Computer Vision – ECCV 2012

1. Front Matter

   PDF

2. Oral Session 5: MRFs and Early Vision

   1. Diverse M-Best Solutions in Markov Random Fields

      • Dhruv Batra, Payman Yadollahpour, Abner Guzman-Rivera, Gregory Shakhnarovich

      Pages 1-16

   2. Generic Cuts: An Efficient Algorithm for Optimal Inference in Higher Order MRF-MAP

      • Chetan Arora, Subhashis Banerjee, Prem Kalra, S. N. Maheshwari

      Pages 17-30

   3. Filter-Based Mean-Field Inference for Random Fields with Higher-Order Terms and Product Label-Spaces

      • Vibhav Vineet, Jonathan Warrell, Philip H. S. Torr

      Pages 31-44

   4. Continuous Markov Random Fields for Robust Stereo Estimation

      • Koichiro Yamaguchi, Tamir Hazan, David McAllester, Raquel Urtasun

      Pages 45-58

   5. Good Regions to Deblur

      • Zhe Hu, Ming-Hsuan Yang

      Pages 59-72

   6. Patch Complexity, Finite Pixel Correlations and Optimal Denoising

      • Anat Levin, Boaz Nadler, Fredo Durand, William T. Freeman

      Pages 73-86

3. Poster Session 6

   1. Guaranteed Ellipse Fitting with the Sampson Distance

      • Zygmunt L. Szpak, Wojciech Chojnacki, Anton van den Hengel

      Pages 87-100

   2. A Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching

      • Shengqi Zhu, Li Zhang, Hailin Jin

      Pages 101-115

   3. A Novel Fast Method for L _∞ Problems in Multiview Geometry

      • Zhijun Dai, Yihong Wu, Fengjun Zhang, Hongan Wang

      Pages 116-129

   4. Visibility Probability Structure from SfM Datasets and Applications

      • Siddharth Choudhary, P. J. Narayanan

      Pages 130-143

   5. A Generative Model for Online Depth Fusion

      • Oliver J. Woodford, George Vogiatzis

      Pages 144-157

   6. Depth Recovery Using an Adaptive Color-Guided Auto-Regressive Model

      • Jingyu Yang, Xinchen Ye, Kun Li, Chunping Hou

      Pages 158-171

   7. Learning Hybrid Part Filters for Scene Recognition

      • Yingbin Zheng, Yu-Gang Jiang, Xiangyang Xue

      Pages 172-185

   8. Parametric Manifold of an Object under Different Viewing Directions

      • Xiaozheng Zhang, Yongsheng Gao, Terry Caelli

      Pages 186-199

   9. Fast Approximations to Structured Sparse Coding and Applications to Object Classification

      • Arthur Szlam, Karol Gregor, Yann LeCun

      Pages 200-213

   10. Displacement Template with Divide-&-Conquer Algorithm for Significantly Improving Descriptor Based Face Recognition Approaches

       • Liang Chen, Ling Yan, Yonghuai Liu, Lixin Gao, Xiaoqin Zhang

       Pages 214-227

   11. Latent Pyramidal Regions for Recognizing Scenes

       • Fereshteh Sadeghi, Marshall F. Tappen

       Pages 228-241

   12. Augmented Attribute Representations

       • Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert

       Pages 242-255

   13. Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation

       • Yuandong Tian, C. Lawrence Zitnick, Srinivasa G. Narasimhan

       Pages 256-269

The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shapes, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation.

• Markov random fields
• activity recognition
• machine learning
• object detectors
• saliency models
• algorithm analysis and problem complexity

• Microsoft Research Ltd., Cambridge, UK

  Andrew Fitzgibbon

• Dept. of Computer Science, University of North Carolina, Chapel Hill, USA

  Svetlana Lazebnik

• California Institute of Technology, Pasadena, USA

  Pietro Perona

• Institute of Industrial Science, The University of Tokyo, Tokyo, Japan

  Yoichi Sato

• INRIA, Montbonnot, France

  Cordelia Schmid

Policies and ethics