{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T15:58:37Z","timestamp":1769443117507,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2018,2,14]],"date-time":"2018-02-14T00:00:00Z","timestamp":1518566400000},"content-version":"tdm","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":[[2019,3]]},"DOI":"10.1007\/s11042-018-5738-6","type":"journal-article","created":{"date-parts":[[2018,2,14]],"date-time":"2018-02-14T11:43:18Z","timestamp":1518608598000},"page":"5731-5749","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Multi-view depth-based pairwise feature learning for person-person interaction recognition"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3497-4391","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Howard","family":"Leung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,2,14]]},"reference":[{"key":"5738_CR1","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.patrec.2014.04.011","volume":"48","author":"JK Aggarwal","year":"2014","unstructured":"Aggarwal JK, Xia L (2014) Human activity recognition from 3d data: a review. Pattern Recogn Lett 48:70\u201380","journal-title":"Pattern Recogn Lett"},{"key":"5738_CR2","unstructured":"Amer MR, Todorovic S (2012) Sum-product networks for modeling activitie with stochastic structure. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1314\u20131321"},{"issue":"3","key":"5738_CR3","first-page":"27","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27","journal-title":"ACM Trans Intell Syst Technol (TIST)"},{"issue":"3","key":"5738_CR4","doi-asserted-by":"publisher","first-page":"4405","DOI":"10.1007\/s11042-015-3177-1","volume":"76","author":"C Chen","year":"2017","unstructured":"Chen C, Jafari R, Kehtarnavaz N (2017) A survey of depth and inertial sensor fusion for human action recognition. Multimed Tools Appl 76(3):4405\u20134425","journal-title":"Multimed Tools Appl"},{"key":"5738_CR5","doi-asserted-by":"crossref","unstructured":"Choi W, Shahid K, Savarese S (2011) Learning context for collective activity recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 3273\u20133280","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"5738_CR6","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-642-33765-9_16","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Wongun Choi","year":"2012","unstructured":"Choi W, Savarese S (2012) A unified framework for multi-target tracking and collective activity recognition. In: Fitzgibbon A, Lazebnik S, Perona P, Sato Y, Schmid C (eds) ECCV 2012, Part IV. LNCS, vol 7575. Springer, Heidelberg, pp 215\u2013230"},{"key":"5738_CR7","doi-asserted-by":"crossref","unstructured":"Desai C, Ramanan D, Fowlkes C (2010) Discriminative models for static human-object interactions. In: IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp 9\u201316","DOI":"10.1109\/CVPRW.2010.5543176"},{"key":"5738_CR8","unstructured":"Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1110\u20131 118"},{"issue":"7","key":"5738_CR9","doi-asserted-by":"publisher","first-page":"3010","DOI":"10.1109\/TIP.2016.2552404","volume":"25","author":"Y Du","year":"2016","unstructured":"Du Y, Fu Y, Wang L (2016) Representation learning of temporal dynamics for skeleton-based action recognition. IEEE Trans Image Process 25(7):3010\u20133022","journal-title":"IEEE Trans Image Process"},{"key":"5738_CR10","doi-asserted-by":"crossref","unstructured":"Filipovych R, Ribeiro E (2008) Recognizing primitive interactions by exploring actor-object states. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1\u20137","DOI":"10.1109\/CVPR.2008.4587726"},{"key":"5738_CR11","unstructured":"Gong S, Xiang T (2003) Recognition of group activities using dynamic probabilistic networks. IEEE international conference on computer vision (ICCV), pp 742\u2013749"},{"issue":"10","key":"5738_CR12","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta A, Kembhavi A, Davis LS (2009) Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE Trans Pattern Anal Mach Intell 31(10):1775\u20131789","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"5738_CR13","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1007\/s00138-014-0596-3","volume":"25","author":"I Guyon","year":"2014","unstructured":"Guyon I, Athitsos V, Jangyodsuk P, Escalante HJ (2014) The ChaLearn gesture dataset (CGD 2011). Mach Vis Appl 25(8):1929\u20131951","journal-title":"Mach Vis Appl"},{"key":"5738_CR14","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.cviu.2017.01.011","volume":"158","author":"F Han","year":"2017","unstructured":"Han F, Reily B, Hoff W, Zhang H (2017) Space-time representation of people based on 3D skeletal data: a review. Comput Vis Image Underst 158:85\u2013105","journal-title":"Comput Vis Image Underst"},{"key":"5738_CR15","doi-asserted-by":"crossref","unstructured":"Ji Y, Ye G, Cheng H (2014) Interactive body part contrast mining for human interaction recognition. In: Multimedia and expo workshops (ICMEW), pp 1\u20136","DOI":"10.1109\/ICMEW.2014.6890714"},{"issue":"1","key":"5738_CR16","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1109\/TIP.2015.2498410","volume":"25","author":"Y Kong","year":"2015","unstructured":"Kong Y, Fu Y (2015) Close human interaction recognition using patch-aware models. IEEE Trans Image Process 25(1):167\u2013178","journal-title":"IEEE Trans Image Process"},{"key":"5738_CR17","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/978-3-642-33718-5_22","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Yu Kong","year":"2012","unstructured":"Kong Y, Jia Y, Fu Y (2012) Learning human interaction by interactive phrases. In: Fitzgibbon A, Lazebnik S, Perona P, Sato Y, Schmid C (eds) ECCV 2012, Part I. LNCS, vol 7572. Springer, Heidelberg, pp 300\u2013313"},{"issue":"9","key":"5738_CR18","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2014.2303090","volume":"36","author":"Y Kong","year":"2014","unstructured":"Kong Y, Jia Y, Fu Y (2014) Interactive phrases: semantic descriptions for human interaction recognition. IEEE Trans Pattern Anal Mach Intell 36(9):1775\u20131788","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"5738_CR19","doi-asserted-by":"publisher","first-page":"1549","DOI":"10.1109\/TPAMI.2011.228","volume":"34","author":"T Lan","year":"2012","unstructured":"Lan T, Wang Y, Yang W, Robinovitch SN, Mori G (2012) Discriminative latent models for recognizing contextual group activities. IEEE Trans Pattern Anal Mach Intell 34(8):1549\u20131562","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5738_CR20","doi-asserted-by":"crossref","unstructured":"Laptev I, Marszalek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587756"},{"issue":"11","key":"5738_CR21","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1109\/TMM.2016.2614228","volume":"18","author":"M Li","year":"2016","unstructured":"Li M, Leung H (2016) Multiview skeletal interaction recognition using active joint interaction graph. IEEE Trans Multimed 18(11):2293\u20132302","journal-title":"IEEE Trans Multimed"},{"key":"5738_CR22","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/978-3-642-33885-4_25","volume-title":"Computer Vision \u2013 ECCV 2012. Workshops and Demonstrations","author":"Shigeyuki Odashima","year":"2012","unstructured":"Odashima S, Shimosaka M, Kaneko T, Fukui R, Sato T (2012) Collective activity localization with contextual spatial pyramid. In: Fusiello A, Murino V, Cucchiara R (eds) ECCV 2012 Ws\/Demos, Part III. LNCS, vol 7585. Springer, Heidelberg, pp 243\u2013252"},{"issue":"12","key":"5738_CR23","doi-asserted-by":"publisher","first-page":"2441","DOI":"10.1109\/TPAMI.2012.24","volume":"34","author":"A Patron-Perez","year":"2012","unstructured":"Patron-Perez A, Marszalek M, Reid I, Zisserman A (2012) Structured learning of human interactions in tv shows. IEEE Trans Pattern Anal Mach Intell 34 (12):2441\u20132453","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"5738_CR24","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/TPAMI.2011.158","volume":"34","author":"A Prest","year":"2012","unstructured":"Prest A, Schmid C, Ferrari V (2012) Weakly supervised learning of interactions between humans and objects. IEEE Trans Pattern Anal Mach Intell 34(3):601\u2013614","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5738_CR25","doi-asserted-by":"crossref","unstructured":"Raptis M, Sigal L (2013) Poselet key-framing: a model for human activity recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 2650\u20132657","DOI":"10.1109\/CVPR.2013.342"},{"key":"5738_CR26","doi-asserted-by":"crossref","unstructured":"Ryoo MS, Aggarwal JK (2006) Recognition of composite human activities through context-free grammar based representation. In: IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 1709\u20131718","DOI":"10.1109\/CVPR.2006.242"},{"key":"5738_CR27","doi-asserted-by":"crossref","unstructured":"Ryoo M, Aggarwal J (2009) Spatio-temporal relationship match: video structure comparison for recognition of complex human activities. In: IEEE international conference on computer vision (ICCV), pp 1593\u20131600","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"5738_CR28","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng TT, Wang G (2016) NTU RGB+ D: a large scale dataset for 3D human activity analysis. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1010\u20131019","DOI":"10.1109\/CVPR.2016.115"},{"key":"5738_CR29","doi-asserted-by":"crossref","unstructured":"Shotton J, Fitzgibbon A, Cook M, Sharp T, Finocchio M, Moore R, Kipman A, Blake A (2011) Real-time human pose recognition in parts from single depth images. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1297\u20131304","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"5738_CR30","doi-asserted-by":"crossref","unstructured":"Vahdat A, Gao B, Ranjbar M, Mori G (2011) A discriminative key pose sequence model for recognizing human interactions. In: IEEE international conference on computer vision workshops (ICCVW), pp 1729\u20131736","DOI":"10.1109\/ICCVW.2011.6130458"},{"key":"5738_CR31","doi-asserted-by":"crossref","unstructured":"Vieira A, Nascimento E, Oliveira G, Liu Z, Campos M (2012) Stop: space-time occupancy patterns for 3D action recognition from depth map sequences. In: Iberoamerican congress on pattern recognition. Buenos Aires, pp 252\u2013259","DOI":"10.1007\/978-3-642-33275-3_31"},{"key":"5738_CR32","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1007\/978-3-642-33709-3_62","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Jiang Wang","year":"2012","unstructured":"Wang J, Liu Z, Chorowski J, Chen Z, Wu Y (2012) Robust 3D action recognition with random occupancy patterns. In: Fitzgibbon A, Lazebnik S, Perona P, Sato Y, Schmid C (eds) ECCV 2012, Part II. LNCS, vol 7573. Springer, Heidelberg, pp 872\u2013885"},{"issue":"5","key":"5738_CR33","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1109\/TPAMI.2013.198","volume":"36","author":"J Wang","year":"2014","unstructured":"Wang J, Liu Z, Wu Y, Yuan J (2014) Learning actionlet ensemble for 3D human action recognition. IEEE Trans Pattern Anal Mach Intell 36(5):914\u2013927","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5738_CR34","doi-asserted-by":"crossref","unstructured":"Xu N, Liu A, Nie W, Wong Y, Li F, Su Y (2015) Multi-modal & multi-view & interactive benchmark dataset for human action recognition. In: ACM international conference on multimedia, pp 1195\u20131198","DOI":"10.1145\/2733373.2806315"},{"key":"5738_CR35","doi-asserted-by":"crossref","unstructured":"Yao B, Fei-Fei L (2010) Modeling mutual context of object and human pose in human-object interaction activities. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 17\u201324","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"5738_CR36","doi-asserted-by":"crossref","unstructured":"Yao A, Gall J, Fanelli G, Van Gool L (2011) Does human action recognition benefit from pose estimation? In: Proceedings of the 22nd British machine vision conference (BMVC), pp 6.71\u201367.11","DOI":"10.5244\/C.25.67"},{"key":"5738_CR37","first-page":"149","volume-title":"Lecture Notes in Computer Science","author":"Mao Ye","year":"2013","unstructured":"Ye M, Zhang Q, Wang L, Zhu J, Yang R, Gall J (2013) A survey on human motion analysis from depth data. In: Grzegorzek M, Theobalt C, Koch R, Kolb A (eds) Time-of-flight and depth imaging. LNCS, vol 8200. Springer, Heidelberg, pp 149\u2013187"},{"key":"5738_CR38","doi-asserted-by":"crossref","unstructured":"Yu TH, Kim TK, Cipolla R (2010) Real-time action recognition by spatiotemporal semantic and structural forests. In: British machine vision conference (BMVC), pp 1\u20137","DOI":"10.5244\/C.24.52"},{"key":"5738_CR39","doi-asserted-by":"crossref","unstructured":"Yun K, Honorio J, Chattopadhyay D, Berg TL, Samaras D (2012) Two-person interaction detection using body-pose features and multiple instance learning. In: IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp 28\u201335","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"5738_CR40","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.patcog.2016.05.019","volume":"60","author":"J Zhang","year":"2016","unstructured":"Zhang J, Li W, Ogunbona PO, Wang P, Tang C (2016) RGB-D-based action recognition datasets: a survey. Pattern Recogn 60:86\u2013105","journal-title":"Pattern Recogn"},{"key":"5738_CR41","doi-asserted-by":"crossref","unstructured":"Zhang S, Liu X, Xiao J (2017) On geometric features for skeleton-based action recognition using multilayer LSTM networks. In: IEEE winter conference on applications of computer vision (WACV), pp 148\u2013157","DOI":"10.1109\/WACV.2017.24"},{"key":"5738_CR42","doi-asserted-by":"crossref","unstructured":"Zhu W, Lan C, Xing J, Zeng W, Li Y, Shen L, Xie X (2016) Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: AAAI, pp 3697\u20133703","DOI":"10.1609\/aaai.v30i1.10451"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-5738-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5738-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5738-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T09:44:08Z","timestamp":1660470248000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-5738-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,14]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["5738"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-5738-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,14]]},"assertion":[{"value":"27 September 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 December 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}