dc.creator | Yu, Gang | |
dc.creator | Goussies, Norberto Adrián | |
dc.creator | Yuan, Junsong | |
dc.creator | Liu, Zicheng | |
dc.date.accessioned | 2020-11-06T16:57:19Z | |
dc.date.accessioned | 2022-10-15T08:54:09Z | |
dc.date.available | 2020-11-06T16:57:19Z | |
dc.date.available | 2022-10-15T08:54:09Z | |
dc.date.created | 2020-11-06T16:57:19Z | |
dc.date.issued | 2011-06 | |
dc.identifier | Yu, Gang; Goussies, Norberto Adrián; Yuan, Junsong; Liu, Zicheng; Fast action detection via discriminative random forest voting and top-K subvolume search; Institute of Electrical and Electronics Engineers; Ieee Transactions On Multimedia; 13; 3; 6-2011; 507-517 | |
dc.identifier | 1520-9210 | |
dc.identifier | http://hdl.handle.net/11336/117819 | |
dc.identifier | CONICET Digital | |
dc.identifier | CONICET | |
dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/4367410 | |
dc.description.abstract | Multiclass action detection in complex scenes is a challenging problem because of cluttered backgrounds and the large intra-class variations in each type of actions. To achieve efficient and robust action detection, we characterize a video as a collection of spatio-temporal interest points, and locate actions via finding spatio-temporal video subvolumes of the highest mutual information score towards each action class. A random forest is constructed to efficiently generate discriminative votes from individual interest points, and a fast top-K subvolume search algorithm is developed to find all action instances in a single round of search. Without significantly degrading the performance, such a top-K search can be performed on down-sampled score volumes for more efficient localization. Experiments on a challenging MSR Action Dataset II validate the effectiveness of our proposed multiclass action detection method. The detection speed is several orders of magnitude faster than existing methods. | |
dc.language | eng | |
dc.publisher | Institute of Electrical and Electronics Engineers | |
dc.relation | info:eu-repo/semantics/altIdentifier/url/http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5730498 | |
dc.relation | info:eu-repo/semantics/altIdentifier/doi/https://doi.org/10.1109/TMM.2011.2128301 | |
dc.rights | https://creativecommons.org/licenses/by-nc-sa/2.5/ar/ | |
dc.rights | info:eu-repo/semantics/restrictedAccess | |
dc.subject | ACTION DETECTION | |
dc.subject | BRANCH AND BOUND | |
dc.subject | RANDOM FOREST | |
dc.subject | TOP-K SEARCH | |
dc.title | Fast action detection via discriminative random forest voting and top-K subvolume search | |
dc.type | info:eu-repo/semantics/article | |
dc.type | info:ar-repo/semantics/artículo | |
dc.type | info:eu-repo/semantics/publishedVersion | |