메뉴 건너뛰기




Volumn , Issue , 2011, Pages 651-658

Correlative multi-label multi-instance image annotation

Author keywords

[No Author keywords available]

Indexed keywords

ANNOTATION PERFORMANCE; CO-OCCURENCE MATRIX; DISTANCE-BASED; IMAGE ANNOTATION; IMAGE REGIONS; LOCAL REGION; MODEL TRAINING; MULTI-LABEL; MULTIPLE LABELS; REAL IMAGES; SEMANTIC CONCEPT; TRAINING SETS; VISUAL FEATURE;

EID: 84863042274     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICCV.2011.6126300     Document Type: Conference Paper
Times cited : (100)

References (31)
  • 1
    • 69549118313 scopus 로고    scopus 로고
    • Unsupervised learning of probabilistic object models (poms) for object classification, segmentation, and recognition using knowledge propagation
    • I
    • Y. Chen, L. Zhu, A. Yuille, and H.-J. Zhang. Unsupervised learning of probabilistic object models (poms) for object classification, segmentation, and recognition using knowledge propagation. TPAMI2009. I
    • (2009) TPAMI
    • Chen, Y.1    Zhu, L.2    Yuille, A.3    Zhang, H.-J.4
  • 2
    • 0035423154 scopus 로고    scopus 로고
    • Unsupervised segmentation of color-texture regions in images and video
    • 2
    • Y. Deng and b.s. Manjunath. Unsupervised segmentation of color-texture regions in images and video. PAMI, 23(8): 800-810, 2001. 2
    • (2001) PAMI , vol.23 , Issue.8 , pp. 800-810
    • Deng, Y.1    Manjunath, B.S.2
  • 3
    • 0038401728 scopus 로고    scopus 로고
    • Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary
    • 6, 7
    • P. Duygulu, K. Barnard, J. d. Freitas, and D. Forsyth. Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In ECCV, 2002. 6, 7
    • (2002) ECCV
    • Duygulu, P.1    Barnard, K.2    Freitas, J.D.3    Forsyth, D.4
  • 4
    • 76649137444 scopus 로고    scopus 로고
    • A kernel method for multilabelled classification
    • 1, 6, 7
    • A. Elisseetl and J. Weston. A kernel method for multilabelled classification. In NIPS, 2002. 1, 6, 7
    • (2002) NIPS
    • Elisseetl, A.1    Weston, J.2
  • 5
    • 9644254228 scopus 로고    scopus 로고
    • Efficient graphbased image segmentation
    • 2
    • P. Felzenszwalb and D. Huttenlocher. Efficient graphbased image segmentation. IJCV, 59(2): 167-181, 2004. 2
    • (2004) IJCV , vol.59 , Issue.2 , pp. 167-181
    • Felzenszwalb, P.1    Huttenlocher, D.2
  • 6
    • 5044225521 scopus 로고    scopus 로고
    • Multiple bernoulli relevance models for image and video annotation
    • 1
    • S. L. Feng, R. Manmatha, and V. Lavrenko. Multiple bernoulli relevance models for image and video annotation. In CVPR, 2004. 1
    • (2004) CVPR
    • Feng, S.L.1    Manmatha, R.2    Lavrenko, V.3
  • 7
    • 33847172327 scopus 로고    scopus 로고
    • Clustering by passing messages between data points
    • 5, 7
    • B. Frey and D. Dueck. Clustering by passing messages between data points. Science, vol.315, 2007. 5, 7
    • (2007) Science , vol.315
    • Frey, B.1    Dueck, D.2
  • 8
    • 33745767102 scopus 로고    scopus 로고
    • Collective multilabel classification
    • 1
    • N. Ghamrawi and A. McCallum. Collective multilabel classification. In CIKM, 2005. 1
    • (2005) CIKM
    • Ghamrawi, N.1    McCallum, A.2
  • 9
    • 77953202699 scopus 로고    scopus 로고
    • Tagprop: Discriminative metric learning in nearest neighbor models for image auto-annotation
    • 1, 6, 7
    • M. Guillaumin, T Mensink, J. Verbeek, and C. Schmid. Tagprop: Discriminative metric learning in nearest neighbor models for image auto-annotation. In ICCV, 2009. 1, 6, 7
    • (2009) ICCV
    • Guillaumin, M.1    Mensink, T.2    Verbeek, J.3    Schmid, C.4
  • 10
    • 5044223520 scopus 로고    scopus 로고
    • Multiscale conditional random fields for image labeling
    • 1
    • X. He, R. S. Zemel, and M. A. Carreira-Perpinan. Multiscale conditional random fields for image labeling. In CVPR, 2004. 1
    • (2004) CVPR
    • He, X.1    Zemel, R.S.2    Carreira-Perpinan, M.A.3
  • 11
    • 70450164149 scopus 로고    scopus 로고
    • Learning a distance metric from multi-instance multi-label data
    • 1
    • R. Jin, S. Wang, and Z.-H. Zhou. Learning a distance metric from multi-instance multi-label data. In CVPR, 2009. 1
    • (2009) CVPR
    • Jin, R.1    Wang, S.2    Zhou, Z.-H.3
  • 12
    • 0001547779 scopus 로고
    • The cutting-plane method for solving convex programs
    • 6
    • J. Kelley. The cutting-plane method for solving convex programs. JSIAM 1960. 6
    • (1960) JSIAM
    • Kelley, J.1
  • 13
    • 50649087214 scopus 로고    scopus 로고
    • Spatially coherent latent topic model for concurrent segmentation and classification of objects and scenes
    • 1
    • F.-F. Li. Spatially coherent latent topic model for concurrent segmentation and classification of objects and scenes. ICCV 2007. 1
    • (2007) ICCV
    • Li, F.-F.1
  • 14
    • 0035358496 scopus 로고    scopus 로고
    • Representing and recognizing the visual appearance of materials using threedimensional textons
    • 6
    • T. Leung and J. Malik. Representing and recognizing the visual appearance of materials using threedimensional textons. IJCV, 43(1 ): 29-44, 2001. 6
    • (2001) IJCV , vol.43 , Issue.1 , pp. 29-44
    • Leung, T.1    Malik, J.2
  • 15
    • 77953193733 scopus 로고    scopus 로고
    • Drosophila gene expression pattern annotation through multi-instance multi-label learning
    • 1
    • Y-X. Li, S. Ji, S. Kumar, J. Ye, and Z.-H. Zhou. Drosophila gene expression pattern annotation through multi-instance multi-label learning. In IlCAI, 2009. 1
    • (2009) IlCAI
    • Li, Y.-X.1    Ji, S.2    Kumar, S.3    Ye, J.4    Zhou, Z.-H.5
  • 16
    • 79951514444 scopus 로고    scopus 로고
    • Unified tag analysis with multi-edge graph
    • 1, 6
    • D. Liu, S. Yan, Y Rui, and H.-J. Zhang. Unified tag analysis with multi-edge graph. ACM MM 2010. 1, 6
    • (2010) ACM MM
    • Liu, D.1    Yan, S.2    Rui, Y.3    Zhang, H.-J.4
  • 17
    • 70449580491 scopus 로고    scopus 로고
    • A new baseline for image annotation
    • 1, 6, 7
    • A. Makadia, V. Pavlovic, and S. Kumar. A new baseline for image annotation. In ECCV, 2008. 1, 6, 7
    • (2008) ECCV
    • Makadia, A.1    Pavlovic, V.2    Kumar, S.3
  • 18
    • 84863048229 scopus 로고    scopus 로고
    • Reverse multi-label leaming
    • 1, 6, 7
    • J. Petterson and T. Caetano. Reverse multi-label leaming. In NIPS, 2010. 1, 6, 7
    • (2010) NIPS
    • Petterson, J.1    Caetano, T.2
  • 20
    • 33845596932 scopus 로고    scopus 로고
    • Using multiple segmentations to discover objects and their extent in image collections
    • 2
    • B. Russell, A. Efros, J. Sivic, W. Freeman, and A. Zisserman. Using multiple segmentations to discover objects and their extent in image collections. In CVPR, 2006. 2
    • (2006) CVPR
    • Russell, B.1    Efros, A.2    Sivic, J.3    Freeman, W.4    Zisserman, A.5
  • 21
    • 78650974747 scopus 로고    scopus 로고
    • Leveraging loosely-tagged images and inter-object correlations for tag recommendation
    • 5
    • Y Shen and J. Fan. Leveraging loosely-tagged images and inter-object correlations for tag recommendation. In ACM MM, 2010. 5
    • (2010) ACM MM
    • Shen, Y.1    Fan, J.2
  • 22
    • 0034244751 scopus 로고    scopus 로고
    • Normalized cuts and image segmentation
    • 2
    • J. Shi and J. Malik. Normalized cuts and image segmentation. PAMI, 22(8): 888-905, 2002. 2
    • (2002) PAMI , vol.22 , Issue.8 , pp. 888-905
    • Shi, J.1    Malik, J.2
  • 23
    • 85162059405 scopus 로고    scopus 로고
    • More data means less inference: A pseudo-max approach to structured learning
    • 4
    • D. Sontag, O. Meshi, T Jaakkola, and A. Globerson. More data means less inference: A pseudo-max approach to structured learning. In NIPS, 2010. 4
    • (2010) NIPS
    • Sontag, D.1    Meshi, O.2    Jaakkola, T.3    Globerson, A.4
  • 24
    • 14344250451 scopus 로고    scopus 로고
    • Support vector machine learning for interdependent and structured output spaces
    • 4
    • I. Tsochantaridis, T Hofmann, T Joachims, and Y Altun. Support vector machine learning for interdependent and structured output spaces. In ICML, 2004. 4
    • (2004) ICML
    • Tsochantaridis, I.1    Hofmann, T.2    Joachims, T.3    Altun, Y.4
  • 26
    • 77956004771 scopus 로고    scopus 로고
    • Semantic context modeling with maximal margin conditional random fields for automatic image annotation
    • 1, 4
    • Y Xiang, X. Zhou, Z. Liu, T-S. Chua, and C.-w. Ngo. Semantic context modeling with maximal margin conditional random fields for automatic image annotation. In CVPR, 2010. 1, 4
    • (2010) CVPR
    • Xiang, Y.1    Zhou, X.2    Liu, Z.3    Chua, T.-S.4    Ngo, C.-W.5
  • 27
    • 71149086466 scopus 로고    scopus 로고
    • Learning structural svms with latent variables
    • 4
    • C.-N. J. Yu and T Joachims. Learning structural svms with latent variables. In ICML, 2009. 4
    • (2009) ICML
    • Yu, C.-N.J.1    Joachims, T.2
  • 28
    • 51949083216 scopus 로고    scopus 로고
    • Joint multi-label multi-instance learning for image classification
    • 1
    • Z.-J. Zha, X.-S. Hua, T Mei, J. Wang, G.-J. Qi, and Z. Wang. Joint multi-label multi-instance learning for image classification. In CVPR, 2008. 1
    • (2008) CVPR
    • Zha, Z.-J.1    Hua, X.-S.2    Mei, T.3    Wang, J.4    Qi, G.-J.5    Wang, Z.6
  • 29
    • 33947681316 scopus 로고    scopus 로고
    • Ml-knn: A lazy learning approach to multi-label learning
    • 1, 6, 7
    • M. Zhang and Z. Zhou. Ml-knn: A lazy learning approach to multi-label learning. Pattern Recognition, 40(7):2038-2048, 2007. 1, 6, 7
    • (2007) Pattern Recognition , vol.40 , Issue.7 , pp. 2038-2048
    • Zhang, M.1    Zhou, Z.2
  • 30
    • 84881063565 scopus 로고    scopus 로고
    • Multi-kernel multi-label learning with maxmargin concept network
    • 2, 4
    • W. Zhang, X. Xue, J. Fan, X. Huang, B. Wu, and M. Liu. Multi-kernel multi-label learning with maxmargin concept network. In IlCAI, 2011. 2, 4
    • (2011) IlCAI
    • Zhang, W.1    Xue, X.2    Fan, J.3    Huang, X.4    Wu, B.5    Liu, M.6
  • 31
    • 85108375679 scopus 로고    scopus 로고
    • Multi-instance multilabel learning with application to scene classification
    • 1
    • Z.-H. Zhou and M.-L. Zhang. Multi-instance multilabel learning with application to scene classification. In NIPS, 2006. 1
    • (2006) NIPS
    • Zhou, Z.-H.1    Zhang, M.-L.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.