{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T15:21:13Z","timestamp":1726500073635},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702066","11747125"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Science and Technology Research Program of Chongqing Education Commission of China","award":["KJZD-M201900601"]},{"DOI":"10.13039\/501100013223","name":"Chongqing Research Program of Basic Research and Frontier Technology","doi-asserted-by":"publisher","award":["cstc2017jcyjAX0256","cstc2018jcyjAX0154"],"id":[{"id":"10.13039\/501100013223","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chongqing Municipal Key Laboratory of Institutions of Higher Education","award":["cqupt-mct-201901"]},{"name":"Technology Foundation of Guizhou Province","award":["QianKeHeJiChu[2020]1Y269"]},{"name":"New academic seedling cultivation and exploration innovation project"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1016\/j.neucom.2020.06.032","type":"journal-article","created":{"date-parts":[[2020,6,16]],"date-time":"2020-06-16T02:12:11Z","timestamp":1592273531000},"page":"304-316","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":76,"special_numbering":"C","title":["Human action recognition using convolutional LSTM and fully-connected LSTM with different attentions"],"prefix":"10.1016","volume":"410","author":[{"given":"Zufan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zongming","family":"Lv","sequence":"additional","affiliation":[]},{"given":"Chenquan","family":"Gan","sequence":"additional","affiliation":[]},{"given":"Qingyi","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2020.06.032_b0005","series-title":"Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO)","first-page":"1921","article-title":"A child caring robot for the dangerous behavior detection based on the object recognition and human action recognition","author":"Nie","year":"2018"},{"issue":"2","key":"10.1016\/j.neucom.2020.06.032_b0010","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/TPAMI.2016.2545669","article-title":"A comprehensive study on cross-view gait based human identification with deep CNNs","volume":"39","author":"Wu","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2020.06.032_b0015","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.1016\/j.neucom.2017.09.080","article-title":"Textual sentiment analysis via three different attention convolutional neural networks and cross-modality consistent regression","volume":"275","author":"Zhang","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2020.06.032_b0020","unstructured":"C. Gan, L. Wang, Z. Zhang, Z. Wang, Sparse attention based separable dilated convolutional neural network for targeted sentiment analysis, Knowl.-Based Syst. 188 (2019) 1\u201310."},{"key":"10.1016\/j.neucom.2020.06.032_b0025","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3169","article-title":"Action recognition by dense trajectories","author":"Wang","year":"2011"},{"key":"10.1016\/j.neucom.2020.06.032_b0030","series-title":"in: Proceedings of the IEEE International Conference on Automatica (ICA)","first-page":"1","article-title":"Action recognition based on object tracking and dense trajectories","author":"Wang","year":"2016"},{"issue":"1","key":"10.1016\/j.neucom.2020.06.032_b0035","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3d convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2020.06.032_b0040","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1725","article-title":"Large-scale video classification with convolutional neural networks","author":"Karpathy","year":"2014"},{"key":"10.1016\/j.neucom.2020.06.032_b0045","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","first-page":"4489","article-title":"Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"2015"},{"key":"10.1016\/j.neucom.2020.06.032_b0050","doi-asserted-by":"crossref","unstructured":"J. Carreira, A. Zisserman, Quo Vadis, Action recognition? A new model and the kinetics dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2017, pp. 4724-4733.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.neucom.2020.06.032_b0055","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3034","article-title":"Dynamic image networks for action recognition","author":"Bilen","year":"2016"},{"key":"10.1016\/j.neucom.2020.06.032_b0060","series-title":"Proceedings of the International Joint Conference on Neural Networks (IJCNN)","first-page":"2865","article-title":"Recent advances in video based human action recognition using deep learning: a review","author":"Wu","year":"2017"},{"key":"10.1016\/j.neucom.2020.06.032_b0065","series-title":"in: Proceeding of the International Conference on Learning Representations (ICLR)","first-page":"1","article-title":"Very Deep Convolutional Networks for Large Scale Image Recognition","author":"Simonyan","year":"2015"},{"key":"10.1016\/j.neucom.2020.06.032_b0070","series-title":"Proceeding of the International Conference on Learning Representations (ICLR)","first-page":"1","article-title":"Delving deeper into convolutional networks for learning video representations","author":"Ballas","year":"2015"},{"key":"10.1016\/j.neucom.2020.06.032_b0075","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4694","article-title":"Beyond short snippets: deep networks for video classification","author":"Ng","year":"2015"},{"key":"10.1016\/j.neucom.2020.06.032_b0080","doi-asserted-by":"crossref","unstructured":"H. Gammulle, S. Denman, S. Sridharan, C. Fookes, Two stream LSTM: a deep fusion framework for human action recognition, in: Proceeding of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2017, pp. 177\u2013186.","DOI":"10.1109\/WACV.2017.27"},{"key":"10.1016\/j.neucom.2020.06.032_b0085","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9378","article-title":"Learning compact recurrent neural networks with block-term tensor decomposition","author":"Ye","year":"2018"},{"key":"10.1016\/j.neucom.2020.06.032_b0090","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"21","article-title":"Global context-aware attention LSTM networks for 3d action recognition","author":"Liu","year":"2017"},{"key":"10.1016\/j.neucom.2020.06.032_b0095","unstructured":"K. Simonyan, A. Zisserman, Two-stream convolutional networks for action recognition in videos, in: Proceedings of the Advances in Neural Information Processing Systems (NIPS), 2014, pp. 568\u2013576."},{"key":"10.1016\/j.neucom.2020.06.032_b0100","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1933","article-title":"Convolutional two-stream network fusion for video action recognition","author":"Feichtenhofer","year":"2016"},{"key":"10.1016\/j.neucom.2020.06.032_b0105","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5699","article-title":"AdaScan: adaptive scan pooling in deep convolutional neural networks for human sction recognition in videos","author":"Kar","year":"2017"},{"key":"10.1016\/j.neucom.2020.06.032_b0110","series-title":"Proceeding of the 14th European Conference on Computer Vision (ECCV)","first-page":"20","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"Wang","year":"2016"},{"issue":"8","key":"10.1016\/j.neucom.2020.06.032_b0115","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1109\/TCSVT.2017.2682196","article-title":"Pooling the convolutional layers in deep convNets for video action recognition","volume":"28","author":"Zhao","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"8","key":"10.1016\/j.neucom.2020.06.032_b0120","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.1016\/j.neucom.2020.06.032_b0125","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2625","article-title":"Long-term recurrent convolutional networks for visual recognition and description","author":"Donahue","year":"2015"},{"issue":"10","key":"10.1016\/j.neucom.2020.06.032_b0130","doi-asserted-by":"crossref","first-page":"4933","DOI":"10.1109\/TIP.2018.2846664","article-title":"Sequential video VLAD: training the aggregation locally and temporally","volume":"27","author":"Xu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2020.06.032_b0135","unstructured":"A. Javidani, A.M. Aznaveh, Learning representative temporal features for action recognition, CoRR (2018) abs\/1802.06724."},{"key":"10.1016\/j.neucom.2020.06.032_b0140","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.sigpro.2017.12.008","article-title":"Recurrent attention network using spatial-temporal relations for action recognition","volume":"145","author":"Zhang","year":"2018","journal-title":"Signal Process."},{"issue":"3","key":"10.1016\/j.neucom.2020.06.032_b0145","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3321511","article-title":"Moving foreground-aware visual attention and key volume mining for human action recognition","volume":"15","author":"Zhang","year":"2019","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"10.1016\/j.neucom.2020.06.032_b0150","unstructured":"S. Sharma, R. Kiros, R. Salakhutdinov, Action recognition using visual attention, CoRR (2015) abs\/1511.04119."},{"key":"10.1016\/j.neucom.2020.06.032_b0155","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","article-title":"VideoLSTM convolves, attends and flows for action recognition","volume":"166","author":"Li","year":"2018","journal-title":"Comput. Vis. Image Underst."},{"issue":"2\u20134","key":"10.1016\/j.neucom.2020.06.032_b0160","first-page":"375","article-title":"Every moment counts: dense detailed labeling of actions in complex videos","volume":"126","author":"Yeung","year":"2015","journal-title":"Int. J. Comput. Vision."},{"key":"10.1016\/j.neucom.2020.06.032_b0165","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.patrec.2018.07.034","article-title":"Joint spatial-temporal attention for action recognition","volume":"112","author":"Yu","year":"2018","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2020.06.032_b0170","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1109\/TIP.2017.2778563","article-title":"Recurrent spatial-temporal attention network for action recognition in videos","volume":"27","author":"Du","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"10.1016\/j.neucom.2020.06.032_b0175","first-page":"416","article-title":"Unified spatio-temporal attention networks for action recognition in videos","volume":"21","author":"Li","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2020.06.032_b0180","doi-asserted-by":"crossref","first-page":"82246","DOI":"10.1109\/ACCESS.2019.2923651","article-title":"R-STAN: Residual spatial-temporal attention network for action recognition","volume":"7","author":"Liu","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2020.06.032_b0185","series-title":"Proceeding of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1617","article-title":"Dynamic tracking attention model for action recognition","author":"Wang","year":"2017"},{"issue":"3","key":"10.1016\/j.neucom.2020.06.032_b0190","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1109\/TCSVT.2018.2808685","article-title":"Two-stream collaborative learning with spatial-temporal attention for video classification","volume":"29","author":"Peng","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2020.06.032_b0195","series-title":"Proceedings of the Advances in Neural Information Processing Systems (NIPS)","first-page":"802","article-title":"Convolutional LSTM network: a machine learning approach for precipitation nowcasting","author":"Shi","year":"2015"},{"key":"10.1016\/j.neucom.2020.06.032_b0200","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1996","article-title":"Recognizing realistic actions from videos in the wild","author":"Liu","year":"2009"},{"key":"10.1016\/j.neucom.2020.06.032_b0205","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","first-page":"2556","article-title":"HMDB: a large video database for human motion recognition","author":"Kuehne","year":"2011"},{"key":"10.1016\/j.neucom.2020.06.032_b0210","unstructured":"K. Soomro, A.R. Zamir, M. Shah, UCF101: a dataset of 101 human actions classes from videos in the wild, CoRR (2012) abs\/1212.0402."},{"key":"10.1016\/j.neucom.2020.06.032_b0215","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231220310031?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231220310031?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,10,20]],"date-time":"2020-10-20T18:41:14Z","timestamp":1603219274000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231220310031"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":43,"alternative-id":["S0925231220310031"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2020.06.032","relation":{},"ISSN":["0925-2312"],"issn-type":[{"type":"print","value":"0925-2312"}],"subject":[],"published":{"date-parts":[[2020,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Human action recognition using convolutional LSTM and fully-connected LSTM with different attentions","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2020.06.032","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2020 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}