{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T08:24:17Z","timestamp":1761294257591},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T00:00:00Z","timestamp":1612828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T00:00:00Z","timestamp":1612828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Science and Technology Overall Innovation Project of Shaanxi Province","award":["2013KTZB03-03-03"],"award-info":[{"award-number":["2013KTZB03-03-03"]}]},{"name":"Shaanxi Province key project of Research and Development Plan","award":["S2018-YF-ZDGY-0187"],"award-info":[{"award-number":["S2018-YF-ZDGY-0187"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s00521-021-05698-0","type":"journal-article","created":{"date-parts":[[2021,2,10]],"date-time":"2021-02-10T04:54:36Z","timestamp":1612932876000},"page":"9375-9389","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["DM-CTSA: a discriminative multi-focused and complementary temporal\/spatial attention framework for action recognition"],"prefix":"10.1007","volume":"33","author":[{"given":"Ming","family":"Tong","sequence":"first","affiliation":[]},{"given":"Kaibo","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Xing","family":"Yue","sequence":"additional","affiliation":[]},{"given":"Mingyang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,9]]},"reference":[{"issue":"10","key":"5698_CR1","doi-asserted-by":"publisher","first-page":"2504","DOI":"10.1109\/TMM.2019.2907060","volume":"21","author":"T Yu","year":"2019","unstructured":"Yu T, Wang L, Da C, Gu H, Xiang S, Pan C (2019) Weakly semantic guided action recognition. IEEE Trans Multimed 21(10):2504\u20132517","journal-title":"IEEE Trans Multimed"},{"key":"5698_CR2","unstructured":"Ibrahim MS, Mori G (2018) Hierarchical relational networks for group activity recognition and retrieval. In: Proceedings of the European conference on computer vision (ECCV). pp 721\u2013736"},{"key":"5698_CR3","doi-asserted-by":"crossref","unstructured":"Hu JF, Zheng WS, Pan J, Lai J, Zhang J (2018) Deep bilinear learning for rgb-d action recognition. In: Proceedings of the European conference on computer vision (ECCV). pp 335\u2013351","DOI":"10.1007\/978-3-030-01234-2_21"},{"key":"5698_CR4","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"5698_CR5","doi-asserted-by":"crossref","unstructured":"Laptev I, Marszalek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"5698_CR6","doi-asserted-by":"crossref","unstructured":"Crasto N, Weinzaepfel P, Alahari K, Schmid C (2019) MARS: motion-augmented RGB stream for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 7882\u20137891","DOI":"10.1109\/CVPR.2019.00807"},{"key":"5698_CR7","doi-asserted-by":"publisher","first-page":"3957","DOI":"10.1109\/TIP.2020.2967577","volume":"29","author":"S Song","year":"2020","unstructured":"Song S, Liu J, Li Y, Guo Z (2020) Modality compensation network: cross-modal adaptation for action recognition. IEEE Trans Image Process 29:3957\u20133969","journal-title":"IEEE Trans Image Process"},{"key":"5698_CR8","doi-asserted-by":"crossref","unstructured":"Du Y, Yuan C, Li B, Zhao L, Li Y, Hu W (2018) Interaction-aware spatio-temporal pyramid attention networks for action classification. In: Proceedings of the European conference on computer vision (ECCV). pp 373\u2013389","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"5698_CR9","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.neunet.2019.10.009","volume":"122","author":"Y Zhu","year":"2020","unstructured":"Zhu Y, Li R, Yang Y, Ye N (2020) Learning cascade attention for fine-grained image classification. Neural Netw 122:174\u2013182","journal-title":"Neural Netw"},{"issue":"6","key":"5698_CR10","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1007\/s00521-018-3711-y","volume":"31","author":"SV Georgakopoulos","year":"2019","unstructured":"Georgakopoulos SV, Kottari K, Delibasis K, Plagianakos VP, Maglogiannis I (2019) Improving the performance of convolutional neural network for skin image classification using the response of image analysis filters. Neural Comput Appl 31(6):1805\u20131822","journal-title":"Neural Comput Appl"},{"key":"5698_CR11","doi-asserted-by":"crossref","unstructured":"Takikawa T, Acuna D, Jampani V, Fidler S (2019) Gated-scnn: Gated shape cnns for semantic segmentation. In: Proceedings of IEEE international conference on computer vision ( ICCV). pp 5229\u20135238","DOI":"10.1109\/ICCV.2019.00533"},{"key":"5698_CR12","doi-asserted-by":"crossref","unstructured":"Tokunaga H, Acuna D, Jampani V, Fidler S (2019) Adaptive weighting multi-field-of-view CNN for semantic segmentation in pathology. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 12597\u201312606","DOI":"10.1109\/CVPR.2019.01288"},{"key":"5698_CR13","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1109\/TIFS.2020.2965301","volume":"15","author":"M Yang","year":"2020","unstructured":"Yang M, Wen W, Wang X, Shen L, Gao G (2020) Adaptive convolution local and global learning for class-level joint representation of facial recognition with a single sample per data subject. IEEE Trans Inf Forensics Secur 15:2469\u20132484","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"5698_CR14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2957285","author":"D Liu","year":"2020","unstructured":"Liu D, Gao X, Wang N, Li J, Peng C (2020) Coupled attribute learning for heterogeneous face recognition. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2019.2957285","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"5698_CR15","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.neunet.2019.09.009","volume":"121","author":"L Zhou","year":"2020","unstructured":"Zhou L, Gu X (2020) Embedding topological features into convolutional neural network salient object detection. Neural Netw 121:308\u2013318","journal-title":"Neural Netw"},{"key":"5698_CR16","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.neucom.2019.09.023","volume":"377","author":"H Zhang","year":"2020","unstructured":"Zhang H, Guo H, Wang X, Ji Y, Wu QJ (2020) Clothescounter: a framework for star-oriented clothes mining from videos. Neurocomputing 377:38\u201348","journal-title":"Neurocomputing"},{"issue":"11","key":"5698_CR17","doi-asserted-by":"publisher","first-page":"7361","DOI":"10.1007\/s00521-018-3579-x","volume":"31","author":"H Zhang","year":"2019","unstructured":"Zhang H, Ji Y, Huang W, Liu L (2019) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl 31(11):7361\u20137380","journal-title":"Neural Comput Appl"},{"key":"5698_CR18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2921960","author":"M Dixit","year":"2019","unstructured":"Dixit M, Li Y, Vasconcelos N (2019) Semantic fisher scores for task transfer: using objects to classify scenes. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2019.2921960","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"5698_CR19","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1109\/TNNLS.2019.2920374","volume":"31","author":"N He","year":"2019","unstructured":"He N, Fang L, Li S, Plaza J, Plaza A (2019) Skip-connected covariance network for remote sensing scene classification. IEEE Trans Neural Netw Learn Syst 31(5):1461\u20131474","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"5698_CR20","doi-asserted-by":"crossref","unstructured":"Li C, Zhong Q, Xie D, Pu S (2019) Collaborative spatiotemporal feature learning for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 7872\u20137881","DOI":"10.1109\/CVPR.2019.00806"},{"key":"5698_CR21","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of IEEE international conference on computer vision (ICCV). pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"5698_CR22","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? A new model and the Kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 4724\u20134733","DOI":"10.1109\/CVPR.2017.502"},{"key":"5698_CR23","doi-asserted-by":"crossref","unstructured":"Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Darrell T, Saenko K (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 677\u2013691","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"5698_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2019.09.029","volume":"122","author":"Q Wang","year":"2020","unstructured":"Wang Q, Chen K (2020) Multi-label zero-shot human action recognition via joint latent ranking embedding. Neural Netw 122:1\u201323","journal-title":"Neural Netw"},{"key":"5698_CR25","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Proceedings of advances in neural information processing systems (NIPS). pp 568\u2013576"},{"key":"5698_CR26","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 1933\u20131941","DOI":"10.1109\/CVPR.2016.213"},{"key":"5698_CR27","doi-asserted-by":"publisher","first-page":"105820","DOI":"10.1016\/j.asoc.2019.105820","volume":"86","author":"C Dai","year":"2020","unstructured":"Dai C, Liu X, Lai J (2020) Human action recognition using two-stream attention based LSTM networks. Applied Soft Computing 86:105820","journal-title":"Applied Soft Computing"},{"issue":"8","key":"5698_CR28","doi-asserted-by":"publisher","first-page":"3703","DOI":"10.1109\/TIP.2019.2901707","volume":"28","author":"M Lu","year":"2019","unstructured":"Lu M, Li ZN, Wang Y, Pan G (2019) Deep attention network for egocentric action recognition. IEEE Trans Image Process 28(8):3703\u20133713","journal-title":"IEEE Trans Image Process"},{"key":"5698_CR29","doi-asserted-by":"publisher","first-page":"112927","DOI":"10.1016\/j.eswa.2019.112927","volume":"141","author":"S Rahimi","year":"2020","unstructured":"Rahimi S, Aghagolzadeh A, Ezoji M (2020) Human action recognition using double discriminative sparsity preserving projections and discriminant ridge-based classifier based on the GDWL-l1 graph. Expert Syst with Appl 141:112927","journal-title":"Expert Syst with Appl"},{"key":"5698_CR30","doi-asserted-by":"publisher","first-page":"107125","DOI":"10.1016\/j.patcog.2019.107125","volume":"100","author":"N Naveenkumar","year":"2020","unstructured":"Naveenkumar N, Domnic S (2020) Deep ensemble network using distance maps and body part features for skeleton based action recognition. Pattern Recognit 100:107125","journal-title":"Pattern Recognit"},{"key":"5698_CR31","first-page":"8674","volume":"33","author":"Y Li","year":"2019","unstructured":"Li Y, Song S, Li Y, Liu J (2019) Temporal bilinear networks for video action recognition. Proce AAAI Conf Artif Intell 33:8674\u20138681","journal-title":"Proce AAAI Conf Artif Intell"},{"key":"5698_CR32","doi-asserted-by":"crossref","unstructured":"Zhang H, Liu D, Xiong Z (2019) Two-stream action recognition-oriented video super-resolution. In: Proceedings of IEEE international conference on computer vision (ICCV). pp 8799\u20138808","DOI":"10.1109\/ICCV.2019.00889"},{"key":"5698_CR33","doi-asserted-by":"crossref","unstructured":"Li L, Zhang Z, Huang Y, Wang L (2018) Deep temporal feature encoding for action recognition. In: 2018 24th international conference on pattern recognition (ICPR). pp 1109\u20131114","DOI":"10.1109\/ICPR.2018.8546263"},{"key":"5698_CR34","doi-asserted-by":"crossref","unstructured":"Zhu J, Zhu Z, Zou W (2018) End-to-end video-level representation learning for action recognition. In: 2018 24th international conference on pattern recognition (ICPR). pp 645\u2013650","DOI":"10.1109\/ICPR.2018.8545710"},{"key":"5698_CR35","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van GL (2016) Temporal segment networks: Towards good practices for deep action recognition. In: Proceedings of the European conference on computer vision (ECCV). pp 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"5698_CR36","doi-asserted-by":"crossref","unstructured":"Fernando B, Anderson P, Hutter M, Gould S (2016) Discriminative hierarchical rank pooling for activity recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 1924\u20131932","DOI":"10.1109\/CVPR.2016.212"},{"key":"5698_CR37","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1109\/TPAMI.2017.2769085","volume":"40","author":"H Bilen","year":"2018","unstructured":"Bilen H, Fernando B, Gavves E, Vedaldi A (2018) Action recognition with dynamic image networks. IEEE Trans Pattern Anal Mach Intell 40:2799\u20132813","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5698_CR38","doi-asserted-by":"crossref","unstructured":"Meng L, Zhao B, Chang B, Huang G, Sun W, Tung F, Sigal L (2019) Interpretable spatio-temporal attention for video action recognition. In: Proceedings of the IEEE international conference on computer vision workshops (ICCV Workshops)","DOI":"10.1109\/ICCVW.2019.00189"},{"issue":"7","key":"5698_CR39","doi-asserted-by":"publisher","first-page":"3459","DOI":"10.1109\/TIP.2018.2818328","volume":"27","author":"S Song","year":"2018","unstructured":"Song S, Lan C, Xing J, Zeng W, Liu J (2018) Spatio-temporal attention-based LSTM networks for 3D action recognition and detection. IEEE Trans Image Process 27(7):3459\u20133471","journal-title":"IEEE Trans Image Process"},{"key":"5698_CR40","doi-asserted-by":"publisher","first-page":"5783","DOI":"10.1109\/TIP.2020.2984904","volume":"29","author":"H Yang","year":"2020","unstructured":"Yang H, Yuan C, Zhang L, Sun Y, Hu W, Maybank SJ (2020) STA-CNN: Convolutional spatial-temporal attention learning for action recognition. IEEE Trans Image Process 29:5783\u20135793","journal-title":"IEEE Trans Image Process"},{"issue":"8","key":"5698_CR41","doi-asserted-by":"publisher","first-page":"3715","DOI":"10.1109\/TNNLS.2017.2731775","volume":"29","author":"B Ni","year":"2018","unstructured":"Ni B, Li T, Yang X (2018) Learning semantic-aligned action representation. IEEE Trans Neural Netw Learn Syst 29(8):3715\u20133725","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"5698_CR42","doi-asserted-by":"crossref","unstructured":"Li D, Qiu Z, Dai Q, Yao T, Mei T (2018) Recurrent tubelet proposal and recognition networks for action detection. In: Proceedings of the European conference on computer vision (ECCV). pp 303\u2013318","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"5698_CR43","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 conference on computer vision and pattern recognition (CVPR). pp 1227\u20131236","DOI":"10.1109\/CVPR.2019.00132"},{"key":"5698_CR44","unstructured":"Soomro K, Zamir AR, Shah M (2012) UCF101: a dataset of 101 human actions classes from videos in the wild. https:\/\/arxiv.org\/abs\/1212.0402v1"},{"key":"5698_CR45","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) HMDB: a large video database for human motion recognition. In: Proceedings of IEEE international conference on computer vision (ICCV). pp 2556\u20132563","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"5698_CR46","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in pytorch. In: Proceedings of NIPS workshop. pp 1\u20134"},{"key":"5698_CR47","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"5698_CR48","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5698_CR49","doi-asserted-by":"crossref","unstructured":"Zach C, Pock T, Bischof H (2007) A duality based approach for realtime tv-l 1 optical flow. In: Proceedings of the 29th DAGM symposium on pattern recognition. pp 214\u2013223","DOI":"10.1007\/978-3-540-74936-3_22"},{"issue":"5","key":"5698_CR50","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TIP.2018.2791180","volume":"27","author":"B Zhang","year":"2018","unstructured":"Zhang B, Wang L, Wang Z, Qiao Y, Wang H (2018) Real-time action recognition with deeply transferred motion vector CNNs. IEEE Trans Image Process 27(5):2326\u20132339","journal-title":"IEEE Trans Image Process"},{"key":"5698_CR51","doi-asserted-by":"crossref","unstructured":"Wei D, Lim JJ, Zisserman A, Freeman WT (2018) Learning and using the arrow of time. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 8052\u20138060","DOI":"10.1109\/CVPR.2018.00840"},{"issue":"2","key":"5698_CR52","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1109\/TMM.2018.2862341","volume":"21","author":"D Li","year":"2018","unstructured":"Li D, Yao T, Duan LY, Mei T, Rui Y (2018) Unified spatio-temporal attention networks for action recognition in videos. IEEE Trans Multimed 21(2):416\u2013428","journal-title":"IEEE Trans Multimed"},{"key":"5698_CR53","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patcog.2018.08.016","volume":"86","author":"L Chen","year":"2019","unstructured":"Chen L, Song Z, Lu J, Zhou J (2019) Learning principal orientations and residual descriptor for action recognition. Pattern Recognit 86:14\u201326","journal-title":"Pattern Recognit"},{"key":"5698_CR54","doi-asserted-by":"crossref","unstructured":"Zhao J, Snoek CG (2019) Dance with flow: Two-in-one stream action detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 9935\u20139944","DOI":"10.1109\/CVPR.2019.01017"},{"key":"5698_CR55","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.patcog.2019.03.002","volume":"91","author":"P Wang","year":"2019","unstructured":"Wang P, Liu L, Shen C, Shen HT (2019) Order-aware convolutional pooling for video based action recognition. Pattern Recognit 91:357\u2013365","journal-title":"Pattern Recognit"},{"key":"5698_CR56","doi-asserted-by":"crossref","unstructured":"Bo Y, Lu Y, He W (2020) Few-shot learning of video action recognition only based on video contents. In: IEEE winter conference on applications of computer vision (WACV). pp 595\u2013604","DOI":"10.1109\/WACV45572.2020.9093481"},{"key":"5698_CR57","doi-asserted-by":"crossref","unstructured":"Girdhar R, Tran D, Torresani L, Ramanan D (2019) Distinit: Learning video representations without a single labeled video. In: Proceedings of the IEEE international conference on computer vision (ICCV). pp 852\u2013861","DOI":"10.1109\/ICCV.2019.00094"},{"key":"5698_CR58","doi-asserted-by":"crossref","unstructured":"Wang C, Fu H, Ling CX, Du P, Ma H (2020) Region-based global reasoning networks. In: Proceedings of the AAAI conference on artificial intelligence. pp 12136\u201312143","DOI":"10.1609\/aaai.v34i07.6893"},{"key":"5698_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2018.07.028","volume":"85","author":"H Yang","year":"2019","unstructured":"Yang H, Yuan C, Li B, Du Y, Xing J, Hu W, Maybank SJ (2019) Asymmetric 3d convolutional neural networks for action recognition. Pattern Recognit 85:1\u201312","journal-title":"Pattern Recognit"},{"key":"5698_CR60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2919303","author":"B Su","year":"2019","unstructured":"Su B, Wu Y (2019) Learning low-dimensional temporal representations with latent alignments. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2019.2919303","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5698_CR61","doi-asserted-by":"crossref","unstructured":"Pang B, Zha K, Cao H, Shi C, Lu C (2019) Deep rnn framework for visual sequential applications. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 423\u2013432","DOI":"10.1109\/CVPR.2019.00051"},{"key":"5698_CR62","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.patcog.2019.03.005","volume":"92","author":"W Hao","year":"2019","unstructured":"Hao W, Zhang Z (2019) Spatiotemporal distilled dense-connectivity network for video action recognition. Pattern Recognit 92:13\u201324","journal-title":"Pattern Recognit"},{"key":"5698_CR63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2984569","author":"K Liu","year":"2020","unstructured":"Liu K, Liu W, Ma H, Tan M, Gan C (2020) A real-time action representation with temporal encoding and deep compression. IEEE Trans Circ Syst Video Technol. https:\/\/doi.org\/10.1109\/TCSVT.2020.2984569","journal-title":"IEEE Trans Circ Syst Video Technol"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05698-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-05698-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05698-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T21:23:26Z","timestamp":1625693006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-05698-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,9]]},"references-count":63,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["5698"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-05698-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,9]]},"assertion":[{"value":"14 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"All the authors of the manuscript declared that there are no potential conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All the authors of the manuscript declared that there is no research involving human participants and\/or animal.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights"}},{"value":"All the authors of the manuscript declared that there is no material that required informed consent.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}