Efficient search of Top-K video subvolumes for multi-instance action detection

Action detection was formulated as a subvolume mutual information maximization problem in [8], where each subvolume identifies where and when the action occurs in the video. Despite the fact that the proposed branch-and-bound algorithm can find the best subvolume efficiently for low resolution video...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Goussies, N.A
Otros Autores: Liu, Z., Yuan, J.
Formato: Acta de conferencia Capítulo de libro
Lenguaje:Inglés
Publicado: 2010
Acceso en línea:Registro en Scopus
DOI
Handle
Registro en la Biblioteca Digital
Aporte de:Registro referencial: Solicitar el recurso aquí
LEADER 06957caa a22007817a 4500
001 PAPER-7498
003 AR-BaUEN
005 20230518203715.0
008 190411s2010 xx ||||fo|||| 10| 0 eng|d
024 7 |2 scopus  |a 2-s2.0-78349239606 
040 |a Scopus  |b spa  |c AR-BaUEN  |d AR-BaUEN 
100 1 |a Goussies, N.A. 
245 1 0 |a Efficient search of Top-K video subvolumes for multi-instance action detection 
260 |c 2010 
270 1 0 |m Goussies, N. A.; DC - FCEyN, Univ. de Buenos AiresArgentina; email: ngoussie@dc.uba.ar 
506 |2 openaire  |e Política editorial 
504 |a Laptev, I., On space-time interest points (2005) International Journal of Computer Vision, 64 (2-3), pp. 107-123 
504 |a Bentley, J., Programming pearls: Algorithm design techniques (1984) Commun. ACM, 27 (9), pp. 865-873 
504 |a Schuldt, C., Laptev, I., Caputo, B., Recognizing human actions: A local svm approach (2004) Proc. IEEE Conf. on Pattern Recognition 
504 |a Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B., Learning realistic human actions from movies (2008) Proc. IEEE Conf. on Computer Vision and Pattern Recognition 
504 |a Reddy, K.K., Liu, J., Shah, M., Incremental action recognition using feature-tree (2009) Proc. IEEE Intl. Conf. on Computer Vision 
504 |a Shechtman, E., Irani, M., Space-time behavior based correlation (2005) Proc. IEEE Conf. on Computer Vision and Pattern Recognition 
504 |a Ke, Y., Sukthankar, R., Hebert, M., Event detection in crowded videos (2007) Proc. IEEE International Conf. on Computer Vision 
504 |a Yuan, J., Liu, Z., Wu, Y., Discriminative subvolume search for efficient action detection (2009) Proc. IEEE Conf. on Computer Vision and Pattern Recognition 
504 |a Hu, Y., Cao, L., Lv, F., Yan, S., Gong, Y., Huang, T.S., Action detection in complex scenes with spatial and temporal ambiguities (2009) Proc. IEEE Intl. Conf. on Computer Vision 
504 |a Lampert, C.H., Blaschko, M.B., Hofmann, T., Beyond sliding windows: Object localization by efficient subwindow search (2008) Proc. IEEE Conf. on Computer Vision and Pattern Recognition 
504 |a Yuan, J., Liu, Z., Wu, Y., Zhang, Z., Speeding up spatio-temporal sliding-window search for efficient event detection in crowded videos (2009) ACM Multimeida Workshop on Events in Multimedia 
504 |a Bobick, A.F., Davis, J.W., The recognition of human movement using temporal templates (2001) IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 23 (3), pp. 257-267 
504 |a Rodriguez, M.D., Ahmed, J., Shah, M., Action mach a spatio-temporal maximum average correlation height filter for action recognition (2008) Proc. IEEE Conf. on Computer Vision and Pattern Recognition 
504 |a Weinland, E.B.D., Ronfard, R., Free viewpoint action recognition using motion history volumes (2006) Computer Vision and Image Understanding, 104 (2-3), pp. 207-229 
504 |a Ke, Y., Sukthankar, R., Hebert, M., Efficient visual event detection using volumetric features (2005) Proc. IEEE International Conf. on Computer Vision 
504 |a Yang, M., Lv, F., Xu, W., Yu, K., Gong, Y., Human action detection by boosting efficient motion features (2009) IEEE Workshop on Video-oriented Object and Event Classification in Conjunction with ICCV, , Kyoto, Japan, Sept.29-Oct.2 
504 |a Lin, Z., Jiang, Z., Davis, L.S., Recognizing actions by shape-motion prototype trees (2009) Proc. IEEE Intl. Conf. on Computer Vision 
504 |a Jiang, H., Drew, M.S., Li, Z.-N., Successive convex matching for action detection (2006) Proc. IEEE Conf. on Computer Vision and Pattern Recognition 
520 3 |a Action detection was formulated as a subvolume mutual information maximization problem in [8], where each subvolume identifies where and when the action occurs in the video. Despite the fact that the proposed branch-and-bound algorithm can find the best subvolume efficiently for low resolution videos, it is still not efficient enough to perform multiinstance detection in videos of high spatial resolution. In this paper we develop an algorithm that further speeds up the subvolume search and targets on real-time multi-instance action detection for high resolution videos (e.g. 320 × 240 or higher). Unlike the previous branch-and-bound search technique which restarts a new search for each action instance, we find the Top-K subvolumes simultaneously with a single round of search. To handle the larger spatial resolution, we downsample the volume of videos for a more efficient upperbound estimation. To validate our algorithm, we perform experiments on a challenging dataset of 54 video sequences where each video consists of several actions performed by different people in a crowded environment. The experiments show that our method is not only efficient, but also capable of handling action variations caused by performing speed and style changes, spatial scale changes, as well as cluttered and moving background. © 2010 IEEE.  |l eng 
593 |a DC - FCEyN, Univ. de Buenos Aires, Argentina 
593 |a Microsoft Research, Redmond, WA, United States 
593 |a School of EEE, Nanyang Technological University, Singapore, 39798, Singapore 
690 1 0 |a ACTION RECOGNITION 
690 1 0 |a BRANCH-AND-BOUND 
690 1 0 |a ACTION RECOGNITION 
690 1 0 |a BRANCH AND BOUNDS 
690 1 0 |a BRANCH-AND-BOUND ALGORITHMS 
690 1 0 |a DATA SETS 
690 1 0 |a HIGH RESOLUTION 
690 1 0 |a HIGH SPATIAL RESOLUTION 
690 1 0 |a LOW RESOLUTION VIDEO 
690 1 0 |a MUTUAL INFORMATION MAXIMIZATION 
690 1 0 |a SEARCH TECHNIQUE 
690 1 0 |a SPATIAL RESOLUTION 
690 1 0 |a SPATIAL SCALE 
690 1 0 |a SUBVOLUMES 
690 1 0 |a UPPER BOUND 
690 1 0 |a VIDEO SEQUENCES 
690 1 0 |a IMAGE RESOLUTION 
690 1 0 |a VIDEO RECORDING 
690 1 0 |a ALGORITHMS 
700 1 |a Liu, Z. 
700 1 |a Yuan, J. 
711 2 |c Singapore  |d 19 July 2010 through 23 July 2010  |g Código de la conferencia: 82118 
773 0 |d 2010  |h pp. 328-333  |p IEEE Int. Conf. Multimedia Expo, ICME  |n 2010 IEEE International Conference on Multimedia and Expo, ICME 2010  |z 9781424474912  |t 2010 IEEE International Conference on Multimedia and Expo, ICME 2010 
856 4 1 |u https://www.scopus.com/inward/record.uri?eid=2-s2.0-78349239606&doi=10.1109%2fICME.2010.5583547&partnerID=40&md5=e453ae4a08d5338ffe4400678a9917e0  |y Registro en Scopus 
856 4 0 |u https://doi.org/10.1109/ICME.2010.5583547  |y DOI 
856 4 0 |u https://hdl.handle.net/20.500.12110/paper_97814244_v_n_p328_Goussies  |y Handle 
856 4 0 |u https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97814244_v_n_p328_Goussies  |y Registro en la Biblioteca Digital 
961 |a paper_97814244_v_n_p328_Goussies  |b paper  |c PE 
962 |a info:eu-repo/semantics/conferenceObject  |a info:ar-repo/semantics/documento de conferencia  |b info:eu-repo/semantics/publishedVersion 
999 |c 68451