{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T12:20:16Z","timestamp":1770985216399,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2017,3,8]],"date-time":"2017-03-08T00:00:00Z","timestamp":1488931200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1007\/s11042-017-4514-3","type":"journal-article","created":{"date-parts":[[2017,3,8]],"date-time":"2017-03-08T11:52:47Z","timestamp":1488973967000},"page":"15065-15081","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Exploring hybrid spatio-temporal convolutional networks for human action recognition"],"prefix":"10.1007","volume":"76","author":[{"given":"Hao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanhua","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erkun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,8]]},"reference":[{"key":"4514_CR1","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 2688\u20132697","author":"A Alfaro","year":"2016","unstructured":"Alfaro A, Mery D, Soto A (2016) Action recognition in video using sparse coding and relative features Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 2688\u20132697"},{"key":"4514_CR2","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 3034\u20133042","author":"H Bilen","year":"2016","unstructured":"Bilen H, Fernando B, Gavves E, Vedaldi A, Gould S (2016) Dynamic image networks for action recognition Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 3034\u20133042"},{"key":"4514_CR3","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2014, I.E. IEEE, pp 596\u2013603","author":"Z Cai","year":"2014","unstructured":"Cai Z, Wang L M, Peng X, Qiao Y (2014) Multi-view super vector for action recognition Conference on computer vision and pattern recognition (CVPR), 2014, I.E. IEEE, pp 596\u2013603"},{"key":"4514_CR4","unstructured":"Diba A, Pazandeh A, Gool LV (2016) Efficient two-stream motion and appearance 3d CNNs for video classfication. arXiv:\n                        1608.08851"},{"key":"4514_CR5","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2009, I.E. IEEE, pp 248\u2013255","author":"J Deng","year":"2009","unstructured":"Deng J, Dong W, Socher R, Li L J, Li K, Li F-F (2009) Imagenet: a large-scale hierarchical image database Conference on computer vision and pattern recognition (CVPR), 2009, I.E. IEEE, pp 248\u2013255"},{"key":"4514_CR6","volume-title":"VS-PETS 2005","author":"P Dollar","year":"2005","unstructured":"Dollar P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatio-temporal features VS-PETS 2005"},{"key":"4514_CR7","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2015, I.E. IEEE, pp 2625\u20132634","author":"J Donahue","year":"2015","unstructured":"Donahue J, Hendricks L A, Rohrbach M, Venugopalan S, Guadarrama S, Saenko K, Darrel T (2015) Long-term recurrent convolutional networks for visual recognition and description Conference on computer vision and pattern recognition (CVPR), 2015, I.E. IEEE, pp 2625\u20132634"},{"key":"4514_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream networks fusion for video action recognition. arXiv:\n                        1604.06573","DOI":"10.1109\/CVPR.2016.213"},{"key":"4514_CR9","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 1924\u20131932","author":"B Fernando","year":"2016","unstructured":"Fernando B, Anderson P, Hutter M, Gounld S (2016) Discriminative hierarchical rank pooling for activity recognition Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 1924\u20131932"},{"key":"4514_CR10","volume-title":"International conference on machine learning (ICML), 2015, pp 448\u2013456","author":"S Ioffe","year":"2015","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift International conference on machine learning (ICML), 2015, pp 448\u2013456"},{"issue":"1","key":"4514_CR11","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"SW Ji","year":"2013","unstructured":"Ji SW, Xu W, Yang M, Yu K (2013) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell (PAMI) 35(1):221\u2013231","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"key":"4514_CR12","doi-asserted-by":"crossref","unstructured":"Jia Y Q, Evan S, Jeff D, Sergey K, Jonathan L, Ross G, Sergio G, Trevor D (2014) Caffe: convolutional architecture for fast feature embedding. arXiv:\n                        1408.5093","DOI":"10.1145\/2647868.2654889"},{"key":"4514_CR13","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2014, I.E. IEEE, pp 1725\u20131732","author":"A Karpathy","year":"2014","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Li Fei-Fei (2014) Large-scale video classification with convolutional neural networks Conference on computer vision and pattern recognition (CVPR), 2014, I.E. IEEE, pp 1725\u20131732"},{"key":"4514_CR14","volume-title":"2008-19th British machine vision conference (BMVC), British machine vision association","author":"A Klaser","year":"2008","unstructured":"Klaser A, Marszalek M, Schmid C (2008) A spatio-temporal descriptor based on 3D-gradients 2008-19th British machine vision conference (BMVC), British machine vision association"},{"key":"4514_CR15","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2015, I.E. IEEE, pp 1054\u20131062","author":"Y Kong","year":"2015","unstructured":"Kong Y, Fu Y (2015) Bilinear heterogeneous information machine for rgbd action recognition Conference on computer vision and pattern recognition (CVPR), 2015, I.E. IEEE, pp 1054\u20131062"},{"key":"4514_CR16","volume-title":"International conference on computer vision (ICCV), 2011, I.E. IEEE, pp 2556\u20132563","author":"H Kuehne","year":"2011","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) HMDB: a large video database for human motion recognition International conference on computer vision (ICCV), 2011, I.E. IEEE, pp 2556\u20132563"},{"issue":"2\u20133","key":"4514_CR17","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev I (2005) On space-time interest points. Int J Comput Vis (IJCV) 64 (2\u20133):107\u2013123","journal-title":"Int J Comput Vis (IJCV)"},{"key":"4514_CR18","unstructured":"Li Z Y, Gavves E, Jain M, Snoek CGM (2016) VideoLSTM convolves, attends and flows for action recognition. arXiv:\n                        1607.01794"},{"key":"4514_CR19","doi-asserted-by":"crossref","unstructured":"Peng X, Wang L M, Wang X, Qiao Y (2016) Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. arXiv:\n                        14054506","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"4514_CR20","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2012, I.E. IEEE, pp 1234\u20131341","author":"S Sadanand","year":"2012","unstructured":"Sadanand S, Corso J J (2012) Action bank: a high-level representation of activity in video Conference on computer vision and pattern recognition (CVPR), 2012, I.E. IEEE, pp 1234\u20131341"},{"key":"4514_CR21","volume-title":"ACM international conference on multimedia (ACM MM), pp 357\u2013360","author":"P Scovanner","year":"2007","unstructured":"Scovanner P, Ali S, Mubarak Shah (2007) A 3-dimensional SIFT descriptor and its application to action recognition ACM international conference on multimedia (ACM MM), pp 357\u2013360"},{"key":"4514_CR22","doi-asserted-by":"crossref","first-page":"2123","DOI":"10.1109\/TPAMI.2015.2505295","volume":"10","author":"A Shahroudy","year":"2016","unstructured":"Shahroudy A, Ng T T, Yang Q, Wang G (2016) Multimodal multipart learning for action recognition in depth videos. IEEE Trans Pattern Anal Mach Intell (PAMI) 10:2123\u20132129","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"key":"4514_CR23","unstructured":"Sharma S, Kiros R, Salakhutdinov R (2015) Action recognition using visual attention. arXiv:\n                        1511.04119"},{"key":"4514_CR24","volume-title":"International conference on computer vision (ICCV), 2015, I.E. IEEE, pp 3200\u20133208","author":"Y Shen","year":"2015","unstructured":"Shen Y, Lin W Y, Yan J C, Xu M L, Wu J X, Wang J D (2015) Person re-identification with correspondence structure learning International conference on computer vision (ICCV), 2015, I.E. IEEE, pp 3200\u20133208"},{"key":"4514_CR25","volume-title":"Annual conference on neural information processing systems (NIPS), pp 568\u2013576","author":"K Simonyan","year":"2014","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos Annual conference on neural information processing systems (NIPS), pp 568\u2013576"},{"key":"4514_CR26","volume-title":"International conference on learning representations (ICLR), pp 1\u201314","author":"K Simonyan","year":"2015","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition International conference on learning representations (ICLR), pp 1\u201314"},{"key":"4514_CR27","unstructured":"Soomro K, Zamir A R, Shah M (2012) UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv:\n                        1212.0402"},{"key":"4514_CR28","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 2818\u20132826","author":"C Szegedy","year":"2016","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J (2016) Rethinking the inception architecture for computer vision Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 2818\u20132826"},{"key":"4514_CR29","volume-title":"International conference on computer vision (ICCV), 2015, I.E. IEEE, pp 4489\u20134497","author":"D Tran","year":"2015","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Manohar Paluri (2015) Learning spatiotemporal features with 3d convolutional networks International conference on computer vision (ICCV), 2015, I.E. IEEE, pp 4489\u20134497"},{"key":"4514_CR30","unstructured":"Varol G, Laptev I, Schmid C (2016) Long-term temporal convolutions for action recognition. arXiv:\n                        1604.04994"},{"key":"4514_CR31","volume-title":"International conference on computer vision (ICCV), 2013, I.E. IEEE, pp 3551\u20133558","author":"H Wang","year":"2013","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories International conference on computer vision (ICCV), 2013, I.E. IEEE, pp 3551\u20133558"},{"key":"4514_CR32","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2015, I.E. IEEE, pp 4305\u20134314","author":"LM Wang","year":"2015","unstructured":"Wang L M, Qiao Y, XO T (2015) Action recognition with trajectory-pooled deep-convolutional descriptors Conference on computer vision and pattern recognition (CVPR), 2015, I.E. IEEE, pp 4305\u20134314"},{"issue":"3","key":"4514_CR33","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1007\/s11263-015-0859-0","volume":"119","author":"LM Wang","year":"2016","unstructured":"Wang L M, Qiao Y, Tang X O (2016) MoFAP: a multi-level representation for action recognition. Int J Comput Vis (IJCV) 119(3):254\u2013271","journal-title":"Int J Comput Vis (IJCV)"},{"key":"4514_CR34","unstructured":"Wang L M, Xiong Y J, Wang Z, Qiao Y, Lin D H, Tang XO, Gool LV (2016) Temproal segment networks: towards good practices for deep action recognition. arXiv:\n                        1608.00859"},{"key":"4514_CR35","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 2658\u20132667","author":"XL Wang","year":"2016","unstructured":"Wang X L, Farhadi A, Gupta A (2016) Action \u223c transformation Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 2658\u20132667"},{"key":"4514_CR36","unstructured":"Wang Y L, Wang S H, Tang J L, O\u2019Hare N, Chang Y, Li BX (2016) Hierarchical attention network for action recognition in videos. arXiv:\n                        1607.0641"},{"key":"4514_CR37","volume-title":"Proceedings of the european conference on computer vision (ECCV), pp 650\u2013663","author":"G Willems","year":"2008","unstructured":"Willems G, Tuytelaars T, Gool L V (2008) An efficient dense and scale-invariant spatio-temporal interest point detector Proceedings of the european conference on computer vision (ECCV), pp 650\u2013663"},{"key":"4514_CR38","volume-title":"ACM international conference on multimedia (ACM MM), pp 461\u2013470","author":"ZX Wu","year":"2015","unstructured":"Wu Z X, Wang X, Jiang Y G, Ye H, Xue X Y (2015) Modeling spatial-temporal clues in a hybrid deep learning framework for video classification ACM international conference on multimedia (ACM MM), pp 461\u2013470"},{"issue":"19","key":"4514_CR39","doi-asserted-by":"crossref","first-page":"12155","DOI":"10.1007\/s11042-015-3112-5","volume":"75","author":"Z Xu","year":"2016","unstructured":"Xu Z, Hu C P, Mei L (2016) Video structured description technology based intelligence analysis of surveillance videos for public security applications. Multimedia Tools and Applications (MTAP) 75 (19):12155\u201312172","journal-title":"Multimedia Tools and Applications (MTAP)"},{"key":"4514_CR40","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.jss.2014.07.024","volume":"102","author":"Z Xu","year":"2015","unstructured":"Xu Z, Liu Y H, Mei L, Hu C P, Chen L (2015) Semantic based representing and organizing surveillance big data using video structural description technology. J Syst Softw 102:217\u2013225","journal-title":"J Syst Softw"},{"issue":"3","key":"4514_CR41","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1007\/s10586-016-0581-x","volume":"19","author":"Z Xu","year":"2016","unstructured":"Xu Z, Mei L, Hu C P, Liu Y H (2016) The big data analytics and applications of the surveillance system using video structured description technology. Clust Comput 19(3):1283\u20131292","journal-title":"Clust Comput"},{"issue":"1\u20132","key":"4514_CR42","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s00607-014-0408-7","volume":"98","author":"Z Xu","year":"2016","unstructured":"Xu Z, Mei L, Liu Y H, Hu C P, Chen L (2016) Semantic enhanced cloud environment for surveillance data management using video structural description. Computing 98(1\u20132):35\u201354","journal-title":"Computing"},{"key":"4514_CR43","doi-asserted-by":"publisher","unstructured":"Yang YH, Deng C, Gao SQ, Liu W, Tao DP, Gao XB (2016) Discriminative multi-instance multi-task learning for 3d action recognition. IEEE Trans Multimedia (TMM). doi:\n                        10.1109\/TMM.2016.2626959","DOI":"10.1109\/TMM.2016.2626959"},{"key":"4514_CR44","first-page":"1","volume":"99","author":"YH Yang","year":"2016","unstructured":"Yang Y H, Deng C, Tao D P, Zhang S T, Liu W, Gao X B (2016) Latent max-margin multitask learning with skelets for 3d action recognition. IEEE Transactions on Cybernetics (TCYB) 99:1\u201310","journal-title":"IEEE Transactions on Cybernetics (TCYB)"},{"key":"4514_CR45","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.sigpro.2015.10.035","volume":"124","author":"YH Yang","year":"2016","unstructured":"Yang Y H, Liu R S, Deng C, Gao X B (2016) Multi-task human action recognition via exploring super-category. Signal Process (SP) 124:36\u201344","journal-title":"Signal Process (SP)"},{"key":"4514_CR46","volume-title":"29th DAGM symposium on pattern recognition, pp 214\u2013223","author":"C Zach","year":"2007","unstructured":"Zach C, Pock T, Bischof H (2007) A duality based approach for realtime TV-l1 optical flow 29th DAGM symposium on pattern recognition, pp 214\u2013223"},{"key":"4514_CR47","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 2718\u20132726","author":"BW Zhang","year":"2016","unstructured":"Zhang B W, Wang L M, Wang Z, Qiao Y, Wang H L (2016) Real-time action recognition with enhanced motion vector CNNs Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 2718\u20132726"},{"key":"4514_CR48","volume-title":"International conference oncomputer vision (ICCV), 2013, I.E. IEEE, pp 3559\u20133566","author":"J Zhu","year":"2013","unstructured":"Zhu J, Wang B Y, Yang X K, Zhang W J, Tu Z W (2013) Action recognition with actons International conference oncomputer vision (ICCV), 2013, I.E. IEEE, pp 3559\u20133566"},{"key":"4514_CR49","volume-title":"Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 1991\u20131999","author":"WJ Zhu","year":"2016","unstructured":"Zhu W J, Hu J, Sun G, Cao X D, Qiao Y (2016) A key volume mining deep framework for action recognition Conference on computer vision and pattern recognition (CVPR), 2016, I.E. IEEE, pp 1991\u20131999"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-4514-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4514-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4514-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,6]],"date-time":"2017-06-06T11:43:16Z","timestamp":1496749396000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-4514-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,8]]},"references-count":49,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2017,7]]}},"alternative-id":["4514"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-4514-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3,8]]}}}