233\/AIC-220268_ref18","doi-asserted-by":"crossref","unstructured":"W.\u00a0Peng, X.\u00a0Hong, G.\u00a0Zhao et al., Tripool: Graph triplet pooling for 3D skeleton-based action recognition, Pattern Recognition, 115 (2021), 107921.","DOI":"10.1016\/j.patcog.2021.107921"},{"key":"10.3233\/AIC-220268_ref19","doi-asserted-by":"crossref","unstructured":"R.\u00a0Qian, J.\u00a0Wang, J.\u00a0Wang et al., Structural attention for channel-wise adaptive graph convolution in skeleton-based action recognition, in: 2022 IEEE International Conference on Multimedia and Expo (ICME), 2022, pp.\u00a001\u201306.","DOI":"10.1109\/ICME52920.2022.9859694"},{"key":"10.3233\/AIC-220268_ref20","doi-asserted-by":"crossref","unstructured":"H.\u00a0Qiu, Y.\u00a0Wu, M.\u00a0Duan et al., GLTA-GCN: Global-local temporal attention graph convolutional network for unsupervised skeleton-based action recognition, in: 2022 IEEE International Conference on Multimedia and Expo (ICME), 2022, pp.\u00a01\u20136.","DOI":"10.1109\/ICME52920.2022.9859752"},{"key":"10.3233\/AIC-220268_ref21","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Qiu, T.\u00a0Yao, T.\u00a0Mei et al., Learning spatio-temporal representation with pseudo-3D residual networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp.\u00a05533\u20135541.","DOI":"10.1109\/ICCV.2017.590"},{"key":"10.3233\/AIC-220268_ref22","doi-asserted-by":"crossref","unstructured":"A.\u00a0Shahroudy, J.\u00a0Liu, T.-T.\u00a0Ng et al., NTU RGB+D: A large scale dataset for 3D human activity analysis, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.\u00a01010\u20131019.","DOI":"10.1109\/CVPR.2016.115"},{"key":"10.3233\/AIC-220268_ref23","doi-asserted-by":"crossref","unstructured":"L.\u00a0Shi, Y.\u00a0Zhang, J.\u00a0Cheng et al., Two-stream adaptive graph convolutional networks for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp.\u00a012026\u201312035.","DOI":"10.1109\/CVPR.2019.01230"},{"key":"10.3233\/AIC-220268_ref24","doi-asserted-by":"crossref","unstructured":"L.\u00a0Shi, Y.\u00a0Zhang, J.\u00a0Cheng et al., Skeleton-based action recognition with multi-stream adaptive graph convolutional networks, in: IEEE Transactions on Image Processing, Vol.\u00a029, 2020, pp.\u00a09532\u20139545.","DOI":"10.1109\/TIP.2020.3028207"},{"key":"10.3233\/AIC-220268_ref25","doi-asserted-by":"crossref","unstructured":"S.\u00a0Song, C.\u00a0Lan, J.\u00a0Xing et al., Spatio-temporal attention-based LSTM networks for 3D action recognition and detection, in: IEEE Transactions on Image Processing, Vol.\u00a027, 2018, pp.\u00a03459\u20133471.","DOI":"10.1109\/TIP.2018.2818328"},{"key":"10.3233\/AIC-220268_ref26","doi-asserted-by":"crossref","unstructured":"K.\u00a0Su, X.\u00a0Liu, E.\u00a0Shlizerman et al., Predict & cluster: Unsupervised skeleton based action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp.\u00a09631\u20139640.","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"10.3233\/AIC-220268_ref27","doi-asserted-by":"crossref","unstructured":"A.\u00a0Tran and L.-F.\u00a0Cheong, Two-stream flow-guided convolutional attention networks for action recognition, in: Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017, pp.\u00a03110\u20133119.","DOI":"10.1109\/ICCVW.2017.368"},{"key":"10.3233\/AIC-220268_ref28","doi-asserted-by":"crossref","unstructured":"J.\u00a0Trelinski and B.\u00a0Kwolek, Embedded features for 1D CNN-based action recognition on depth maps, in: VISIGRAPP (4: VISAPP), 2021, pp.\u00a0536\u2013543.","DOI":"10.5220\/0010340105360543"},{"key":"10.3233\/AIC-220268_ref29","doi-asserted-by":"crossref","unstructured":"J.\u00a0Tu, M.\u00a0Liu, H.\u00a0Liu et al., Skeleton-based human action recognition using spatial temporal 3D convolutional neural networks, in: 2018 IEEE International Conference on Multimedia and Expo (ICME), IEEE, 2018, pp.\u00a01\u20136.","DOI":"10.1109\/ICME.2018.8486566"},{"key":"10.3233\/AIC-220268_ref30","doi-asserted-by":"crossref","unstructured":"H.\u00a0Wang, Y.\u00a0Mei, J.\u00a0Lin et al., Temporal residual feature learning for efficient 3D convolutional neural network on action recognition task, in: 2020 IEEE Workshop on Signal Processing Systems (SiPS), IEEE, 2020, pp.\u00a01\u20136.","DOI":"10.1109\/SiPS50750.2020.9195240"},{"key":"10.3233\/AIC-220268_ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"10.3233\/AIC-220268_ref32","doi-asserted-by":"crossref","unstructured":"S.\u00a0Yan, Y.\u00a0Xiong, D.\u00a0Lin et al., Spatial temporal graph convolutional networks for skeleton-based action recognition, in: Thirty-Second AAAI Conference on Artificial Intelligence, 2018.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"10.3233\/AIC-220268_ref33","doi-asserted-by":"crossref","unstructured":"B.\u00a0Zhang, L.\u00a0Wang, Z.\u00a0Wang et al., Real-time action recognition with deeply transferred motion vector CNNs, in: IEEE Transactions on Image Processing, Vol.\u00a027, 2018, pp.\u00a02326\u20132339.","DOI":"10.1109\/TIP.2018.2791180"},{"key":"10.3233\/AIC-220268_ref34","doi-asserted-by":"crossref","unstructured":"P.\u00a0Zhang, C.\u00a0Lan, J.\u00a0Xing et al., View adaptive recurrent neural networks for high performance human action recognition from skeleton data, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp.\u00a02117\u20132126.","DOI":"10.1109\/ICCV.2017.233"},{"key":"10.3233\/AIC-220268_ref35","doi-asserted-by":"crossref","unstructured":"P.\u00a0Zhang, C.\u00a0Lan, J.\u00a0Xing et al., View adaptive neural networks for high performance skeleton-based human action recognition, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.\u00a041, 2019, pp.\u00a01963\u20131978.","DOI":"10.1109\/TPAMI.2019.2896631"},{"key":"10.3233\/AIC-220268_ref36","doi-asserted-by":"crossref","unstructured":"P.\u00a0Zhang, C.\u00a0Lan, W.\u00a0Zeng et al., Semantics-guided neural networks for efficient skeleton-based human action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp.\u00a01112\u20131121.","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"10.3233\/AIC-220268_ref37","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Zhang, G.\u00a0Tian, S.\u00a0Zhang et al., A knowledge-based approach for multiagent collaboration in smart home: From activity recognition to guidance service, in: IEEE Transactions on Instrumentation and Measurement, Vol.\u00a069, 2019, pp.\u00a0317\u2013329.","DOI":"10.1109\/TIM.2019.2895931"},{"key":"10.3233\/AIC-220268_ref38","doi-asserted-by":"crossref","unstructured":"B.\u00a0Zhao, X.\u00a0Li, X.\u00a0Lu et al., TTH-RNN: Tensor-train hierarchical recurrent neural network for video summarization, in: IEEE Transactions on Industrial Electronics, Vol.\u00a068, 2020, pp.\u00a03629\u20133637.","DOI":"10.1109\/TIE.2020.2979573"},{"key":"10.3233\/AIC-220268_ref39","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.neucom.2022.07.046","article-title":"Adaptive spatiotemporal graph convolutional network with intermediate aggregation of multi-stream skeleton features for action recognition","volume":"505","author":"Zhao","year":"2022","journal-title":"Neurocomputing"}],"container-title":["AI Communications"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIC-220268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:15:58Z","timestamp":1741626958000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/AIC-220268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":39,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/aic-220268","relation":{},"ISSN":["1875-8452","0921-7126"],"issn-type":[{"type":"electronic","value":"1875-8452"},{"type":"print","value":"0921-7126"}],"subject":[],"published":{"date-parts":[[2023,8,21]]}}}