Preprints

  1. Cooperative Training of Descriptor and Generator Networks [pdf] [web]
    J. Xie, Y. Lu, S.C. Zhu, and Y.N. Wu
    arXiv: 1609.09408

  2. Modeling and Inferring Human Intents and Hidden Functional Objects for Trajectory Prediction [pdf] [web]
    D. Xie, T. Shu, S. Todorovic and S.C. Zhu
    under review for PAMI, arXiv: 1606.07827 (short version appeared in ICCV 2013).

  3. Synthesizing Dynamic Textures and Sounds by Spatial-Temporal Generative ConvNet [pdf] [web]
    J. Xie, S.C. Zhu, and Y.N. Wu
    under review, 2016.

  4. Exploring Generative Perspective of Convolutional Neural Networks by Learning Random Field Models [pdf] [web]
    Y. Lu, S.C. Zhu, and Y.N. Wu
    under review, 2016.

  5. Joint Image-Text News Topic Detection and Tracking by Multimodal Topic And-Or Graph [pdf][web]
    W. Li, J. Joo, H. Qi, and S.C. Zhu
    IEEE Trans on Multimedia (accepted, early version appeared as arXiv:1512.04701)

  6. A Restricted Visual Turing Test for Deep Scene and Event Understanding [pdf][web]
    H. Qi, T.F. Wu, M.W. Lee, S.C. Zhu
    arXiv:1512.01715

  7. Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose [pdf] [web]
    S. Park, B. X. Nie and S.C. Zhu
    Under Review arXiv: 1605.02112 (short version appeared in ICCV2015).

  8. Learning Mixtures of Bernoulli Templates by Two-Round EM with Performance Guarantee
    A. Barbu, T. Wu and Y.N. Wu
    Electronic Journal of Statistics (EJS), (Accepted) [pdf] [slides]

  9. Modeling 4D Human-Object Interactions for Joint Event Segmentation, Recognition, and Object Localization [pdf] [web]
    P. Wei, Y.B. Zhao, N.N. Zheng and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence (accepted, short version appears at ICCV 2013), 2015.

  10. Online Object Tracking, Learning and Parsing with And-Or Graphs [pdf] [web]
    T.F. Wu, Y. Lu, and S.C. Zhu
    IEEE Trans on Pattern Analysis and Machine Intelligence, (accepted), arXiv 1509.08067, (short version appears at CVPR 2014).

  11. Single-View 3D Scene Reconstruction and Parsing by Attributed Grammar [pdf]
    X.B. Liu, Y.B. Zhao, and S.C. Zhu
    IEEE Trans on Pattern Analysis and Machine Intelligence, (accepted), (short version appear in CVPR 2014.)

  12. 2017

  13. Learning Social Affordance Grammar from Videos: Transferring Human Interactions to Human-Robot Interactions
    T. Shu, X. Gao, M. S. Ryoo, S.-C. Zhu
    International Conference on Robotics and Automation (ICRA), 2017.

  14. The Martian: Examining Human Physical Judgments Across Virtual Gravity Fields [pdf] [web]
    T. Ye*, S. Qi*, J. Kubricht, Y. Zhu, H. Lu, S.C. Zhu
    *Equal contributors
    IEEE VR, March. 2017. Accepted to TVCG.

  15. Alternating Back-Propagation for Generator Network [pdf][web]
    T. Han, Y. Lu, S.C. Zhu, and Y.N. Wu
    31th AAAI Conference on Artificial Intelligence (AAAI), San Francisco, Feb, 2017

  16. Cross-view People Tracking by Scene-Centered Spatio-Temporal Parsing [pdf][web]
    Y. Xu, X. B.Liu, L. Qin, and S.C. Zhu
    31th AAAI Conference on Artificial Intelligence (AAAI), San Francisco, Feb, 2017

  17. Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning [pdf][web]
    Q. Zhang, R. Cao, Y. N. Wu, and S.C. Zhu
    31th AAAI Conference on Artificial Intelligence (AAAI), San Francisco, Feb, 2017

  18. Inferring Context through Scene Understanding [pdf]
    M. Walton, D. Lange and S.C. Zhu
    31th AAAI Conference on Artificial Intelligence (AAAI) Symposium on Computational Context, San Francisco, Feb, 2017

  19. 2016

  20. Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation [pdf][web]
    T.F. Wu, B. Li and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 38, issue no. 9: 1829-1843, 2016.

  21. Inducing Wavelets into Random Fields via Generative Boosting [pdf][web]
    J. Xie, Y. Lu, S.C. Zhu, and Y.N. Wu
    Applied and Computational Harmonic Analysis, Volume 41, Issue 1, pp4–25, July 2016.

  22. A Virtual Reality Platform for Dynamic Human-Scene Interaction [pdf] [web]
    J. Lin*, X. Guo*, J. Shao*, C. Jiang, Y. Zhu, S.C. Zhu
    *Equal contributors
    Siggraph Asia, Virtual reality meets physical reality workshop, Dec. 2016.

  23. Jointly Learning Grounded Task Structures from Language Instruction and Visual Demonstration [pdf]
    C. Liu, S. Yang, S. Saba-Sadiya, N. Shukla, Y. He, S.-C. Zhu, and J. Chai
    Conference on Empirical Methods in Natural Language Processing Austin, Texas, Nov. 2016.

  24. Inferring Human Intent from Video by Sampling Hierarchical Plans [pdf]
    S. Holtzen, Y.B. Zhao, T. Gao, J. B. Tenenbaum, S.C. Zhu
    Int'l Conf. on Intelligent Robots and Systems (IROS), Deajeon, Oct., 2016.

  25. Integrating Function, Geometry, Appearance for Scene Parsing [pdf] [web]
    Y. Zhao and S.C. Zhu
    Int'l Journal of Computer Vision (Accepted, short version appeared in CVPR 2013).

  26. A Reconfigurable Tangram Model for Scene Representation and Categorization [pdf][web]
    J.Zhu, T.F. Wu, B. Li, S.C. Zhu, X.K. Yang and W.J. Zhang
    IEEE Trans. on Image Processing 25(1):150-166, 2016.

  27. Learning Perceptual Causality from Video [pdf]
    A. Fire and S.C. Zhu
    ACM Trans. on Intelligent Systems and Technology (Special Issue on Causal Discovery and Inference) 7(2): 23, January 2016.

  28. What is Where: Inferring Containment Relations from Videos [pdf][web]
    W. Liang, Y. Zhu and S.C. Zhu
    25th Int'l joint Conf. on Artificial Intelligence (IJCAI), 2016.

  29. Learning Social Affordance for Human-Robot Interaction [pdf][web]
    T. Shu, M. S. Ryoo, and S.C. Zhu
    25th Int'l joint Conf. on Artificial Intelligence (IJCAI), 2016.

  30. A Theory of Generative ConvNet [pdf][web]
    J. Xie, Y. Lu, S.C. Zhu and Y.N. Wu
    Int'l Conf. on Machine Learning (ICML), 2016.

  31. Grounded Semantic Role Labeling [pdf][web]
    S. Yang, Q. Gao, C. Liu, C. Xiong, S.C. Zhu, and J. Y. Chai
    15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NA-ACL), San Diego, 2016

  32. Probabilistic Simulation Predicts Human Performance on Viscous Fluid-Pouring Problem [pdf][web]
    J. Kubricht*, C. Jiang*, Y. Zhu*, S.C. Zhu, D. Terzopoulos, and H. Lu
    *Equal contributors
    38th Annual Meeting of the Cognitive Science Society (CogSci), 2016.

  33. Critical Features of Joint Actions that Signal Human Interaction [pdf][web]
    T. Shu, S. Thurman, D. Chen, S.C. Zhu, and H.J. Lu
    38th Annual Meeting of the Cognitive Science Society (CogSci), 2016.

  34. Multi-view People Tracking via Hierarchical Trajectory Composition [pdf][web]
    Y. Xu, X.Liu, Y. Liu and S.-C. Zhu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016.

  35. Recognizing Car Fluents from Video [pdf][web][Dataset]
    B. Li, T.F. Wu, C. Xiong, and S.C. Zhu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016.

  36. Inferring Forces and Learning Human Utilities from Video [pdf][web]
    Y. Zhu*, C. Jiang*, Y. Zhao, D. terzopoulos and S.C. Zhu
    *Equal contributors
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016.

  37. Robot Learning with a Spatial, Temporal, and Causal And-Or Graph [pdf][web]
    C.M. Xiong, N. Shukla, W. Xiong and S.C. Zhu
    Int'l Conference on Robotics and Automation (ICRA), 2016.

  38. Learning FRAME Models Using CNN Filters [pdf][web]
    Y. Lu, S.C. Zhu and Y.N. Wu
    30th AAAI Conference on Artificial Intelligence (AAAI), Phoenix, Arizona, 2016.

  39. Task Learning through Visual Demonstration and Situated Dialogue [pdf]
    C.S. Liu, J. Y. Chai, N. Shukla and S.C.Zhu
    AAAI Workshop on Symbiotic Cognitive Systems, Phoenix, Arizona, 2016.

  40. 2015

  41. Learning Hierarchical Space Tiling for Scene Modeling, Parsing and Attribute Tagging
    S. Wang, Y.Z. Wang, and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence Vol. 37, No. 12: 2478-2491, 2015. [pdf][web]

  42. Learning 3D Object Templates by Quantizing Geometry and Appearance Spaces
    W. Hu and S.C. Zhu
    IEEE Trans on Pattern Analysis and Machine Intelligence, Vol.37, No. 6, 1190-1205, 2015. [pdf] [web]

  43. Scene Understanding by Reasoning Stability and Safety
    B. Zheng, Y. Zhao, J. Yu, K. Ikeuchi, and S.C. Zhu
    Int'l Journal of Computer Vision, vol. 112, no. 2, pp221-238, 2015 [pdf] [web]

  44. Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection [pdf][web]
    T.F. Wu and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 37, no. 5, pp 1013-1027, 2015.

  45. Video Primal Sketch : A Unified Middel Level Representation of video
    Z. Han, Z. Xu, and S.C. Zhu
    Journal of Mathematical Imaging and Vision, 53(2): 151-170, 2015. [pdf][web]

  46. Learning Sparse FRAME Models for Natural Image Patterns
    J. Xie, W. Hu, S.C. Zhu and Y.N. Wu
    Int'l Journal of Computer Vision , 112(2): 221-238, 2015. [pdf] [web]

  47. Mapping Energy Landscapes of Non-Convex Learning Problems
    M. Pavlovskaia, K.W. Tu and S.C. Zhu
    under review (arXiv 2014, no. 1410.0576, short version appears at EMMCVPR Jan, 2015) [pdf][web]

  48. Attributed Grammars for Joint Estimation of Human Attributes, Parts and Poses [pdf][web]
    S. Park and S.C. Zhu
    Proc. of International Conference on Computer vision (ICCV), 2015.

  49. Mining And-Or Graphs for Graph Matching and Object Discovery [pdf][web]
    Q.S. Zhang, Y.N. Wu and S.C. Zhu
    Proc. of International Conference on Computer vision (ICCV), 2015.

  50. Automated Facial Trait Judgment and Election Outcome Prediction: Social Dimensions of Face [pdf][web]
    J. Joo, F. Steen and S.C. Zhu
    Proc. of International Conference on Computer vision (ICCV), 2015.

  51. A Unified Framework for Human-Robot Knowledge Transfer [pdf][web]
    N. Shukla, C.M. Xiong and S.C. Zhu
    AAAI Symposium on Artificial Intelligence and Human-Robot Interaction (AI-HRI), 2015.

  52. Represent and Infer Human Theory of Mind for Human-Robot Interaction [pdf][web]
    Y.B. Zhao, S. Holtzen, T. Gao and S.C. Zhu
    AAAI Symposium on Artificial Intelligence and Human-Robot Interaction (AI-HRI), 2015.

  53. Understanding Tools: Task-Oriented Object Modeling, Learning and Recognition [pdf][web]
    Y. Zhu*, Y.B. Zhao* and S.C. Zhu
    *Equal contributors
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2015.

  54. Joint Inference of Groups, Events and Human Roles in Aerial Videos [pdf][web]
    T. Shu, D. Xie, B. Rothrock, S. Todorovic and S.C. Zhu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2015.

  55. Joint Action Recognition and Pose Estimation From Video [pdf][web]
    B. X. Nie, C. Xiong and S.C. Zhu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2015.

  56. Evaluating Human Cognition of Containing Relations with Physical Simulation [pdf][web]
    W. Liang, Y. B. Zhao, Y. Zhu and S.C. Zhu
    37th Annual Cognitive Science Conference (CogSci), Los Angeles, 2015.

  57. Mapping Energy Landscapes of Non-Convex Learning Problems [pdf]
    M. Pavlovskaia, K.W. Tu and S.C. Zhu
    Proc. of Energy Minimization Method for Computer Vision and Pattern Recognition (EMMCVPR), Hong Kong, Jan. 2015.

    2014

  58. Joint Video and Text Parsing for Understanding Events and Answering Queires
    K. Tu, M. Meng, M. W. Lee, T.E. Choi, and S.C. Zhu
    IEEE MultiMedia Vol.21, no.2, pp.42-70, 2014. [pdf] [web]

  59. Unsupervised Learning of Compositional Sparse Code for Natural Image Representation
    Y. Hong, Z.Z. Si, W.Z Hu, S.C. Zhu and Y.N. Wu
    Quarterly of Applied Mathematics, 72, 373-406, 2014. [pdf] [web with data and code]

  60. Animated Pose Templates for Modeling and Detecting Human Actions
    B. Yao, B. Nie, Z. Liu, and S.C. Zhu
    IEEE Trans on Pattern Analysis and Machine Intelligence, Vol. 36, no.3, 436-452, 2014. [pdf] [web]

  61. Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model. [pdf][web]
    B. Li, T.F. Wu and S.C. Zhu
    Proc. of European Conf. on Computer Vision (ECCV), 2014.

  62. Visual Persuasion: Inferring the Communicative Intents of Images [pdf][web]
    J. Joo, W.X. Li, F. Steen and S.C. Zhu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014.

  63. Cross-View Action Modeling, Learning and Recognition [pdf][web]
    J. Wang, B. Nie, Y. Wu and S.C. Zhu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014.

  64. Single-View 3D Scene Parsing by Attributed Grammar [pdf][web]
    X.B. Liu, Y.B. Zhao and S.C. Zhu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014.

  65. Online Object Tracking, Learning and Parsing with And-Or Graphs [pdf][web]
    Y. Lu, T.F. Wu and S.C. Zhu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014.

  66. Learning Inhomogeneous FRAME Models for Object Patterns [pdf][web]
    J. Xie. W. Hu, S.C. Zhu and , Y. Wu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014.

  67. Unsupervised Learning of Dictionaries of Hierarchical Compositional Models [pdf][web]
    J. Dai, Y. Hong, W. Hu, S.C. Zhu and Y. Wu
    Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014.

  68. Detecting Potential Falling Objects by Inferring Human Action and Natural Disturbance [pdf] [web]
    B. Zheng, Y.B. Zhao, J. C. Yu, K. Ikeuchi and S.C. Zhu
    Proc. Int'l Conf. on Robotics and Automations (ICRA), 2014.

  69. 2013

  70. Video Event Parsing and Learning with Goal and Intent Prediction
    M.T. Pei, Z.Z. Si, B. Yao, and S.C. Zhu
    Computer Vision and Image Understanding, vol. 117, no. 10, pp 1369-1383, 2013 [pdf] [web with data and code]

  71. Learning And-Or Templates for Object Modeling and Recognition
    Z. Si and S.C. Zhu
    IEEE Trans on Pattern Analysis and Machine Intelligence, vol. 35, no.9, 2189-2205, 2013 [pdf] [web with data and code]

  72. Abstract Painting with Interactive Control of Perceptual Entropy
    M.T. Zhao and S.C. Zhu
    ACM Trans on Applied Perception, Vol.10, No.1, Febuary, 2013. [pdf] [web][reprint]

  73. Video Stylization: Painterly Rendering and Optimization with Content Extraction
    L. Lin, K. Zeng, Y.Z. Wang, Y.-Q. Xu, S.-C. Zhu
    IEEE Transactions on Circuits and Systems for Video Technology, vol.23, no4, pp577-590, 2013 . [pdf][web]

  74. Unsupervised Structure Learning of Stochastic And-Or Grammars [pdf][web]
    K.W Tu, M. Pavlovskaia and S.C. Zhu
    Proc. Neural Information Processing Systems (NIPS), 2013.

  75. Inferring ‘Dark Matter’ and ‘Dark Energy’ from Videos [pdf][web]
    D. Xie, S. Todorovic and S.C. Zhu
    Proc. Int’l Conference on Computer Vision (ICCV), 2013.

  76. Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection [pdf][web]
    T.F. Wu and S.C. Zhu
    Proc. Int’l Conference on Computer Vision (ICCV), 2013.

  77. Monte Carlo Tree Search for Scheduling Activity Recognition [pdf][web]
    M. Amer, S. Todorovic, A. Fern and S.C. Zhu
    Proc. Int’l Conference on Computer Vision (ICCV), 2013.

  78. Human Attribute Recognition by Rich Appearance Dictionary [pdf][web]
    J. Joo, S. Wang and S.C. Zhu
    Proc. Int’l Conference on Computer Vision (ICCV), 2013.

  79. Cosegmentation and Cosketch by Unsupervised Learning [pdf][web]
    J. Dai, Y. Wu, J. Zhou and S.C. Zhu
    Proc. Int’l Conference on Computer Vision (ICCV), 2013.

  80. Concurrent Action Detection with Structural Prediction [pdf][web]
    P. Wei, N.N. Zheng, Y.B. Zhao and S.C. Zhu
    Proc. Int’l Conference on Computer Vision (ICCV), 2013.

  81. Modeling Occlusion by Discriminative AND-OR Structures [pdf][web]
    B. Li, W. Hu, T.F. Wu and S.C. Zhu
    Proc. Int’l Conference on Computer Vision (ICCV), 2013.

  82. Modeling 4D Human-Object Interactions for Event and Object Recognition [pdf][web]
    P. Wei, Y. B. Zhao, N.N. Zheng and S.C. Zhu
    Proc. Int’l Conference on Computer Vision (ICCV), 2013.

  83. Rates for Inductive Learning of Compositional Models [pdf]
    A. Barbu, M. Pavlovskaia and S.C. Zhu
    AAAI Workshop on Learning Rich Representations from Low-Level Sensors (RepLearning), Bellvue, WA, 2013

  84. Scene Parsing by Integrating Function, Geometry and Appearance Models [pdf] [web with data]
    Y. B. Zhao and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013.

  85. Beyond Point Clouds: Scene Understanding by Reasoning Geometry and Physics [pdf] [web with data]
    B. Zheng, Y.B. Zhao, J.C. Yu, K. Ikeuchi, and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013.

  86. Integrating Grammar and Segmentation for Human Pose Estimation [pdf] [web with data]
    B. Rothrock, S. Park, and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013.

  87. Discriminatively Trained And-Or Tree Models for Object Detection [pdf] [web with data]
    X. Song, T.F. Wu, Y. Jia, and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013.

  88. Weakly Supervised Learning for Attribute Localization in Outdoor Scenes [pdf] [web with data]
    S. Wang, J. Joo, Y.Z. Wang, and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013.

  89. Using Causal Induction in Humans to Learn and Infer Causality from Video [pdf] [poster][web]
    A. Fire and S.C. Zhu
    35th Annual Cognitive Science Conference (CogSci), Berlin, Germany, 2013

  90. Learning Perceptual Causality from Video [pdf] [slides] [poster]
    A. Fire and S.C. Zhu
    AAAI Workshop on Learning Rich Representations from Low-Level Sensors (RepLearning), Bellvue, WA, 2013

  91. 2012

  92. Intrackability : Characterizing Video Statistics and Pursuing Video Representations
    H.F. Gong and S.C. Zhu
    Int'l Journal of Computer Vision, vol 97, no.3, pp255-275, 2012 [pdf] [web]

  93. Learning Hybrid image Template (HiT) by Information Projection
    Z. Si and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 34, no.7, pp1354-1367, 2012. [pdf] [web]

  94. Background Modeling by Subspace Learning on Spatio-temporal Patches
    Y.D. Zhao, H. F. Gong, Y. Jia, and S.C. Zhu
    Pattern Recognition Letter, Vol.33, 1134-1147, 2012. [pdf]

  95. Cost-Sensitive Top-down/Bottom-up Inference for Multiscale Activity Recognition [pdf][web with dataset]
    M. R. Amer, D. Xie, M. Zhao, S. Todorovic, and S.C. Zhu
    European Conf. on Computer Vision (ECCV), 2012.

  96. Hierarchical Space Tiling for Scene Modelling [pdf] [web]
    S. Wang, Y.Z Wang, and S.C. Zhu
    Asia Conf. on Computer Vision (ACCV), 2012.

  97. Reconfigurable Templates for Robust Vehicle Detection and Classification [pdf][web]
    Y. Lu, B. Yao, Y. Wang and S.C. Zhu
    Workshop on Application of Computer Vision (WACV), Colorado, 2012

  98. Learning Reconfigurable Scene Representation by Tangram Model [pdf][web]
    J. Zhu, T.F. Wu, S.C. Zhu, X.K. Yang, W. Zhang
    Workshop on Application of Computer Vision (WACV), Colorado, 2012

  99. Artistic Rendering of Portraits [pdf][web]
    M.T. Zhao and S.C. Zhu
    Book chapter in Image and Video based Artistic Stylization, Eds. J. Collomosse and P. Rossin, Springer, 2012

  100. Hierarchical Organization by And-Or Tree [pdf][web]
    J. Joo, S. Wang and S.C. Zhu
    Book chapter in Handbook of Perceptual Organization, eds.J. Wagemans, Springer, 2012

  101. Structure v.s. Appearance and 3D v.s. 2D? A Numeric Answer [pdf][web]
    W.Z. Hu, Z. Si, and S.C. Zhu
    Book chapter in Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective Eds.S. Dickinson and Z. Pizlo Springer, 2012

  102. Learning 3D Object Templates by Hierarchical Quantization of Geometry and Appearance Spaces [pdf][web]
    W.Z. Hu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, RI 2012.

  103. 2011

  104. A Numeric Study of the Bottom-up and Top-down Inference Processes in And-Or Graphs
    T.F. Wu and S.C. Zhu
    Int'l Journal of Computer Vision, vol. 93, no 2, p226-252, June 2011. [pdf] (short version in ICCV09) [web]

  105. C4 : Computing Multiple Solutions in Graphical Models by Cluster Sampling
    J. Porway and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.33, no.9, 1713-1727, 2011[pdf] [web]

  106. Image Parsing via Stochastic Scene Grammar[pdf] [web]
    Y.B. Zhao and S.C. Zhu
    the Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), Granada, Spain, 2011.

  107. Unsupervised Learning of Stochastic And-Or Templates for Object modeling [pdf] [web]
    Z.Z. Si and S.C. Zhu
    Int'l Workshop on Stochastic Image Grammar (SIG), Barcelona, Spain, 2011

  108. Human Parsing using Stochastic And-Or grammar and Rich Appearance [pdf] [web]
    B. Rothrock and S.C. Zhu
    Int'l Workshop on Stochastic Image Grammar (SIG), Barcelona, Spain, 2011

  109. Parsing Video Events with Goal inference and Intent Prediction [pdf] [web]
    M. Pei, Y. Jia, and S.-C. Zhu
    Int'l Conf. on Computer Vision (ICCV), Barcelona, Spain, 2011.

  110. Unsupervised Learning of Event And-Or Grammar and Semantics from Video [pdf] [web]
    Z. Si, M. Pei, Z.Y. Yao, and S.-C. Zhu
    Int'l Conf. on Computer Vision (ICCV), Barcelona, Spain, 2011.

  111. Image Representation by Active Curves [pdf] [web]
    W.Z. Hu, Y.N. Wu and S.-C. Zhu
    Int'l Conf. on Computer Vision (ICCV), Barcelona, Spain, 2011.

  112. Video Primal Sketch: A Generic Middle-Level Representation of Video [pdf] [web]
    Z. Han, Z.B. Xu, and S.-C. Zhu
    Int'l Conf. on Computer Vision (ICCV), Barcelona, Spain, 2011.

  113. Inferring Social Roles in Long Timespan Video Sequence [pdf] [web]
    J. Zhang, W. Hu, B. Yao, Y. Wang and S.C. Zhu
    Int'l Workshop on Video Event Categorization, Tagging and Retrieval for Real World Applications, Barcelona, Spain, 2011.

  114. Customizing Painterly Rendering Styles Using Stroke Processes [pdf] [web]
    M.T. Zhao and S.-C. Zhu
    Int'l Symposium on Non-Photorealistic Animation and Rendering (NPAR), Vancouver, Canada, 2011.

  115. Portrait Painting Using Active Templates [pdf] [web]
    M.T. Zhao and S.-C. Zhu
    Int'l Symposium on Non-Photorealistic Animation and Rendering (NPAR), Vancouver, Canada, 2011.

  116. 2010

  117. Learning Active Basis Model for Object Detection and Recognition
    Y.N. Wu, Z.Z. Si, H.F. Gong, and S.C. Zhu
    Int'l Journal of Computer Vision, Vol.90, no.2, pp 198-235, 2010 [pdf] [reprint]

  118. A Compositional and Dynamic Model for Face Aging
    J.L. Suo, S.C. Zhu, S. Shan, and X. Chen
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 32, no. 3, pp 385-401, March 2010. [pdf][web]

  119. Layered Graph Matching by Composite Cluster Sampling
    L. Lin, X.B. Liu and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.32, no. 8. pp 1426-1442, August, 2010. [pdf]

  120. Hierarchical and Contextual Model for Aerial Image Understanding
    J. Porway, K. Wang, and S.C. Zhu
    Int'l Journal of Computer Vision, vol.88, no.2, pp 254-283, 2010 [pdf] [web]

  121. I2T: Image Parsing to Text Description
    Z.Y. Yao, X. Yang, L. Lin, M. W. Lee, and S.C. Zhu
    Proceedings of IEEE, Vol 98, no.8,, pp 1485-1508, August, 2010. (special issue on Internet Vision) [pdf] [web]

  122. Learning Active Basis Models by EM-Type Algorithms [pdf]
    Z. Si, H. Gong, S.C. Zhu, and Y.N. Wu
    Statistical Science , Vol. 25, No. 4, 458-475, 2010.

  123. CO3 for Ultra-fast and Accurate Interactive Segmentation [pdf] [web]
    Y.B. Zhao, S.C. Zhu, and S.W. Luo,
    ACM conference on Multi-media (MM'10, Long paper), Firenze, Italy, October, 2010.

  124. Artistic Paper-cut of Human Portraints [pdf] [web]
    M. Meng, M.T. Zhao, S.C. Zhu,
    ACM conference on Multi-media (MM'10, short paper), October, 2010, Firenze, Italy.

  125. Sisley the Abstract Painter [pdf] [web]
    M.T. Zhao and S.C. Zhu
    Int'l Symposium on Non-Photorealistic Animation and Rendering (NPAR) Annecy, France, 2010.

  126. Painterly Animation Using Video Semantics and Feature Correspondence [pdf] [web]
    L. Lin K. Zeng H. Lv Y.Z. Wang, Y. Xu, and S. C. Zhu
    Int'l Symposium on Non-Photorealistic Animation and Rendering (NPAR) Annecy, France, 2010.

  127. Learning Artistic Lighting Template from Portrait Photographs [pdf] [web]
    X. Jin, M.T. Zhao, X.W Chen,Q.P. Zhao, S.C. Zhu
    Proc. of European Conf. on Computer Vision (ECCV), 2010.

  128. Learning a Probabilistic Model Mixing 3D and 2D Primitives for View Invariant Object Recognition [pdf] [web]
    W.Z. Hu and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , San Francisco, 2010.

  129. Discovering Scene Categories by Information Projection and Cluster Sampling [pdf]
    D.X. Dai, T.F. Wu and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , San Francisco, 2010

  130. 2009

  131. Bottom-up/Top-down Image Parsing with Attribute Graph Grammar
    F. Han and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence , vol.31, no.1, pp 59-73, Jan. 2009 [pdf] [reprint]

  132. From Image Parsing to Painterly Rendering
    K. Zeng, M.T. Zhao, C. Xiong, and S.C. Zhu
    ACM Trans. on Graphics, vol. 29, no.1, Dec. 2009. [reprint]

  133. Learning Explicit and Implicit Visual Manifolds by Information Projection
    S.C. Zhu, K. Shi, and Z.Z. Si
    Pattern Recognition Letter (invited paper for the Aggarwal Lecture), August 2009. [pdf] [reprint]

  134. An and-or graph model for face representation, sketching and aging [pdf]
    F. Min, J.L. Suo, and S.C. Zhu
    Chapter in Encyclopedia of Biometric Recognition , Springer, 2009.

  135. Learning Deformable Action Templates from Cluttered Videos [pdf]
    B. Yao and S.C. Zhu
    Proc. Int'l Conf. on Computer Vision (ICCV) , Kyoto, Japan, 2009

  136. Evaluating Information Contributions of Bottom-up and Top-down Processes [pdf]
    X. Yang, T.F. Wu, and S.C. Zhu
    Proc. Int'l Conf. on Computer Vision (ICCV) , Kyoto, Japan, 2009

  137. Learning Mixed Templates for Object Recognition [pdf]
    Z.Z. Si, H.F. Gong, Y.N. Wu, and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , Miami, Florida, June, 2009

  138. Flow Mosaicking: Real-time Pedestrian Counting without Scene-Specific Learning [pdf]
    Y. Cong, H.F. Gong, and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , Miami, Florida, June, 2009

  139. Trajectory Parsing by Cluster Sampling in Spatio-Temporal Graph [pdf]
    X.B. Liu, L. Lin, and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , Miami, Florida, June, 2009

  140. Layered Graph Matching by Composite Clustering with Collaborative and Competitive Interactions [pdf]
    L. Lin, K. Zeng, X. B. Liu and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , Miami, Florida, June, 2009

  141. Learning compositional models for object categories from small sample sets [pdf]
    J. Porway, B. Yao, and S.C. Zhu
    Book Chapter in Sven Dickinson et al (eds.) Object Categorization: Computer and Human Vision Perspectives, Cambridge University Press. 2009

  142. 2008

  143. A Composite Template for Human Face Modeling and Sketch
    Z.J. Xu, H. Chen, S.C. Zhu, and J. Luo
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.30, no.6, 955-969, 2008. [pdf] [reprint.pdf]

  144. Perceptual Scale Space and Its Applications
    Y.Z. Wang and S.C. Zhu
    Int'l Journal of Computer Vision, vol. 80, no.1, pp143-165, Oct, 2008. [pdf] [reprint]

  145. A Hierarchical and Contextual Model for Aerial Image Understanding
    J. Porway, K. Wang, and S.C. Zhu,
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , Anchorage, Alaska, June, 2008. [pdf]

  146. An Integrated Background Model for Video Surveillance Based on Primal Sketch and 3D Scene Geometry
    W. HU, H.F. Gong, S.C. Zhu, and Y. Wang,
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) , Anchorage, Alaska, June, 2008.[pdf]

  147. Learning a Scene Contextual Model for Tracking and Abnormality Detection
    B. Yao, L. Wang and S.C. Zhu
    Proc. 3rd Int'l Workshop on Semantic Learning and Applications in Multimedia, Anchorage, Alaska, June, 2008. [pdf]

  148. SAVE: A Framework for Semantic Annotation of Visual Events
    M.W. lee, A. Hakeem, N. Haering, and S.C. Zhu,
    Proc. 1st Int'l Workshop on Internet Vision, Anchorage, Alaska, June, 2008. [pdf]

  149. 2007

  150. From Information Scaling of Natural Images to Regimes of Statistical Models
    Y.N. Wu, C.E. Guo, and S.C. Zhu
    Quarterly of Applied Mathematics, 2007. [preprint.pdf]

  151. Primal Sketch: Integrating Texture and Structure
    C.E. Guo, S.C. Zhu and Y.N. Wu
    Computer Vision and Image Understanding, vol. 106, issue 1, 5-19, April, 2007 [pdf] [reprint.pdf]

  152. Generalizing Swendsen-Wang for Image Analysis
    A. Barbu and S.C. Zhu
    Journal of Computational and Graphical Statistics, vol. 16, no. 4, 877-900, 2007 [Long_survey.pdf] [reprint.pdf]

  153. A Two-Level Generative Model for Cloth Representation and Shape-From-Shading
    F. Han and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.29, no.7, pp 1230-1243, July 2007 [pdf]

  154. Statistical Principles in Image Modeling [pdf]
    Y.N. Wu, J. Li. Z. Liu, and S.C. Zhu
    Technometrics, 49, pp249-261, 2007.

  155. Deformable Template As Active Basis
    Y.N. Wu, Z.Z. Si, C. Fleming, and S.C. Zhu
    Proc. Int'l Conf. on Computer Vision (ICCV), Rio. Brazil, Oct, 2007. [pdf]

  156. An Empirical Study of Object Category Recognition: Sequential Testing with Generalized Samples
    L. Lin, S.W Peng, J. Porway, S.C. Zhu, and Y.T. Wang
    Proc. Int'l Conf. on Computer Vision (ICCV), Rio. Brazil, Oct, 2007. [pdf]

  157. Introduction to a large scale general purpose groundtruth dataset: methodology, annotation tool, and benchmarks
    Z.Y. Yao, X. Yang, and S.C. Zhu
    Proc. 6th Int'l Conf on Energy Minimization Methods in CVPR (EMMCVPR), Springer LNCS 4679, Ezhou, China, Aug 2007. [pdf]

  158. Object category recognition using generative template boosting
    S.W. Peng, L. Lin, J. Porway, N. Sang, and S.C. Zhu
    Proc. 6th Int'l Conf on Energy Minimization Methods in CVPR (EMMCVPR), Springer LNCS 4679, Ezhou, China, Aug 2007. [pdf]

  159. An Automatic Portrait System Based on And-Or Graph Representation
    F Min, J.L. Suo, S.C. Zhu, and N. Sang
    Proc. 6th Int'l Conf on Energy Minimization Methods in CVPR (EMMCVPR), Springer LNCS 4679, Ezhou, China, Aug 2007. [pdf]

  160. Dynamic Feature Cascade for Multiple Object Tracking with Trackability Analysis
    Z. Li, H.F. Gong, S.C. Zhu, and N. Sang
    Proc. 6th Int'l Conf on Energy Minimization Methods in CVPR (EMMCVPR), Springer LNCS 4679, Ezhou, China, Aug 2007. [pdf]

  161. Bayesian Inference for Layer Representation with Mixed Markov Random Field
    R.X. Gao, T.F Wu, N. Sang, and S.C. Zhu
    Proc. 6th Int'l Conf on Energy Minimization Methods in CVPR (EMMCVPR), Springer LNCS 4679, Ezhou, China, Aug 2007. [pdf]

  162. Mapping the Ensemble of Natural Image Patches by Emplicit and Implicit Manifolds
    K, Shi and S.C. Zhu
    Proc. IEEE. Conf. on Computer Vision and Pattern Recognition (CVPR), June, 2007. [pdf]

  163. Compositional Boosting for Computing Hierarchical Image Structures
    T.F. Wu, G.S. Xia, and S.C. Zhu
    Proc. IEEE. Conf. on Computer Vision and Pattern Recognition (CVPR) , June, 2007. [pdf]

  164. Layered Graph Matching with Graph Editing
    L. Lin, S.C. Zhu and Y.T. Wang
    Proc. IEEE. Conf. on Computer Vision and Pattern Recognition (CVPR), June, 2007. [pdf]

  165. A Multi-Resolution Dynamic Model for Face Aging Simulation
    Jl. Suo, F. Min, S.C. Zhu, S.G. Shan, and X. L. Chen
    Proc. IEEE. Conf. on Computer Vision and Pattern Recognition (CVPR) , June, 2007. [pdf]

  166. 2006

  167. Parsing Images into Regions, Curves, and Curve Groups
    Z.W. Tu and S.C. Zhu,
    Int'l Journal of Computer Vision, 69(2), 223-249, August, 2006. [pdf] [reprint.pdf]

  168. First-hitting-time Analysis of Independence Metropolis Sampler.
    R. Maciuca and S.C. Zhu,
    Journal of Theoretical Probability, 2006 [pdf] [reprint pdf]. A version published at SCTV03 for Vision audience [pdf]

  169. A Stochastic Grammar of Images
    S.C. Zhu and D. Mumford
    Foundations and Trends in Computer Graphics and Vision, Vol.2, No.4, pp 259-362, 2006. [pdf] [reprint pdf]

  170. A Genrative Sketch Model for Human Hair Analysis and Synthesis
    H. Chen and S.C. Zhu
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.28, no.7, 1025-1040, July, 2006. [pdf] [reprint.pdf]

  171. Composite Templates for Cloth Modeling and Sketching
    H. Chen, Z.J. Xu, Z.Q. Liu, and S.C. Zhu
    Proc. IEEE Conf. on Pattern Recognition and Computer Vision (CVPR), June, 2006. [pdf]

  172. 2005

  173. What are Textons?
    S.C. Zhu, C. E. Guo, Y.Z. Wang, and Z.J. Xu
    Int'l J. of Computer Vision, vol.62(1/2), 121-143, April/May, 2005. [pdf] [reprint pdf]

  174. Image parsing: unifying segmentation, detection and recognition
    Z.W. Tu, X.R. Chen, A.L. Yuille, and S.C. Zhu,
    Int'l J. of Computer Vision, 63(2), 113-140, 2005. [pdf] [reprint pdf]

  175. Generalizing Swendsen-Wang to Sampling Arbitrary Posterior Probabilities
    A. Barbu and S.C. Zhu,
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.27, no.8, 1239-1253, 2005. [pdf] [reprint pdf]

  176. Incorporating Visual Knowledge Representation in Stereo Reconstruction
    A. Barbu and S.C. Zhu
    Proc. Int'l Conf. on Computer Vision (ICCV), Beijing, China, Oct. 2005. [pdf]

  177. Perceptual Scale Space and It Applications
    Y. Z. Wang, S. Bahrami, and S.C. Zhu
    Proc. Int'l Conf. on Computer Vision (ICCV), Beijing, China, Oct. 2005. [pdf]

  178. Bottom-up/Top-Down Image Parsing by Attribute Graph Grammar
    F. Han and S.C. Zhu
    Proc. Int'l Conf. on Computer Vision (ICCV), Beijing, China, Oct. 2005. [pdf]

  179. A generative model of human hair for hair sketching
    H. Chen and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), San Diego, June 2005.[pdf]

  180. A high resolution grammatical model for face representation and sketching
    Z.J. Xu, H. Chen and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), San Diego, June 2005.[pdf]

  181. Cloth representation by shape from shading with shading primitives
    F. Han and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), San Diego, June 2005.[pdf]

  182. 2004

  183. Range Image Segmentation by an Effective Jump-Diffusion Method,
    F. Han, Z. W. Tu, and S.C. Zhu,
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 26, no. 9, pp 1138-1153, Sept, 2004. [pdf] [reprint pdf]

  184. Analysis and Synthesis of Textured Motion: Particles and Waves,
    Y.Z. Wang and S.C. Zhu,
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 26, no. 10, pp 1348-1363, Oct, 2004. [pdf] [reprint pdf]

  185. Perceptual Scaling [pdf]
    Y.N. Wu, C.E. Guo, and S.C. Zhu
    Book Chapter in A. Gelman and X.L. Meng (Eds)
    Applied Bayesian Modeling and Causal Inference from an Incomplete Data Perspective John Wiley, 2004.

  186. Modeling complex motion by tracking and editing hidden Markov graphs
    Y.Z. Wang and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Washington, DC, June 2004. [pdf]

  187. Information scaling laws in natural scenes
    C.E. Guo, Y.N. Wu, and S.C. Zhu
    Prod. 2nd Workshop on Generative Model Based Vision Washington, DC, June 2004. [pdf]

  188. Multigrid and multi-level Swendsen-Wang cuts for hierarchic graph partition
    A. Barbu and S.C. Zhu
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Washington, DC, June 2004. [pdf]

  189. On the relationship between image and motion segmentation
    A. Barbu and S.C. Zhu
    Proc. Workshop on Spatial Coherence for Visual Motion Analysis , Prague, Czech, May, 2004. [pdf]

  190. Automatic single view building reconstruction by integrating segmentation
    F. Han and S.C. Zhu
    Proc. IEEE Workshop on Perceptual Organization in Computer Vision Washington, DC, June 2004.

  191. 2003

  192. Statistical Edge Detection: Learning and Evaluating Edge Cues,
    S. Kinishi, A. L. Yuille, J. M. Coughlan, and S. C. Zhu,
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.25, no.1, pp 57-74 January, 2003. [ps.gz] [reprint pdf]

  193. Modeling Visual Patterns by Integrating Descriptive and Generative Models,
    C. E Guo, S.C. Zhu, and Y. N. Wu,
    International Journal of Computer Vision, 53(1), 5-29, 2003. [ps.gz] [reprint pdf]

  194. Statistical Modeling and Conceptualization of Visual Patterns,
    S.C. Zhu,
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 25, no.6, pp. 691-712, 2003. [pdf][reprint pdf]

  195. On advances in statistical modeling of natural images [pdf]
    A. Srivastava, A.B. Lee, E.P. Simoncelli, and S.C. Zhu
    J. of Math Imaging and Vision, 18(1), 17-33, 2003.

  196. A mathematical theory of primal sketch and sketchability.
    C.E. Guo, S.C. Zhu and Y.N. Wu.
    Proc. of Int'l Conf. on Computer Vision (ICCV), Nice, France, October, 2003. [demo][pdf]

  197. Image parsing: segmentation, detection, and recognition.
    Z.W. Tu, X.R. Chen, A.L Yuille, and S.C. Zhu.
    Proc. of Int'l Conf. on Computer Vision (ICCV), Nice, France, October, 2003.[demo][pdf]

  198. Modeling textured motion: particles, waves, and cartoon sketch.
    Y.Z. Wang and S.C. Zhu.
    Proc. of Int'l Conf. on Computer Vision (ICCV), Nice, France, October, 2003.[demo][pdf]

  199. Graph partition by Swendsen-Wang cut.
    A. Barbu and S.C. Zhu.
    Proc. of Int'l Conf. on Computer Vision (ICCV), Nice, France, October, 2003.[demo][pdf]

  200. A multiscale generative model for animate shape and parts.
    A. Dubinskiy and S.C. Zhu.
    Proc. of Int'l Conf. on Computer Vision (ICCV), Nice, France, October, 2003.[demo][pdf]

  201. How do heuristics expedite Markov chain search? .
    R. Maciuca and S.C. Zhu.
    Proc. of Int'l workshop on Statistical and Computational Theories of Vision. (SCTV) , Nice, France, October, 2003 .[demo] [pdf]

  202. Bayesian reconstruction of 3D shapes and scenes from a single image .
    F. Han and S.C. Zhu.
    Proc. of Int'l workshop on High Level Knowledge in 3D Modeling and Motion. (HLK) , Nice, France, October, 2003.[demo] [pdf]

  203. 2002

  204. Image Segmentation by Data-Driven Markov Chain Monte Carlo,
    Z.W. Tu and S.C. Zhu,
    IEEE Trans on Pattern Analysis and Machine Intelligence, vol.24, no.5, pp. 657-673, May, 2002. [ps.gz][reprint pdf]

  205. Learning in Gibbsian Feilds: How Accurate and How Fast can It Be?"
    S. C. Zhu and X. W. Liu,
    IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.24, no.7, pp. 1001-1006, July, 2002. [ps.gz] [reprint pdf]

  206. A generative model for textured motion: analysis and synthesis.
    Y.Z. Wang and S.C. Zhu.
    Proc. of European Conf. on Computer Vision (ECCV), Copenhagen, June,2002.[pdf]

  207. Parsing images into region and curve processes
    Z.W. Tu and S.C. Zhu
    Proc. of European Conf. on Computer Vision (ECCV), Copenhagen, June, 2002.[pdf]

  208. What are textons?
    S.C. Zhu, C.E. Guo, Y.N. Wu, and Y.Z. Wang
    Proc. of European Conf. on Computer Vision (ECCV), Copenhagen, June, 2002.[pdf]

  209. Statistical modeling of texture sketch
    Y.N. Wu, S.C. Zhu, and C.E. Guo
    Proc. of European Conf. on Computer Vision (ECCV), Copenhagen, June, 2002.[pdf]

  210. A Stochastic Algorithm for 3D Scene Segmentation and Reconstruction
    F. Han, Z.W. Tu, and S.C. Zhu
    Proc. of European Conf. on Computer Vision (ECCV), Copenhagen,