{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:09:04Z","timestamp":1760609344317,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s12559-021-09851-8","type":"journal-article","created":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T10:03:16Z","timestamp":1614765796000},"page":"698-708","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Discriminative Dictionary Design for Action Classification in Still Images and Videos"],"prefix":"10.1007","volume":"13","author":[{"given":"Abhinaba","family":"Roy","sequence":"first","affiliation":[]},{"given":"Biplab","family":"Banerjee","sequence":"additional","affiliation":[]},{"given":"Amir","family":"Hussain","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3167-2208","authenticated-orcid":false,"given":"Soujanya","family":"Poria","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,3]]},"reference":[{"issue":"11","key":"9851_CR1","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1109\/TPAMI.2012.28","volume":"34","author":"B Alexe","year":"2012","unstructured":"Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows. IEEE Trans Pattern Anal Mach Intell. 2012;34(11):2189\u2013202.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"9851_CR2","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/34.1000236","volume":"24","author":"D Comaniciu","year":"2002","unstructured":"Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell. 2002;24(5):603\u201319.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9851_CR3","doi-asserted-by":"crossref","unstructured":"Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y. Locality-constrained linear coding for image classification. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on.\u00a0IEEE, 2010. pp. 3360\u20133367.","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"9851_CR4","doi-asserted-by":"crossref","unstructured":"Perronnin F, S\u00e1nchez J, Mensink T. Improving the fisher kernel for large-scale image classification. In European conference on computer vision.\u00a0Springer, 2010.\u00a0pp. 143\u2013156.","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"9851_CR5","unstructured":"Cheng G, Wan Y, Saudagar AN, Namuduri K, Buckles BP. Advances in human action recognition: a survey. arXiv preprint 2015. arXiv:1501.05964"},{"key":"9851_CR6","doi-asserted-by":"crossref","unstructured":"Yang W, Wang Y, Mori G. Recognizing human actions from still images with latent poses. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on.\u00a0IEEE, 2010. pp. 2030\u20132037.","DOI":"10.1109\/CVPR.2010.5539879"},{"issue":"2","key":"9851_CR7","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG. Distinctive image features from scale-invariant keypoints. Int J Comput Vis. 2004;60(2):91\u2013110.","journal-title":"Int J Comput Vis"},{"key":"9851_CR8","doi-asserted-by":"crossref","unstructured":"Chatfield K, Lempitsky VS, Vedaldi A, Zisserman A. The devil is in the details: an evaluation of recent feature encoding methods. In BMVC. 2011.\u00a0vol. 2, p. 8.","DOI":"10.5244\/C.25.76"},{"issue":"9","key":"9851_CR9","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D. Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell. 2010;32(9):1627\u201345.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9851_CR10","first-page":"3075","volume":"13","author":"Y Wang","year":"2012","unstructured":"Wang Y, Tran D, Liao Z, Forsyth D. Discriminative hierarchical part-based models for human parsing and action recognition. J Mach Learn Res. 2012;13:3075\u2013102.","journal-title":"J Mach Learn Res"},{"key":"9851_CR11","doi-asserted-by":"crossref","unstructured":"Yao B, Jiang X, Khosla A, Lin AL, Guibas L, Fei-Fei L. Human action recognition by learning bases of action attributes and parts. In 2011 International Conference on Computer Vision.\u00a0IEEE, 2011. pp. 1331\u20131338.","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"9851_CR12","doi-asserted-by":"crossref","unstructured":"Sharma G, Jurie F, Schmid C. Expanded parts model for human attribute and action recognition in still images. In Proc IEEE Conf Comput Vis Pattern Recognit. 2013.\u00a0pp. 652\u2013659.","DOI":"10.1109\/CVPR.2013.90"},{"key":"9851_CR13","doi-asserted-by":"crossref","unstructured":"Zhang L, Li C, Peng P, Xiang X, Song J. Towards optimal vlad for human action recognition from still images. Image and Vision Computing. 2016;.","DOI":"10.1109\/ICASSP.2016.7471995"},{"key":"9851_CR14","doi-asserted-by":"crossref","unstructured":"Juneja M, Vedaldi A, Jawahar C, Zisserman A. Blocks that shout: Distinctive parts for scene classification. In Proc IEEE Conf Comput Vis Pattern Recognit.\u00a02013. pp. 923\u2013930.","DOI":"10.1109\/CVPR.2013.124"},{"key":"9851_CR15","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.cviu.2015.08.002","volume":"141","author":"R Sicre","year":"2015","unstructured":"Sicre R, Jurie F. Discriminative part model for visual recognition. Comput Vis Image Underst. 2015;141:28\u201337.","journal-title":"Comput Vis Image Underst"},{"key":"9851_CR16","doi-asserted-by":"crossref","unstructured":"Zhou Y, Ni B, Hong R, Wang M, Tian Q. Interaction part mining: A mid-level approach for fine-grained action recognition. In Proc IEEE Conf Comput Vis Pattern Recognit. 2015.\u00a0pp. 3323\u20133331.","DOI":"10.1109\/CVPR.2015.7298953"},{"issue":"2\u20133","key":"9851_CR17","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev I. On space-time interest points. Int J Comput Vis. 2005;64(2\u20133):107\u201323.","journal-title":"Int J Comput Vis"},{"key":"9851_CR18","doi-asserted-by":"crossref","unstructured":"Chakraborty B, Holte MB, Moeslund TB, Gonzalez J, Roca FX. A selective spatio-temporal interest point detector for human action recognition in complex scenes. In Computer Vision (iccv), 2011 Ieee International Conference on.\u00a0IEEE, 2011.\u00a0pp. 1776\u20131783.","DOI":"10.1109\/ICCV.2011.6126443"},{"key":"9851_CR19","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C. Action recognition with improved trajectories. In Computer Vision (ICCV), 2013 IEEE International Conference on.\u00a0IEEE, 2013. pp. 3551\u20133558.","DOI":"10.1109\/ICCV.2013.441"},{"issue":"2","key":"9851_CR20","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1006\/cviu.1998.0711","volume":"71","author":"W Xiong","year":"1998","unstructured":"Xiong W, Lee JC-M. Efficient scene change detection and camera motion annotation for video classification. Comput Vis Image Underst. 1998;71(2):166\u201381.","journal-title":"Comput Vis Image Underst"},{"key":"9851_CR21","unstructured":"Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos. In Adv Neural Inf Proces Syst. 2014.\u00a0pp. 568\u2013576."},{"key":"9851_CR22","unstructured":"Shukla P, Biswas KK, Kalra PK. Action recognition using temporal bag-of-words from depth maps. In MVA. 2013.\u00a0pp. 41\u201344."},{"key":"9851_CR23","doi-asserted-by":"crossref","unstructured":"Bettadapura V, Schindler G, Pl\u00f6tz T, Essa I. Augmenting bag-of-words: Data-driven discovery of temporal and structural information for activity recognition. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp. 2619\u20132626. IEEE, 2013.","DOI":"10.1109\/CVPR.2013.338"},{"key":"9851_CR24","unstructured":"Qiu Q, Jiang Z, Chellappa R. Sparse dictionary-based representation and recognition of action attributes. In Computer Vision (ICCV), 2011 IEEE International Conference on.\u00a0IEEE, 2011.\u00a0pp. 707\u2013714."},{"key":"9851_CR25","doi-asserted-by":"crossref","unstructured":"Liu W, Wang Z, Tao D, Yu J. Hessian regularized sparse coding for human action recognition. In International Conference on Multimedia Modeling.\u00a0Springer, 2015. pp. 502\u2013511.","DOI":"10.1007\/978-3-319-14442-9_55"},{"key":"9851_CR26","doi-asserted-by":"crossref","unstructured":"Lu C, Shi J, Jia J. Abnormal event detection at 150 fps in matlab. In Computer Vision (ICCV), 2013 IEEE International Conference on.\u00a0IEEE, 2013. pp. 2720\u20132727.","DOI":"10.1109\/ICCV.2013.338"},{"issue":"1","key":"9851_CR27","first-page":"2617","volume":"14","author":"SR Fanello","year":"2013","unstructured":"Fanello SR, Gori I, Metta G, Odone F. Keep it simple and sparse: Real-time action recognition. J Mach Learn Res. 2013;14(1):2617\u201340.","journal-title":"J Mach Learn Res"},{"issue":"3","key":"9851_CR28","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/TCSVT.2017.2665359","volume":"27","author":"K Xu","year":"2017","unstructured":"Xu K, Jiang X, Sun T. Two-stream dictionary learning architecture for action recognition. IEEE Trans Circuits Syst Video Technol. 2017;27(3):567\u201376.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"9851_CR29","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A. Return of the devil in the details: Delving deep into convolutional nets. arXiv preprint 2014. arXiv:1405.3531","DOI":"10.5244\/C.28.6"},{"key":"9851_CR30","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In Adv Neural Inf Proces Syst.\u00a02012.\u00a0pp. 1097\u20131105."},{"key":"9851_CR31","doi-asserted-by":"crossref","unstructured":"Roy A, Banerjee B, Murino V. Discriminative dictionary design for action classification in still images. In International Conference on Image Analysis and Processing.\u00a0Springer, 2017.\u00a0pp. 160\u2013170.","DOI":"10.1007\/978-3-319-68548-9_15"},{"issue":"1","key":"9851_CR32","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1109\/TPAMI.2007.250608","volume":"29","author":"M Pavan","year":"2007","unstructured":"Pavan M, Pelillo M. Dominant sets and pairwise clustering. IEEE Trans Pattern Anal Mach Intell. 2007;29(1):167\u201372.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9851_CR33","unstructured":"Bishop CM. Pattern recognition. Mach Learn. 2006;128:"},{"key":"9851_CR34","unstructured":"Zhu X, Ghahramani Z. Learning from labeled and unlabeled data with label propagation. 2002."},{"issue":"5","key":"9851_CR35","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s00138-012-0450-4","volume":"24","author":"KK Reddy","year":"2013","unstructured":"Reddy KK, Shah M. Recognizing 50 human action categories of web videos. Mach Vis Appl. 2013;24(5):971\u201381.","journal-title":"Mach Vis Appl"},{"key":"9851_CR36","unstructured":"Li LJ, Su H, Fei-Fei L, Xing EP. Object bank: A high-level image representation for scene classification & semantic feature sparsification. In Adv Neural Inf Proces Syst. 2010.\u00a0pp. 1378\u20131386."},{"key":"9851_CR37","doi-asserted-by":"crossref","unstructured":"Jiang Z, Lin Z, Davis LS. Learning a discriminative dictionary for sparse coding via label consistent k-svd. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on.\u00a0IEEE, 2011. pp. 1697\u20131704.","DOI":"10.1109\/CVPR.2011.5995354"},{"key":"9851_CR38","doi-asserted-by":"crossref","unstructured":"Lazebnik S, Schmid C, Ponce J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906).\u00a0IEEE, 2006.\u00a0vol. 2, pp. 2169\u20132178.","DOI":"10.1109\/CVPR.2006.68"},{"key":"9851_CR39","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0079-6123(06)55002-2","volume":"155","author":"A Oliva","year":"2006","unstructured":"Oliva A, Torralba A. Building the gist of a scene: The role of global image features in recognition. Prog Brain Res. 2006;155:23\u201336.","journal-title":"Prog Brain Res"},{"key":"9851_CR40","doi-asserted-by":"crossref","unstructured":"Sadanand S, Corso JJ. Action bank: A high-level representation of activity in video. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on.\u00a0IEEE, 2012. pp. 1234\u20131241.","DOI":"10.1109\/CVPR.2012.6247806"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-021-09851-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-021-09851-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-021-09851-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T06:34:18Z","timestamp":1724567658000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-021-09851-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,3]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["9851"],"URL":"https:\/\/doi.org\/10.1007\/s12559-021-09851-8","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"type":"print","value":"1866-9956"},{"type":"electronic","value":"1866-9964"}],"subject":[],"published":{"date-parts":[[2021,3,3]]},"assertion":[{"value":"9 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}