Fast action detection via discriminative random forest voting and top-K subvolume search | ||
| dc.conicet.organizacion | Nanyang Technological University | |
| dc.conicet.organizacion | Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación | |
| dc.conicet.organizacion | Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria | |
| dc.conicet.organizacion | Nanyang Technological University | |
| dc.conicet.organizacion | Microsoft Research | |
| dc.contributor.author | Yu, Gang | |
| dc.contributor.author | Goussies, Norberto Adrián | |
| dc.contributor.author | Yuan, Junsong | |
| dc.contributor.author | Liu, Zicheng | |
| dc.date.issued | 2011-06 | |
| 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. | es |
| dc.description.fil | Fil: Yu, Gang. Nanyang Technological University; Singapur | |
| dc.description.fil | Fil: Goussies, Norberto Adrián. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria; Argentina | |
| dc.description.fil | Fil: Yuan, Junsong. Nanyang Technological University; Singapur | |
| dc.description.fil | Fil: Liu, Zicheng. Microsoft Research; Estados Unidos | |
| dc.format | application/pdf | es |
| dc.identifier.citation | 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 | es |
| dc.identifier.institucional | CONICET | |
| dc.identifier.issn | 1520-9210 | es |
| dc.identifier.repo | CONICET Digital | |
| dc.identifier.uri | http://hdl.handle.net/11336/117819 | |
| dc.journal.ciudad | Nueva York | es |
| dc.journal.number | 3 | es |
| dc.journal.pagination | 507-517 | es |
| dc.journal.pais | Estados Unidos | es |
| dc.journal.title | Ieee Transactions On Multimedia | es |
| dc.journal.volume | 13 | es |
| dc.language.iso | eng | es |
| dc.publisher | Institute of Electrical and Electronics Engineers | es |
| dc.relation.alternativeid | info:eu-repo/semantics/altIdentifier/url/http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5730498 | |
| dc.relation.alternativeid | info:eu-repo/semantics/altIdentifier/doi/https://doi.org/10.1109/TMM.2011.2128301 | |
| dc.rights | info:eu-repo/semantics/openAccess | * |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc-sa/2.5/ar/ | * |
| dc.subject | ACTION DETECTION | es |
| dc.subject | BRANCH AND BOUND | es |
| dc.subject | RANDOM FOREST | es |
| dc.subject | TOP-K SEARCH | es |
| dc.subject.classification | Ciencias de la Computación | es |
| dc.subject.classification | Ciencias de la Computación e Información | es |
| dc.subject.classification | CIENCIAS NATURALES Y EXACTAS | es |
| dc.title | Fast action detection via discriminative random forest voting and top-K subvolume search | es |
| dc.type | info:eu-repo/semantics/article | |
| dc.type | info:ar-repo/semantics/artículo | |
| dc.type | info:eu-repo/semantics/publishedVersion | |
Archivos
Bloque original
Cargando...
- Nombre:
- CONICET_Digital_Nro.90baf2fd-b089-4937-be64-3026ddf54d7a_A.pdf
- Tamaño:
- 3.16 MB
- Formato:
- Adobe Portable Document Format