{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T00:27:01Z","timestamp":1768091221823,"version":"3.49.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2019,3,30]],"date-time":"2019-03-30T00:00:00Z","timestamp":1553904000000},"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":[[2019,8]]},"DOI":"10.1007\/s11042-019-7429-3","type":"journal-article","created":{"date-parts":[[2019,3,30]],"date-time":"2019-03-30T09:02:46Z","timestamp":1553936566000},"page":"21673-21694","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A correlation based feature representation for first-person activity recognition"],"prefix":"10.1007","volume":"78","author":[{"given":"Reza","family":"Kahani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alireza","family":"Talebpour","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1867-3612","authenticated-orcid":false,"given":"Ahmad","family":"Mahmoudi-Aznaveh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,3,30]]},"reference":[{"key":"7429_CR1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.cviu.2015.10.015","volume":"149","author":"G Abebe","year":"2016","unstructured":"Abebe G, Cavallaro A, Parra X (2016) Robust multi-dimensional motion features for first-person vision activity recognition. Comput Vis Image Underst 149:229\u2013248","journal-title":"Comput Vis Image Underst"},{"key":"7429_CR2","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1145\/1922649.1922653","volume":"43","author":"JK Aggarwal","year":"2011","unstructured":"Aggarwal JK, Ryoo MS (2011) Human activity analysis: a review. ACM Computing Surveys (CSUR) 43:16","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"7429_CR3","unstructured":"Agrawal P, Girshick R, Malik J (2014) Analyzing the performance of multilayer neural networks for object recognition,\" in European Conference on Computer Vision, pp. 329\u2013344"},{"key":"7429_CR4","doi-asserted-by":"crossref","unstructured":"Betancourt A, Morerio P, Regazzoni CS, Rauterberg M (2015) The Evolution of First Person Vision Methods: A Survey","DOI":"10.1109\/TCSVT.2015.2409731"},{"key":"7429_CR5","doi-asserted-by":"crossref","unstructured":"Chatfield K, Lempitsky VS, Vedaldi A, Zisserman A (2011) The devil is in the details: an evaluation of recent feature encoding methods, in BMVC, p. 8","DOI":"10.5244\/C.25.76"},{"key":"7429_CR6","doi-asserted-by":"crossref","unstructured":"Choi J, Jeon WJ, Lee SC (2008) \"Spatio-temporal pyramid matching for sports videos,\" in Proceedings of the 1st ACM international conference on Multimedia information retrieval, pp. 291\u2013297","DOI":"10.1145\/1460096.1460144"},{"key":"7429_CR7","unstructured":"Csurka G, Dance C, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints, in Workshop on statistical learning in computer vision, ECCV, pp. 1\u20132"},{"key":"7429_CR8","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection,\" in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, pp. 886\u2013893"},{"key":"7429_CR9","unstructured":"Dalal N, Triggs B, Schmid C (2006) Human detection using oriented histograms of flow and appearance, in Computer Vision\u2013ECCV 2006, ed: Springer, pp. 428\u2013441"},{"key":"7429_CR10","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 Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pp. 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7429_CR11","unstructured":"Dollar P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatio-temporal features,\" in Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005. 2nd Joint IEEE International Workshop on, pp. 65\u201372"},{"key":"7429_CR12","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, et al. (2015) \"Long-term recurrent convolutional networks for visual recognition and description,\" in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"7429_CR13","unstructured":"Feichtenhofer C, Pinz A, Wildes R (2016) Spatiotemporal residual networks for video action recognition,\" in Advances in Neural Information Processing Systems, pp. 3468\u20133476"},{"key":"7429_CR14","unstructured":"Fei-Fei L, Perona P (2005) A bayesian hierarchical model for learning natural scene categories,\" in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, pp. 524\u2013531"},{"key":"7429_CR15","doi-asserted-by":"crossref","unstructured":"Fu Y (2016) \"Human Activity Recognition and Prediction,\" ed: Springer","DOI":"10.1007\/978-3-319-27004-3"},{"key":"7429_CR16","unstructured":"Gong S, Xiang T (2011) Action Recognition, in Visual Analysis of Behaviour: From Pixels to Semantics, ed London: Springer London, pp. 133\u2013160"},{"key":"7429_CR17","unstructured":"Graham D, Langroudi SHF, Kanan C, Kudithipudi D (2017) Convolutional Drift Networks for Video Classification, arXiv preprint arXiv:1711.01201"},{"key":"7429_CR18","unstructured":"Gregor K, Danihelka I, Graves A, Rezende DJ, Wierstra D (2015) \"DRAW: A recurrent neural network for image generation,\" arXiv preprint arXiv:1502.04623"},{"key":"7429_CR19","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition, arXiv preprint arXiv:1512.03385, 2015"},{"key":"7429_CR20","doi-asserted-by":"crossref","unstructured":"Iwashita Y, Takamine A, Kurazume R, Ryoo M (2014) \"First-person animal activity recognition from egocentric videos,\" in Pattern Recognition (ICPR), 2014 22nd International Conference on, pp. 4310\u20134315","DOI":"10.1109\/ICPR.2014.739"},{"key":"7429_CR21","unstructured":"Jaakkola T, Haussler D (1999) \"Exploiting generative models in discriminative classifiers,\" Advances in neural information processing systems, pp. 487\u2013493"},{"key":"7429_CR22","unstructured":"Jain M, Gemert J, Snoek CG (2014) University of amsterdam at thumos challenge 2014"},{"key":"7429_CR23","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, et al. (2014) Caffe: Convolutional architecture for fast feature embedding, in Proceedings of the ACM International Conference on Multimedia, 2014, pp. 675\u2013678"},{"key":"7429_CR24","unstructured":"Kahani R, Talebpour A, Mahmoudi-Aznaveh A (2016) Time series correlation for first-person videos, in Electrical Engineering (ICEE), 2016 24th Iranian Conference on, 2016, pp. 805\u2013809"},{"key":"7429_CR25","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2014.223"},{"key":"7429_CR26","unstructured":"Kitani KM, Okabe T, Sato Y, Sugimoto A (2011) Fast unsupervised ego-action learning for first-person sports videos, in Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, 2011, pp. 3241\u20133248"},{"key":"7429_CR27","unstructured":"Klaser A, Marsza\u0142ek M, Schmid C (2008) A spatio-temporal descriptor based on 3d-gradients, in BMVC 2008-19th British Machine Vision Conference, pp. 275: 1\u201310"},{"key":"7429_CR28","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1109\/TIP.2016.2556940","volume":"25","author":"Y Kong","year":"2016","unstructured":"Kong Y, Fu Y (2016) Discriminative relational representation learning for RGB-D action recognition. IEEE Trans Image Process 25:2856\u20132865","journal-title":"IEEE Trans Image Process"},{"key":"7429_CR29","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks,\" in Advances in neural information processing systems, pp. 1097\u20131105"},{"key":"7429_CR30","doi-asserted-by":"publisher","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 64:107\u2013123","journal-title":"Int J Comput Vis"},{"key":"7429_CR31","unstructured":"Laptev I, Marsza\u0142ek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies,\" in Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pp. 1\u20138"},{"key":"7429_CR32","doi-asserted-by":"crossref","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) \"Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories,\" in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, pp. 2169\u20132178","DOI":"10.1109\/CVPR.2006.68"},{"key":"7429_CR33","unstructured":"Moreira TP, Menotti D, Pedrini H (2017) First-person action recognition through Visual Rhythm texture description, in Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference on, pp. 2627\u20132631"},{"key":"7429_CR34","unstructured":"Narayan S, Kankanhalli MS, Ramakrishnan KR (2014) Action and Interaction Recognition in First-person videos, in Computer Vision and Pattern Recognition Workshops (CVPRW), 2014 IEEE Conference on, 2014, pp. 526\u2013532"},{"key":"7429_CR35","doi-asserted-by":"crossref","unstructured":"Nowak E, Jurie F, Triggs B (2006) \"Sampling strategies for bag-of-features image classification,\" in Computer Vision\u2013ECCV 2006, ed: Springer, pp. 490\u2013503","DOI":"10.1007\/11744085_38"},{"key":"7429_CR36","unstructured":"Ozkan F, Arabaci MA, Surer E, Temizel A (2017) Boosted Multiple Kernel Learning for First-Person Activity Recognition, arXiv preprint arXiv:1702.06799"},{"key":"7429_CR37","unstructured":"Perronnin F, Dance C (2007) Fisher kernels on visual vocabularies for image categorization,\" in Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on, pp. 1\u20138"},{"key":"7429_CR38","unstructured":"Perronnin F, S\u00e1nchez J, Mensink T (2010) Improving the fisher kernel for large-scale image classification, in Computer Vision\u2013ECCV 2010, ed: Springer, pp. 143\u2013156"},{"key":"7429_CR39","unstructured":"Philbin J, Chum O, Isard M, Sivic J, Zisserman A (2008) Lost in quantization: Improving particular object retrieval in large scale image databases, in Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pp. 1\u20138"},{"key":"7429_CR40","doi-asserted-by":"crossref","unstructured":"Piergiovanni A, Fan C, Ryoo MS (2017) Learning latent sub-events in activity videos using temporal attention filters, in Proceedings of the 31st AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11240"},{"key":"7429_CR41","unstructured":"Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition,\" in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 806\u2013813"},{"key":"7429_CR42","unstructured":"Ryoo MS, Matthies L (2013) \"First-person activity recognition: What are they doing to me?,\" in Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp. 2730\u20132737"},{"key":"7429_CR43","unstructured":"Ryoo M, Matthies L (2015) First-Person Activity Recognition: Feature, Temporal Structure, and Prediction,\" International Journal of Computer Vision, pp. 1\u201322"},{"key":"7429_CR44","doi-asserted-by":"crossref","unstructured":"Ryoo M, Matthies L (2016) Video-based convolutional neural networks for activity recognition from robot-centric videos,\" in SPIE Defense+ Security, pp. 98370R-98370R-6","DOI":"10.1117\/12.2229531"},{"key":"7429_CR45","unstructured":"Ryoo MS, Rothrock B, Matthies L (2015) Pooled motion features for first-person videos, in Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on, pp. 896\u2013904"},{"key":"7429_CR46","unstructured":"Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition,\" in Proceedings of the 15th international conference on Multimedia, pp. 357\u2013360"},{"key":"7429_CR47","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos, in Advances in Neural Information Processing Systems, , pp. 568\u2013576"},{"key":"7429_CR48","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition,\" arXiv preprint arXiv:1409.1556"},{"key":"7429_CR49","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition, ICLR"},{"key":"7429_CR50","unstructured":"Sudhakaran S, Lanz O (2017) Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactions, in Computer Vision Workshop (ICCVW), 2017 IEEE International Conference on, pp. 2339\u20132346"},{"key":"7429_CR51","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. (2015) Going deeper with convolutions, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139"},{"key":"7429_CR52","unstructured":"van Gemert JC, Geusebroek JM, Veenman CJ, Smeulders AW (2008) Kernel codebooks for scene categorization, in Computer Vision\u2013ECCV 2008, ed: Springer, pp. 696\u2013709"},{"key":"7429_CR53","unstructured":"Wang X (2011) Action recognition using topic models,\" in Visual Analysis of Humans, ed: Springer, pp. 311\u2013332"},{"key":"7429_CR54","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories, in Computer Vision (ICCV), 2013 IEEE International Conference on, 2013, pp. 3551\u20133558"},{"key":"7429_CR55","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang H, Kl\u00e4ser A, Schmid C, Liu C-L (2013) Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis 103:60\u201379","journal-title":"Int J Comput Vis"},{"key":"7429_CR56","first-page":"914","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,\" Pattern Analysis and Machine Intelligence. IEEE Transactions on 36:914\u2013927","journal-title":"IEEE Transactions on"},{"key":"7429_CR57","unstructured":"Wang L, Qiao Y, Tang X (2015) \"Action recognition with trajectory-pooled deep-convolutional descriptors,\" arXiv preprint arXiv:1505.04868"},{"key":"7429_CR58","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, et al. (2016) Temporal segment networks: towards good practices for deep action recognition, in European Conference on Computer Vision, pp. 20\u201336"},{"key":"7429_CR59","doi-asserted-by":"crossref","unstructured":"Wang X, Gao L, Song J, Zhen X, Sebe N, Shen HT (2017) Deep appearance and motion learning for egocentric activity recognition, Neurocomputing","DOI":"10.1016\/j.neucom.2017.08.063"},{"key":"7429_CR60","unstructured":"Willems G, Tuytelaars T, Van Gool L (2008) An efficient dense and scale-invariant spatio-temporal interest point detector, in Computer Vision\u2013ECCV 2008, ed: Springer, pp. 650\u2013663"},{"key":"7429_CR61","doi-asserted-by":"publisher","first-page":"2984","DOI":"10.1109\/TIP.2015.2438540","volume":"24","author":"Y Yan","year":"2015","unstructured":"Yan Y, Ricci E, Liu G, Sebe N (2015) Egocentric daily activity recognition via multitask clustering. IEEE Trans Image Process 24:2984\u20132995","journal-title":"IEEE Trans Image Process"},{"key":"7429_CR62","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1109\/TCSVT.2013.2240916","volume":"23","author":"X Zhen","year":"2013","unstructured":"Zhen X, Shao L, Tao D, Li X (2013) Embedding motion and structure features for action recognition. IEEE Transactions on Circuits and Systems for Video Technology 23:1182\u20131190","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-7429-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-7429-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-7429-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T21:55:23Z","timestamp":1663192523000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-7429-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,30]]},"references-count":62,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["7429"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-7429-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,30]]},"assertion":[{"value":"4 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}