Print Email Facebook Twitter APT: Action localization proposals from dense trajectories Title APT: Action localization proposals from dense trajectories Author Gemert, J.C. Jain, M. Gati, E. Snoek, C.G.M. Faculty Electrical Engineering, Mathematics and Computer Science Department Intelligent Systems Date 2015-09-10 Abstract This paper is on action localization in video with the aid of spatio-temporal proposals. To alleviate the computational expensive segmentation step of existing proposals, we propose bypassing the segmentations completely by generating proposals directly from the dense trajectories used to represent videos during classification. Our Action localization Proposals from dense Trajectories (APT) use an efficient proposal generation algorithm to handle the high number of trajectories in a video. Our spatio-temporal proposals are faster than current methods and outperform the localization and classification accuracy of current proposals on the UCF Sports, UCF 101, and MSR-II video datasets. Corrected version: we fixed a mistake in our UCF-101 ground truth. Numbers are different; conclusions are unchanged To reference this document use: http://resolver.tudelft.nl/uuid:d29d1fa5-18f4-42fa-a041-2048e0c7d7e0 Publisher BMVA Press Source Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), BMVA Press, September 2015. Swansea, UK, September 7-10, 2015. Part of collection Institutional Repository Document type conference paper Rights (c) 2015 The Author(s) Files PDF 328187.pdf 2.32 MB Close viewer /islandora/object/uuid:d29d1fa5-18f4-42fa-a041-2048e0c7d7e0/datastream/OBJ/view