{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T02:47:04Z","timestamp":1789354024061,"version":"build-2803163510"},"reference-count":50,"publisher":"SPIE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,3,4]]},"DOI":"10.1117\/12.2082880","type":"proceedings-article","created":{"date-parts":[[2015,3,5]],"date-time":"2015-03-05T02:31:20Z","timestamp":1425522680000},"page":"94070O","source":"Crossref","is-referenced-by-count":2,"title":["Spatio-temporal action localization for human action recognition in large dataset"],"prefix":"10.1117","volume":"9407","author":[{"given":"Sameh","family":"Megrhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marwa","family":"Jmal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Azeddine","family":"Beghdadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wided","family":"Mseddi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"c1","first-page":"345","article-title":"The state-of-the-art research progress on motion segmen-tation","author":"Liu","year":"2014"},{"key":"c2","first-page":"398","article-title":"Motion segmentation: A review","author":"Zappella","year":"2008"},{"key":"c3","unstructured":"T. Brox, M. Rousson, R. Deriche, and J. Weickert, \u201cColour, texture, and motion in level set based segmentation and tracking,\u201d Image and Vision Computing."},{"key":"c4","first-page":"674","article-title":"An iterative image registration technique with an application to stereo vision.","volume":"81","author":"Lucas","year":"1981"},{"key":"c5","unstructured":"J.-Y. Bouguet, \u201cPyramidal implementation of the affine lucas kanade feature tracker description of the algorithm,\u201d Intel Corporation."},{"key":"c6","doi-asserted-by":"crossref","unstructured":"H. Bay, T. Tuytelaars, and L. Van Gool, \u201cSurf: Speeded up robust features,\u201d in Computer Vision- ECCV\u201906, pp. 404-417.","DOI":"10.1007\/11744023_32"},{"key":"c7","unstructured":"J. R. Uijlings, A. W. Smeulders, and R. J. Scha, \u201cReal-time visual concept classification,\u201d Multimedia, IEEE Transactions on."},{"key":"c8","unstructured":"J.-M. Odobez and P. Bouthemy, \u201cRobust multiresolution estimation of parametric motion models,\u201d Journal of visual communication and image representation."},{"key":"c9","unstructured":"M. Jain, H. J\u00e9gou, and P. Bouthemy, \u201cBetter exploiting motion for better action recognition,\u201d in IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201913), pp. 2555-2562."},{"key":"c10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9"},{"key":"c11","doi-asserted-by":"crossref","unstructured":"D. H. Nga and K. Yanai, \u201cA spatio-temporal feature based on triangulation of dense surf,\u201d in IEEE International Conference on Computer Vision Workshops, ICCVW\u201913, pp. 420-427.","DOI":"10.1109\/ICCVW.2013.62"},{"key":"c12","unstructured":"W. Li, Z. Zhang, and Z. Liu, \u201cExpandable data-driven graphical modeling of human actions based on salient postures,\u201d IEEE Transactions on Circuits and Systems for Video Technology."},{"key":"c13","doi-asserted-by":"crossref","unstructured":"N. Dalal and B. Triggs, \u201cHistograms of oriented gradients for human detection,\u201d in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR\u201905., 1, pp. 886-893.","DOI":"10.1109\/CVPR.2005.177"},{"key":"c14","unstructured":"I. Laptev, \u201cOn space-time interest points,\u201d International Journal of Computer Vision."},{"key":"c15","doi-asserted-by":"publisher","DOI":"10.5244\/C.22"},{"key":"c16","doi-asserted-by":"crossref","unstructured":"G. Willems, T. Tuytelaars, and L. Van Gool, \u201cAn efficient dense and scale-invariant spatio-temporal interest point detector,\u201d in Computer Vision-ECCV\u201908, pp. 650-663.","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"c17","first-page":"357","article-title":"A 3-dimensional sift descriptor and its application to action recog-nition","author":"Scovanner","year":"2007"},{"key":"c18","doi-asserted-by":"crossref","unstructured":"H. Wang, A. Kl\u00e4ser, C. Schmid, and C.-L. Liu, \u201cDense trajectories and motion boundary descriptors for action recognition,\u201d International Journal of Computer Vision, pp. 1-20, 2013.","DOI":"10.1007\/s11263-012-0588-6"},{"key":"c19","doi-asserted-by":"crossref","unstructured":"J. Sun, Y. Mu, S. Yan, and L.-F. Cheong, \u201cActivity recognition using dense long-duration trajectories,\u201d in IEEE International Conference on Multimedia and Expo (ICME\u201910), pp. 322-327.","DOI":"10.1109\/ICME.2010.5583046"},{"key":"c20","doi-asserted-by":"crossref","unstructured":"S. Megrhi, W. Souidene, and A. Beghdadi, \u201cSpatio-temporal salient feature extraction for perceptual content based video retrieval,\u201d in Colour and Visual Computing Symposium (CVCS\u201913), pp. 1-7.","DOI":"10.1109\/CVCS.2013.6626272"},{"key":"c21","first-page":"514","article-title":"Trajectons: Action recognition through the motion analysis of tracked features","author":"Matikainen","year":"2009"},{"key":"c22","doi-asserted-by":"crossref","unstructured":"R. Messing, C. Pal, and H. Kautz, \u201cActivity recognition using the velocity histories of tracked key-points,\u201d in IEEE 12th International Conference on Computer Vision, ICCV\u201909, pp. 104-111.","DOI":"10.1109\/ICCV.2009.5459154"},{"key":"c23","unstructured":"O. Oreifej and Z. Liu, \u201cHon4d: Histogram of oriented 4d normals for activity recognition from depth sequences,\u201d in IEEE Conference on Computer Vision and Pattern Recognition, CVPR\u201913, pp. 716-723."},{"key":"c24","article-title":"Unsupervised learning of human motion models","volume":"V.14","author":"Song","year":"2003"},{"key":"c25","unstructured":"C. Rao, A. Yilmaz, and M. Shah, \u201cView-invariant representation and recognition of actions,\u201d International Journal of Computer Vision."},{"key":"c26","doi-asserted-by":"crossref","unstructured":"N. P. Cuntoor and R. Chellappa, \u201cEpitomic representation of human activities,\u201d in Computer Vision and Pattern Recognition, CVPR\u201907., pp. 1-8.","DOI":"10.1109\/CVPR.2007.383135"},{"key":"c27","unstructured":"D. G. Lowe, \u201cDistinctive image features from scale-invariant keypoints,\u201d International journal ofcom-puter vision."},{"key":"c28","first-page":"1","article-title":"Feature tracking and motion compensation for action recognition.","author":"Uemura","year":"2008"},{"key":"c29","unstructured":"N. Johnson and D. Hogg, \u201cLearning the distribution of object trajectories for event recognition,\u201d Image and vision computing."},{"key":"c30","doi-asserted-by":"crossref","unstructured":"P. Viola, M. J. Jones, and D. Snow, \u201cDetecting pedestrians using patterns of motion and appearance,\u201d in Ninth IEEE International Conference on Computer Vision, ICCV\u201903., pp. 734-741.","DOI":"10.1109\/ICCV.2003.1238422"},{"key":"c31","doi-asserted-by":"crossref","unstructured":"O. Kliper-Gross, Y. Gurovich, T. Hassner, and L. Wolf, \u201cMotion interchange patterns for action recog-nition in unconstrained videos,\u201d in Computer Vision-ECCV\u201912, pp. 256-269.","DOI":"10.1007\/978-3-642-33783-3_19"},{"key":"c32","doi-asserted-by":"crossref","unstructured":"N. Dalal, B. Triggs, and C. Schmid, \u201cHuman detection using oriented histograms of flow and appear ance,\u201d in Computer Vision-ECCV\u201906, pp. 428-441.","DOI":"10.1007\/11744047_33"},{"key":"c33","first-page":"56","article-title":"Real-time action recognition by spatiotemporal semantic and structural forests","author":"Yu","year":"2010"},{"key":"c34","unstructured":"T. Guha and R. K. Ward, \u201cLearning sparse representations for human action recognition,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"c35","unstructured":"K. N. Tran, I. A. Kakadiaris, and S. K. Shah, \u201cModeling motion of body parts for action recognition.,\u201d in BMVC\u201911, pp. 1-12."},{"key":"c36","unstructured":"I. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld, \u201cLearning realistic human actions from movies,\u201d in IEEE Conference on Computer Vision and Pattern Recognition. CVPR\u201908., pp. 1-8."},{"key":"c37","unstructured":"G. Csurka, C. Dance, L. Fan, J. Willamowski, and C. Bray, \u201cVisual categorization with bags of key-points,\u201d in Workshop on statistical learning in computer vision, ECCV\u201904, p. 22."},{"key":"c38","article-title":"Action recognition in videos: from motion capture labs to the web","author":"Brandao Lopes","year":"2010"},{"key":"c39","unstructured":"J. Canny, \u201cA computational approach to edge detection,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"c40","article-title":"Template matching techniques in computer vision","author":"Brunelli","year":"2008"},{"key":"c41","doi-asserted-by":"crossref","unstructured":"D. Sun, S. Roth, and M. J. Black, \u201cSecrets of optical flow estimation and their principles,\u201d in IEEE Conference on Computer Vision and Pattern Recognition, CVPR\u201910., pp. 2432-2439.","DOI":"10.1109\/CVPR.2010.5539939"},{"key":"c42","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume":"abs\/1212.0402","author":"Soomro","year":"2012"},{"key":"c43","unstructured":"Youtube, \u201cStatistiques@ONLINE,\u201d June 2009."},{"key":"c44","article-title":"L1-regularized logistic regression stacking and transductive crf smoothing for action recognition in video","author":"Karaman","year":"2013"},{"key":"c45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"c46","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014"},{"key":"c47","first-page":"412","article-title":"Ordered trajectories for large scale human action recognition","author":"Murthy","year":"2013"},{"key":"c48","article-title":"Lpm for fast action recognition with large number of classes","author":"Shi","year":"2013"},{"key":"c49","article-title":"Lear-inria submission for the thumos workshop","author":"Wang","year":"2013"},{"key":"c50","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume":"abs\/1212.0402","author":"Soomro","year":"2012"}],"event":{"name":"IS&T\/SPIE Electronic Imaging","location":"San Francisco, California, United States"},"container-title":["SPIE Proceedings","Video Surveillance and Transportation Imaging Applications 2015"],"original-title":[],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T18:43:42Z","timestamp":1747766622000},"score":1,"resource":{"primary":{"URL":"http:\/\/proceedings.spiedigitallibrary.org\/proceeding.aspx?doi=10.1117\/12.2082880"}},"subtitle":[],"editor":[{"given":"Robert P.","family":"Loce","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]},{"given":"Eli","family":"Saber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2015,3,4]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1117\/12.2082880","relation":{},"ISSN":["0277-786X"],"issn-type":[{"value":"0277-786X","type":"print"}],"subject":[],"published":{"date-parts":[[2015,3,4]]}}}