{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T12:22:20Z","timestamp":1761740540276,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,6,21]],"date-time":"2016-06-21T00:00:00Z","timestamp":1466467200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003513","name":"University of Surrey","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003513","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1007\/s11263-016-0917-2","type":"journal-article","created":{"date-parts":[[2016,6,21]],"date-time":"2016-06-21T06:25:48Z","timestamp":1466490348000},"page":"95-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Hollywood 3D: What are the Best 3D Features for Action Recognition?"],"prefix":"10.1007","volume":"121","author":[{"given":"Simon","family":"Hadfield","sequence":"first","affiliation":[]},{"given":"Karel","family":"Lebeda","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Bowden","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,6,21]]},"reference":[{"key":"917_CR1","unstructured":"Beaudet, P. (1978). Rotationally invariant image operators. In Joint conference on pattern recognition."},{"issue":"4","key":"917_CR2","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1109\/34.993558","volume":"24","author":"S Belongie","year":"2003","unstructured":"Belongie, S., Malik, J., & Puzicha, J. (2003). Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Intelligence, 24(4), 509\u2013522.","journal-title":"IEEE Transactions on Pattern Analysis and Intelligence"},{"key":"917_CR3","doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., & Basri, R. (2005). Actions as space-time shapes. In ICCV.","DOI":"10.1109\/ICCV.2005.28"},{"key":"917_CR4","doi-asserted-by":"crossref","unstructured":"Brand, M., Oliver, N., & Pentland, A. (1997). Coupled hidden Markov models for complex action recognition. In CVPR.","DOI":"10.1109\/CVPR.1997.609450"},{"key":"917_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Qin, L., Ye, Y., Huang, Q., & Tian, Q. (2012). Human daily action analysis with multi-view and color-depth data. In ECCV workshop.","DOI":"10.1007\/978-3-642-33868-7_6"},{"key":"917_CR6","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B., & Schmid, C. (2006). Human detection using oriented histograms of flow and appearance. In Proceedings of the ECCV, Graz, Austria.","DOI":"10.1007\/11744047_33"},{"key":"917_CR7","doi-asserted-by":"crossref","unstructured":"Desai, C., & Ramanan, D. (2012). Detecting actions, poses, and objects with relational phraselets. In ECCV.","DOI":"10.1007\/978-3-642-33765-9_12"},{"key":"917_CR8","doi-asserted-by":"crossref","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 workshop.","DOI":"10.1109\/VSPETS.2005.1570899"},{"issue":"2","key":"917_CR9","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The PASCAL visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"917_CR10","unstructured":"Gilbert, A., & Bowden, R. (2014). Data mining for action recognition. In ACCV."},{"issue":"5","key":"917_CR11","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1109\/TPAMI.2010.144","volume":"33","author":"A Gilbert","year":"2011","unstructured":"Gilbert, A., Illingworth, J., & Bowden, R. (2011). Action recognition using mined hierarchical compound features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 883\u2013897.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"917_CR12","doi-asserted-by":"crossref","unstructured":"Gorelick, L., Blank, M., Shechtman, E., Irani, M., & Basri, R. (2007). Actions as space-time shapes. Pattern Analysis and Machine Intelligence, 29(12), 2247\u20132253.","DOI":"10.1109\/TPAMI.2007.70711"},{"key":"917_CR13","doi-asserted-by":"publisher","unstructured":"Hadfield, S., & Bowden, R. (2013). Hollywood 3d dataset, code and calibration. doi: 10.15126\/surreydata.00808228 . http:\/\/cvssp.org\/Hollywood3D .","DOI":"10.15126\/surreydata.00808228"},{"key":"917_CR14","doi-asserted-by":"crossref","unstructured":"Hadfield, S., & Bowden, R. (2011). Kinecting the dots: Particle based scene flow from depth sensors. In ICCV.","DOI":"10.1109\/ICCV.2011.6126509"},{"key":"917_CR15","doi-asserted-by":"crossref","unstructured":"Hadfield, S., & Bowden, R. (2013). Hollywood 3D: Recognizing actions in 3D natural scenes. In CVPR.","DOI":"10.1109\/CVPR.2013.436"},{"key":"917_CR16","doi-asserted-by":"crossref","unstructured":"Hadfield, S., & Bowden, R. (2014). Scene flow estimation using intelligent cost functions. In BMVC.","DOI":"10.5244\/C.28.108"},{"issue":"3","key":"917_CR17","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1109\/TPAMI.2013.162","volume":"36","author":"S Hadfield","year":"2014","unstructured":"Hadfield, S., & Bowden, R. (2014). Scene particles: Unregularized particle based scene flow estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(3), 564\u2013576.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"917_CR18","doi-asserted-by":"crossref","unstructured":"Hadfield, S., Lebeda, K., & Bowden, R. (2014). Natural action recognition using invariant 3D motion encoding. In ECCV.","DOI":"10.1007\/978-3-319-10605-2_49"},{"key":"917_CR19","doi-asserted-by":"crossref","unstructured":"Harris, C., & Stephens, M. (1988). A combined corner and edge detector. In Alvey vision conference (pp. 147\u2013152).","DOI":"10.5244\/C.2.23"},{"key":"917_CR20","volume-title":"Multiple view geometry in computer vision","author":"R Hartley","year":"2000","unstructured":"Hartley, R., & Zisserman, A. (2000). Multiple view geometry in computer vision. Cambridge: Cambridge University Press."},{"key":"917_CR21","doi-asserted-by":"crossref","unstructured":"Hoai, M., Ladicky, L., & Zisserman, A. (2014). Action recognition from weak alignment of body parts. In BMVC.","DOI":"10.5244\/C.28.86"},{"key":"917_CR22","doi-asserted-by":"crossref","unstructured":"Huguet, F., & Devernay, F. (2007). A variational method for scene flow estimation from stereo sequences. In ICCV.","DOI":"10.1109\/ICCV.2007.4409000"},{"key":"917_CR23","unstructured":"Iosifidis, A., Tefas, A., Nikolaidis, N., & Pitas, I. (2014). Human action recognition in stereoscopic videos based on bag of features and disparity pyramids. In: European signal processing conference."},{"key":"917_CR24","volume-title":"Artificial intelligence: Methods and applications","author":"A Iosifidis","year":"2014","unstructured":"Iosifidis, A., Tefas, A., & Pitas, I. (2014). Multi-view regularized extreme learning machine for human action recognition. In A. Likas, K. Blekas, & D. Kalles (Eds.), Artificial intelligence: Methods and applications. New York: Springer International Publishing."},{"issue":"1","key":"917_CR25","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., & Yu, K. (2013). 3d convolutional neural networks for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1), 221\u2013231.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"917_CR26","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 2014 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1725\u20131732).","DOI":"10.1109\/CVPR.2014.223"},{"key":"917_CR27","unstructured":"Konda, K., & Memisevic, R. (2013). Learning to combine depth and motion. arXiv preprint arXiv:1312.3429 ."},{"key":"917_CR28","doi-asserted-by":"crossref","unstructured":"Kukelova, Z., Bujnak, M., & Pajdla, T. (2008). Polynomial eigenvalue solutions to the 5-pt and 6-pt relative pose problems. In BMVC.","DOI":"10.5244\/C.22.56"},{"key":"917_CR29","doi-asserted-by":"crossref","unstructured":"Laptev, I., & Lindeberg, T. (2003). Space-time interest points. In ICCV.","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"917_CR30","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., & Rozenfeld, B. (2008). Learning realistic human actions from movies. In CVPR.","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"917_CR31","doi-asserted-by":"crossref","unstructured":"Laptev, I., & Perez, P. (2007). Retrieving actions in movies. In ICCV.","DOI":"10.1109\/ICCV.2007.4409105"},{"key":"917_CR32","doi-asserted-by":"crossref","unstructured":"Lebeda, K., Matas, J., & Chum, O. (2012). Fixing the locally optimized RANSAC. In BMVC.","DOI":"10.5244\/C.26.95"},{"key":"917_CR33","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, Z., & Liu, Z. (2010). Action recognition based on a bag of 3D points. In CVPR workshops.","DOI":"10.1109\/CVPRW.2010.5543273"},{"issue":"2","key":"917_CR34","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"key":"917_CR35","doi-asserted-by":"crossref","unstructured":"Mademlis, I., Iosifidis, A., Tefas, A., Nikolaidis, N., & Pitas, I. (2014). Stereoscopic video description for human action recognition. In Symposium on computational intelligence.","DOI":"10.1109\/CIMSIVP.2014.7013263"},{"key":"917_CR36","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., & Schmid, C. (2009). Actions in context. In CVPR.","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"917_CR37","doi-asserted-by":"crossref","unstructured":"Messing, R., Pal, C., & Kautz, H. (2009). Activity recognition using the velocity histories of tracked keypoints. In ICCV.","DOI":"10.1109\/ICCV.2009.5459154"},{"issue":"7","key":"917_CR38","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala, T., Pietik\u00e4inen, M., & \u00e4enp\u00e4\u00e4, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971\u2013987.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"917_CR39","doi-asserted-by":"crossref","unstructured":"Oreifej, O., & Liu, Z. (2013). HON4D: Histogram of oriented 4D normals for activity recognition from depth sequences. In CVPR.","DOI":"10.1109\/CVPR.2013.98"},{"key":"917_CR40","doi-asserted-by":"crossref","unstructured":"Oshin, O., Gilbert, A., & Bowden, R. (2011). Capturing the relative distribution of features for action recognition. In IEEE international conference on automatic face and gesture recognition.","DOI":"10.1109\/FG.2011.5771382"},{"key":"917_CR41","doi-asserted-by":"crossref","unstructured":"Richardt, C., Orr, D., Davies, I., Criminisi, A., & Dodgson, N. (2010). Real-time spatiotemporal stereo matching using the dual-cross-bilateral grid. In ECCV.","DOI":"10.1007\/978-3-642-15558-1_37"},{"issue":"1","key":"917_CR42","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/BF03024331","volume":"19","author":"EB Saff","year":"1997","unstructured":"Saff, E. B., & Kuijlaars, A. B. (1997). Distributing many points on a sphere. The Mathematical Intelligencer, 19(1), 5\u201311.","journal-title":"The Mathematical Intelligencer"},{"key":"917_CR43","doi-asserted-by":"crossref","unstructured":"Sapienza, M., Cuzzolin, F., & Torr, P. (2012). Learning discriminative space-time actions from weakly labelled videos. In BMVC.","DOI":"10.5244\/C.26.123"},{"key":"917_CR44","doi-asserted-by":"crossref","unstructured":"Scharstein, D., & Szeliski, R. (2003). High-accuracy stereo depth maps using structured light. In: IEEE computer society conference on CVPR (Vol.\u00a01).","DOI":"10.1109\/CVPR.2003.1211354"},{"key":"917_CR45","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., & Caputo, B. (2004). Recognizing human actions: A local SVM approach. In ICPR.","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"917_CR46","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Ali, S., & Shah, M. (2007). A 3-dimensional SIFT descriptor and its application to action recognition. In International conference on multimedia.","DOI":"10.1145\/1291233.1291311"},{"key":"917_CR47","first-page":"568","volume":"27","author":"K Simonyan","year":"2014","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. Advances in Neural Information Processing Systems, 27, 568\u2013576.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"917_CR48","doi-asserted-by":"crossref","unstructured":"Torr, P., & Zisserman, A. (1998). Robust computation and parametrization of multiple view relations. In ICCV.","DOI":"10.1109\/ICCV.1998.710798"},{"issue":"3","key":"917_CR49","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1561\/0600000017","volume":"3","author":"T Tuytelaars","year":"2008","unstructured":"Tuytelaars, T., & Mikolajczyk, K. (2008). Local invariant feature detectors\u2014A survey. Foundations and Trends in Computer Graphics and Vision, 3(3), 177\u2013280.","journal-title":"Foundations and Trends in Computer Graphics and Vision"},{"key":"917_CR50","doi-asserted-by":"crossref","unstructured":"Vieira, A. W., Nascimento, E. R., Oliveira, G. L., Liu, Z., & Campos, M. F. (2012). Stop: Space-time occupancy patterns for 3D action recognition from depth map sequences. In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, vol. 7441 of the series Lecture Notes in Computer Science, pp. 252\u2013259.","DOI":"10.1007\/978-3-642-33275-3_31"},{"key":"917_CR51","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., & Liu, C. L. (2011). Action recognition by dense trajectories. In CVPR.","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"917_CR52","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2012). Mining actionlet ensemble for action recognition with depth cameras. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1290\u20131297).","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"917_CR53","doi-asserted-by":"crossref","unstructured":"Willems, G., Tuytelaars, T., & Van\u00a0Gool, L. (2008). An efficient dense and scale-invariant spatio-temporal interest point detector. In: ECCV. Berlin: Springer.","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"917_CR54","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, C., & Tian, Y. (2012). Recognizing actions using depth motion maps-based histograms of oriented gradients. In ACM international conference on multimedia.","DOI":"10.1145\/2393347.2396382"},{"key":"917_CR55","unstructured":"Yao, B., & Fei-Fei, L. (2012). Action recognition with exemplar based 2.5 d graph matching. In ECCV."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0917-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-016-0917-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0917-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0917-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T12:47:22Z","timestamp":1498308442000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-016-0917-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6,21]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["917"],"URL":"https:\/\/doi.org\/10.1007\/s11263-016-0917-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2016,6,21]]}}}