메뉴 건너뛰기




Volumn , Issue , 2012, Pages 1314-1321

Sum-product networks for modeling activities with stochastic structure

Author keywords

[No Author keywords available]

Indexed keywords

ACTIVITY DETECTION; ALTERNATIVE CONFIGURATIONS; CLASSIFICATION ACCURACY; DATA SETS; EM ALGORITHMS; HUMAN ACTIVITIES; LINEAR COMPLEXITY; MIXTURE COMPONENTS; MOST PROBABLE EXPLANATION; NUMBER OF LAYERS; PRECISION AND RECALL; PRIMITIVE ACTIONS; SPACETIME; STOCHASTIC STRUCTURE; SUM PRODUCT; TERMINAL NODES; VARIABLE NUMBER; VISUAL WORD;

EID: 84866674206     PISSN: 10636919     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CVPR.2012.6247816     Document Type: Conference Paper
Times cited : (67)

References (27)
  • 1
    • 79955649703 scopus 로고    scopus 로고
    • Human activity analysis: A review
    • J. Aggarwal and M. Ryoo. Human activity analysis: A review. ACM Comput. Surv., 43:16:1-16:43, 2011.
    • (2011) ACM Comput. Surv. , vol.43 , pp. 1601-1643
    • Aggarwal, J.1    Ryoo, M.2
  • 3
    • 84866665047 scopus 로고    scopus 로고
    • A Chains model for localizing group activities in videos
    • M. Amer and S. Todorovic. A Chains model for localizing group activities in videos. In ICCV, 2011.
    • (2011) ICCV
    • Amer, M.1    Todorovic, S.2
  • 4
    • 80052876485 scopus 로고    scopus 로고
    • A probabilistic representation for efficient large scale visual recognition tasks
    • S. Bhattacharya, R. Sukthankar, R. Jin, and M. Shah. A probabilistic representation for efficient large scale visual recognition tasks. In CVPR, 2011.
    • (2011) CVPR
    • Bhattacharya, S.1    Sukthankar, R.2    Jin, R.3    Shah, M.4
  • 5
  • 6
    • 70450202741 scopus 로고    scopus 로고
    • Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos
    • A. Gupta, P. Srinivasan, J. Shi, and L. Davis. Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In CVPR, 2009.
    • (2009) CVPR
    • Gupta, A.1    Srinivasan, P.2    Shi, J.3    Davis, L.4
  • 7
    • 50649089570 scopus 로고    scopus 로고
    • Structure fromstatistics: Unsupervised activity analysis using suffix trees
    • R. Hamid, S. Maddi, A. Bobick, and I. Essa. Structure fromstatistics: Unsupervised activity analysis using suffix trees. In ICCV, pages 1-8, 2007.
    • (2007) ICCV , pp. 1-8
    • Hamid, R.1    Maddi, S.2    Bobick, A.3    Essa, I.4
  • 8
    • 80053141645 scopus 로고    scopus 로고
    • Multidimensional counting grids: Inferring word order from disordered bags of words
    • N. Jojic and A. Perina. Multidimensional counting grids: Inferring word order from disordered bags of words. In UAI, 2011.
    • (2011) UAI
    • Jojic, N.1    Perina, A.2
  • 9
    • 77955993558 scopus 로고    scopus 로고
    • Learning a hierarchy of discriminative space-time neighborhood features for human action recognition
    • A. Kovashka and K. Grauman. Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In CVPR, 2010.
    • (2010) CVPR
    • Kovashka, A.1    Grauman, K.2
  • 10
    • 85161996274 scopus 로고    scopus 로고
    • Beyond actions: Discriminative models for contextual group activities
    • T. Lan, Y. Wang, W. Yang, and G. Mori. Beyond actions: Discriminative models for contextual group activities. In NIPS, 2010.
    • (2010) NIPS
    • Lan, T.1    Wang, Y.2    Yang, W.3    Mori, G.4
  • 12
    • 80052874098 scopus 로고    scopus 로고
    • Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis
    • Q. V. Le, W. Y. Zou, S. Y. Yeung, and A. Y. Ng. Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In CVPR,2011.
    • (2011) CVPR
    • Le, Q.V.1    Zou, W.Y.2    Yeung, S.Y.3    Ng, A.Y.4
  • 13
    • 85101031354 scopus 로고    scopus 로고
    • Recognizing actions by shape-motion prototype trees
    • Z. Lin, Z. Jiang, and L. S. Davis. Recognizing actions by shape-motion prototype trees. In ICCV, 2009.
    • (2009) ICCV
    • Lin, Z.1    Jiang, Z.2    Davis, L.S.3
  • 14
    • 80052874353 scopus 로고    scopus 로고
    • Modeling temporal structure of decomposable motion segments for activityclassification
    • J. Niebles, C.-W. Chen, and L. Fei-Fei. Modeling temporal structure of decomposable motion segments for activityclassification. In ECCV, 2010.
    • (2010) ECCV
    • Niebles, J.1    Chen, C.-W.2    Fei-Fei, L.3
  • 15
    • 45049084813 scopus 로고    scopus 로고
    • Unsupervised learning of human action categories using spatial-temporal words
    • J. Niebles, H. Wang, and L. Fei-Fei. Unsupervised learning of human action categories using spatial-temporal words. IJCV, 79(3):299-318, 2008.
    • (2008) IJCV , vol.79 , Issue.3 , pp. 299-318
    • Niebles, J.1    Wang, H.2    Fei-Fei, L.3
  • 16
    • 80052890615 scopus 로고    scopus 로고
    • A large-scale benchmark dataset for event recognition in surveillance video
    • S. Oh and et al. A large-scale benchmark dataset for event recognition in surveillance video. In CVPR, 2011.
    • (2011) CVPR
    • Oh, S.1
  • 17
    • 80052905394 scopus 로고    scopus 로고
    • Image analysis by counting on a grid
    • A. Perina and N. Jojic. Image analysis by counting on a grid. In CVPR, 2011.
    • (2011) CVPR
    • Perina, A.1    Jojic, N.2
  • 18
    • 80053162579 scopus 로고    scopus 로고
    • Sum-product networks: A new deep architecture
    • H. Poon and P. Domingos. Sum-product networks: A new deep architecture. In UAI, 2011.
    • (2011) UAI
    • Poon, H.1    Domingos, P.2
  • 19
    • 77953187842 scopus 로고    scopus 로고
    • Spatiotemporal relationship match: Video structure comparison for recognition of complex human activities
    • M. S. Ryoo and J. K. Aggarwal. Spatiotemporal relationship match: Video structure comparison for recognition of complex human activities. In ICCV, 2009.
    • (2009) ICCV
    • Ryoo, M.S.1    Aggarwal, J.K.2
  • 20
    • 10044233701 scopus 로고    scopus 로고
    • Recognizing human actions: A local SVM approach
    • C. Schueldt, I. Laptev, and B. Caputo. Recognizing human actions: A local SVM approach. In ICPR, 2004.
    • (2004) ICPR
    • Schueldt, C.1    Laptev, I.2    Caputo, B.3
  • 21
    • 84856636962 scopus 로고    scopus 로고
    • Unsupervised learning of event AND-OR grammar and semantics from video
    • Z. Si, M. Pei, B. Yao, and S.-C. Zhu. Unsupervised learning of event AND-OR grammar and semantics from video. In ICCV, 2011.
    • (2011) ICCV
    • Si, Z.1    Pei, M.2    Yao, B.3    Zhu, S.-C.4
  • 22
    • 80052902614 scopus 로고    scopus 로고
    • Event modeling and recognition using Markov logic networks
    • S. D. Tran and L. S. Davis. Event modeling and recognition using Markov logic networks. In ECCV, 2008.
    • (2008) ECCV
    • Tran, S.D.1    Davis, L.S.2
  • 24
    • 84898428599 scopus 로고    scopus 로고
    • Improving bag-of features action recognition with non-local cues
    • M. M. Ullah, S. N. Parizi, and I. Laptev. Improving bag-of features action recognition with non-local cues. In BMVC, 2010.
    • (2010) BMVC
    • Ullah, M.M.1    Parizi, S.N.2    Laptev, I.3
  • 25
    • 78751648503 scopus 로고    scopus 로고
    • A survey of vision-based methods for action representation, segmentation and recognition
    • D. Weinland, R. Ronfard, and E. Boyer. A survey of vision-based methods for action representation, segmentation and recognition. In CVIU, volume 115, pages 224-241, 2011.
    • (2011) CVIU , vol.115 , pp. 224-241
    • Weinland, D.1    Ronfard, R.2    Boyer, E.3
  • 26
    • 80052908096 scopus 로고    scopus 로고
    • Action recognition using context and appearance distribution features
    • X.Wu, D. Xu, L. Duan, and J. Luo. Action recognition using context and appearance distribution features. In CVPR, 2011.
    • (2011) CVPR
    • Wu, X.1    Xu, D.2    Duan, L.3    Luo, J.4
  • 27
    • 80054879214 scopus 로고    scopus 로고
    • Knowledge based activity recognition with Dynamic Bayesian Network
    • Z. Zeng and Q. Ji. Knowledge based activity recognition with Dynamic Bayesian Network. In ECCV, 2010.
    • (2010) ECCV
    • Zeng, Z.1    Ji, Q.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.