{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:38Z","timestamp":1740122858770,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,10,13]],"date-time":"2020-10-13T00:00:00Z","timestamp":1602547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,13]],"date-time":"2020-10-13T00:00:00Z","timestamp":1602547200000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s11042-020-09992-2","type":"journal-article","created":{"date-parts":[[2020,10,13]],"date-time":"2020-10-13T09:03:07Z","timestamp":1602579787000},"page":"6203-6220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Weakly-supervised action localization based on seed superpixels"],"prefix":"10.1007","volume":"80","author":[{"given":"Sami","family":"Ullah","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7439-2428","authenticated-orcid":false,"given":"Naeem","family":"Bhatti","sequence":"additional","affiliation":[]},{"given":"Tehreem","family":"Qasim","sequence":"additional","affiliation":[]},{"given":"Najmul","family":"Hassan","sequence":"additional","affiliation":[]},{"given":"Muhammad","family":"Zia","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,13]]},"reference":[{"key":"9992_CR1","unstructured":"Abidi SR, Piccardi M, Williams M Action recognition in still images by latent superpixel classification, arXiv:1507.08363"},{"issue":"11","key":"9992_CR2","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta R, Shaji A, Smith K, Lucchi A, Fua P, S\u00fcsstrunk S (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274\u20132282","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9992_CR3","doi-asserted-by":"crossref","unstructured":"Aljanabi MA, Shnain NA, Lu SF (2017) An image similarity measure based on joint histogram \u2014 entropy for face recognition. In: 2017 3rd IEEE international conference on computer and communications (ICCC), pp 1626\u20131631","DOI":"10.1109\/CompComm.2017.8322815"},{"issue":"3","key":"9992_CR4","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/B:VISI.0000045324.43199.43","volume":"61","author":"A Bruhn","year":"2005","unstructured":"Bruhn A, Weickert J, Schn\u00f6rr C. (2005) Lucas\/kanade meets horn\/schunck: combining local and global optic flow methods. Int J Comput Vis 61 (3):211\u2013231","journal-title":"Int J Comput Vis"},{"key":"9992_CR5","doi-asserted-by":"crossref","unstructured":"Carrara F, Elias P, Sedmidubsk\u00fd J, Zezula P (2019) LSTM-Based real-time action detection and prediction in human motion streams. Multimed Tools Appl pp 1\u201323","DOI":"10.1007\/s11042-019-07827-3"},{"issue":"1","key":"9992_CR6","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/TPAMI.2016.2535231","volume":"39","author":"RG Cinbis","year":"2017","unstructured":"Cinbis RG, Verbeek J, Schmid C (2017) Weakly supervised object localization with multi-fold multiple instance learning. IEEE Trans Pattern Anal Mach Intell 39(1):189\u2013203","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9992_CR7","doi-asserted-by":"crossref","unstructured":"Dedeo\u011flu Y, T\u00f6reyin BU, G\u00fcd\u00fckbay U, \u00c7etin AE (2006) Silhouette-based method for object classification and human action recognition in video. In: European conference on computer vision. Springer, New York, pp 64\u201377","DOI":"10.1007\/11754336_7"},{"issue":"2","key":"9992_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-016-0939-9","volume":"121","author":"L Del Pero","year":"2017","unstructured":"Del Pero L, Ricco S, Sukthankar R, Ferrari V (2017) Behavior discovery and alignment of articulated object classes from unstructured video. Int J Comput Vis 121(2):303\u2013325","journal-title":"Int J Comput Vis"},{"key":"9992_CR9","doi-asserted-by":"crossref","unstructured":"Guermeur Y, Elisseeff A, Paugam-Moisy H (2000) A new multi-class SVM based on a uniform convergence result. In: Proceedings of the IEEE-INNS-ENNS international joint conference on neural networks. IJCNN 2000. neural computing: new challenges and perspectives for the New Millennium,. vol. 4, vol 4, pp 183\u2013188","DOI":"10.1109\/IJCNN.2000.860770"},{"key":"9992_CR10","doi-asserted-by":"crossref","unstructured":"Hu T, Zhu X, Wang S, Duan L (2018) Human interaction recognition using spatial-temporal salient feature. Multimed Tools Appl pp 1\u201321","DOI":"10.1007\/s11042-018-6074-6"},{"issue":"5","key":"9992_CR11","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1007\/s11760-017-1228-y","volume":"12","author":"S Islam","year":"2018","unstructured":"Islam S, Qasim T, Yasir M, Bhatti N, Mahmood H, Zia M (2018) Single-and two-person action recognition based on silhouette shape and optical point descriptors. Signal Image Video Process 12(5):853\u2013860","journal-title":"Signal Image Video Process"},{"key":"9992_CR12","doi-asserted-by":"crossref","unstructured":"Jain M, Gemert JV, J\u00e9gou H, Bouthemy P, Snoek CGM (2014) Action localization with tubelets from motion. In: 2014 IEEE conference on computer vision and pattern recognition, pp 740\u2013747","DOI":"10.1109\/CVPR.2014.100"},{"key":"9992_CR13","doi-asserted-by":"crossref","unstructured":"Jain M, Van Gemert JC, Mensink T, Snoek CG (2015) Objects2action: classifying and localizing actions without any video example. In: Proceedings of the IEEE international conference on computer vision, pp 4588\u20134596","DOI":"10.1109\/ICCV.2015.521"},{"key":"9992_CR14","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"key":"9992_CR15","unstructured":"Lan T, Wang Y, Mori G (2011) Discriminative figure-centric models for joint action localization and recognition. In: Computer vision (ICCV), international conference on IEEE, pp 2003\u20132010"},{"key":"9992_CR16","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li Z, Gavrilyuk K, Gavves E, Jain M, Snoek CG (2018) Videolstm convolves, attends and flows for action recognition. Comput Vis Image Underst 166:41\u201350","journal-title":"Comput Vis Image Underst"},{"issue":"11","key":"9992_CR17","doi-asserted-by":"publisher","first-page":"2596","DOI":"10.1109\/TCYB.2015.2482970","volume":"46","author":"C Liu","year":"2016","unstructured":"Liu C, Wu X, Jia Y (2016) Transfer latent SVM for joint recognition and localization of actions in videos. IEEE Trans Cybern 46(11):2596\u20132608","journal-title":"IEEE Trans Cybern"},{"key":"9992_CR18","doi-asserted-by":"crossref","unstructured":"Liu S, Chen P, Cui X (2017) Action recognition in videos based on weighted hyper-sphere support vector machine. In: Machine learning and cybernetics (ICMLC), 2017 international conference on, IEEE, vol 1, pp 299\u2013304","DOI":"10.1109\/ICMLC.2017.8107780"},{"key":"9992_CR19","unstructured":"Ma F, Zhu L, Yang Y, Zha S, Kundu G, Feiszli M, Shou Z Sf-net: Single-frame supervision for temporal action localization, arXiv:2003.06845"},{"key":"9992_CR20","doi-asserted-by":"crossref","unstructured":"Ma S, Zhang J, Ikizler-Cinbis N, Sclaroff S (2013) Action recognition and localization by hierarchical space-time segments. In: 2013 IEEE international conference on computer vision, pp 2744\u20132751","DOI":"10.1109\/ICCV.2013.341"},{"issue":"2-4","key":"9992_CR21","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1007\/s11263-016-0980-8","volume":"126","author":"S Ma","year":"2018","unstructured":"Ma S, Zhang J, Sclaroff S, Ikizler-Cinbis N, Sigal L (2018) Space-time tree ensemble for action recognition and localization. Int J Comput Vis 126(2-4):314\u2013332","journal-title":"Int J Comput Vis"},{"issue":"2","key":"9992_CR22","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s11760-013-0533-3","volume":"8","author":"U Mahbub","year":"2014","unstructured":"Mahbub U, Imtiaz H, Ahad MAR (2014) Action recognition based on statistical analysis from clustered flow vectors. Signal Image Video Process 8(2):243\u2013253","journal-title":"Signal Image Video Process"},{"key":"9992_CR23","doi-asserted-by":"crossref","unstructured":"Mettes P, Snoek CG (2017) Spatial-aware object embeddings for zero-shot localization and classification of actions. In: Proceedings of the IEEE international conference on computer vision, pp 4443\u20134452","DOI":"10.1109\/ICCV.2017.476"},{"key":"9992_CR24","unstructured":"Mettes P, Snoek CGM, Chang S Localizing actions from video labels and pseudo-annotations, arXiv:1707.09143"},{"issue":"3","key":"9992_CR25","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s11263-018-1120-4","volume":"127","author":"P Mettes","year":"2019","unstructured":"Mettes P, Snoek CGM (2019) Pointly-supervised action localization. Int J Comput Vis 127(3):263\u2013281","journal-title":"Int J Comput Vis"},{"key":"9992_CR26","unstructured":"Mettes P, Snoek CGM (2018) Spatio-temporal instance learning: Action tubes from class supervision, arXiv:1807.02800"},{"key":"9992_CR27","doi-asserted-by":"crossref","unstructured":"Mettes P, Van Gemert JC, Snoek CG (2016) Spot on: action localization from pointly-supervised proposals. In: European conference on computer vision. Springer, New York, pp 437\u2013453","DOI":"10.1007\/978-3-319-46454-1_27"},{"issue":"7","key":"9992_CR28","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1007\/s11760-017-1083-x","volume":"11","author":"M Oszust","year":"2017","unstructured":"Oszust M, Padjasek J, Kasprzyk P (2017) An approach to vision-based localisation with binary features for partially sighted people. Signal Image Video Process 11(7):1261\u20131269","journal-title":"Signal Image Video Process"},{"key":"9992_CR29","doi-asserted-by":"crossref","unstructured":"Raptis M, Kokkinos I, Soatto S (2012) Discovering discriminative action parts from mid-level video representations. In: Computer vision and pattern recognition (CVPR). IEEE conference on, IEEE, 2012, pp 1242\u20131249","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"9992_CR30","doi-asserted-by":"crossref","unstructured":"Raptis M, Sigal L (2013) Poselet key-framing: a model for human activity recognition. In: 2013 IEEE conference on computer vision and pattern recognition, pp 2650\u20132657","DOI":"10.1109\/CVPR.2013.342"},{"key":"9992_CR31","unstructured":"Soomro K, Zamir AR, Shah M UCF101: a dataset of 101 human actions classes from videos in the wild, arXiv:1212.0402"},{"issue":"1","key":"9992_CR32","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1007\/s11042-018-5657-6","volume":"78","author":"Y Su","year":"2019","unstructured":"Su Y, Li Y, Liu A (2019) Open-view human action recognition based on linear discriminant analysis. Multimed Tools Appl 78(1):767\u2013782","journal-title":"Multimed Tools Appl"},{"key":"9992_CR33","doi-asserted-by":"crossref","unstructured":"Tian Y, Sukthankar R, Shah M (2013) Spatiotemporal deformable part models for action detection. In: 2013 IEEE conference on computer vision and pattern recognition, pp 2642\u20132649","DOI":"10.1109\/CVPR.2013.341"},{"key":"9992_CR34","unstructured":"Tran D, Yuan J (2012) Max-margin structured output regression for spatio-temporal action localization. In: Advances in neural information processing systems, pp 350\u2013358"},{"key":"9992_CR35","doi-asserted-by":"crossref","unstructured":"Van Gemert JC, Jain M, Gati E, Snoek CG, et al. (2015) Apt: action localization proposals from dense trajectories. In: BMVC, vol 2, p 4","DOI":"10.5244\/C.29.177"},{"key":"9992_CR36","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/j.neucom.2019.01.008","volume":"333","author":"W Xu","year":"2019","unstructured":"Xu W, Miao Z, Yu J, Ji Q (2019) Action recognition and localization with spatial and temporal contexts. Neurocomputing 333:351\u2013363","journal-title":"Neurocomputing"},{"key":"9992_CR37","doi-asserted-by":"crossref","unstructured":"Yang J, Yuan J (2017) Common action discovery and localization in unconstrained videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2157\u20132166","DOI":"10.1109\/ICCV.2017.237"},{"key":"9992_CR38","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.neucom.2013.10.024","volume":"131","author":"J Yu","year":"2014","unstructured":"Yu J, Jeon M, Pedrycz W (2014) Weighted feature trajectories and concatenated bag-of-features for action recognition. Neurocomputing 131:200\u2013207","journal-title":"Neurocomputing"},{"issue":"8","key":"9992_CR39","doi-asserted-by":"publisher","first-page":"9919","DOI":"10.1007\/s11042-018-6622-0","volume":"78","author":"H Zhang","year":"2019","unstructured":"Zhang H, Xia C, Gao X (2019) Action recognition based on multi-stage jointly training convolutional network. Multimed Tools Appl 78(8):9919\u20139931","journal-title":"Multimed Tools Appl"},{"issue":"4","key":"9992_CR40","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1109\/TMM.2015.2404779","volume":"17","author":"Z Zhou","year":"2015","unstructured":"Zhou Z, Shi F, Wu W (2015) Learning spatial and temporal extents of human actions for action detection. IEEE Trans Multimed 17(4):512\u2013525","journal-title":"IEEE Trans Multimed"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09992-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09992-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09992-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T08:08:23Z","timestamp":1634112503000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09992-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,13]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["9992"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09992-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2020,10,13]]},"assertion":[{"value":"6 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}