I. Principle:
Recognition, Detection and Matching (oral)
- 1. Compact Signatures for High-Speed Interest Point Description and Matching (PDF). Michael Calonder, Vincent Lepetit, Pascal Fua, Kurt Konolige, James Bowman, Patrick Mihelich
- Problem: Require to run on low memory device so neet to compact data from descriptor
- Solution: Using Compressive Sensing theory
- Detail: Impove a descriptor (called Signature [19]) by Compressive Sensing Theory make a new descriptor (called compact descriptor)
- [6] M. Calonder, V.Lepetit, and P. Fua. Keypoint signatures for fast learning and recognition. In ECCV' 08
- [19] M. Ozuysal, M. Calonder, V. Lepetit , and P. Fua. Fast Keypoint Recognition using Random Ferns. PAMI, 2009. Accepted for Publication
- Low Level Vision and Others (poster)
- 3. Image Saliency by Isocentric Curvedness and Color. Roberto Valenti, Nicu Sebe, Theo Gevers
- 4. Detecting Interpretable and Accurate Scale-Invariant keypoints (PDF). Wolfgang Förstner, Timo Dickscheid, Falko Schindler
Learning and Recognition - 1 (poster)
2. Fast Ray Features for Learning Irregular Shapes (PDF). Kevin Smith, Alan Carleton, Vincent Lepetit
See note here
- Topic: Salient Object detection (don't care) - Finding the most interesting object in an image
- Method: Weighted segmentation
- See note here
5. An Algebraic Model for fast Corner Detection. Andrew Willis, Yunfeng Sui
6. Contour Segment Network
II. Secondary
Recognition, Detection and Matching (oral)
1. A Shape-Based Object Class Model for Knowledge Transfer (PDF). Michael Stark, Michael Goesele, Bernt Schiele
- Learning and Recognition - 2 (poster)
- 2. Consensus Set Maximization with Guaranteed Global Optimality for Robust Geometry Estimation. Hongdong Li
- Matching and Alignment (poster)
- 3. Robust Matching of Building Facades under Large Viewpoint Changes. Jimmy A. Lee, Kin-Choong Yow, Alex Y. S. Chia
- 4. Feature Correspondence and Deformable Object Matching via Agglomerative Correspondence Clustering. Minsu Cho, Jungmin Lee, Kyoung Mu Lee
- 5. Subspace matching: Unique solutions to point matching with geometric constraints (PDF). Manuel Marques, Marko Stosic, Joao Costeira
- 6. Deformation Invariant Image Matching by Spectrally Controlled Diffeomorphic Alignment. Christopher M. Yang, Sai Ravela
- 7. Wide-Baseline Image Matching Using Line Signatures (PDF, project, results). Lu Wang, Ulrich Neumann, Suya You
- 8. Matching as a Non-Cooperative Game. Andrea Albarelli, Samuel Rota Bulò, Andrea Torsello, Marcello Pelillo
- 9. An Algebraic Approach to Affine Registration of Point Sets (PDF). Jeffrey Ho, Adrian Peter, Anand Ranganranjan, Ming-Hsuan Yang
- Low Level Vision and Others (poster)
- 10. Recovering Planar Homographies between 2D Shapes (PDF). Jozsef Nemeth, Csaba Domokos, Zoltan Kato
- 11. GroupSAC: Efficient Consensus in the Presence of Groupings (PDF). Kai Ni, Hailin Jin, Frank Dellaert
- Problem: Low-texture screne and non-planar screne for Wide baseline matching
- Solution: Use line feature called Line Signature and propose a new matching algorithms for Line Signature matching
III Auxiliary:
Shading and Color (oral)
1. Estimating Natural Illumination from a Single Outdoor Image(PDF, project, supplementary material) - formely: Illumination Estimation from a Single Outdoor Image. Jean-François Lalonde, Alexei A. Efros, Srinivasa G. NarasimhanSimilarity Metrics and Nearest Neighbors (oral)
2. Similarity Metrics for Categorization: From Monolithic to Category Specific(PDF, abstract) - formely: Similarity Functions for Categorization: from Monolithic to Category SpecificBoris Babenko, Steve Branson, Serge BelongieLow Level Vision and Others (poster)
21. Efficient, High-Quality Image Contour Detection (, project). Bryan Catanzaro, Bor-Yiing Su, Narayanan Sundaram, Yunsup Lee, Mark Murphy, Kurt Keutzer
21. Efficient, High-Quality Image Contour Detection (, project). Bryan Catanzaro, Bor-Yiing Su, Narayanan Sundaram, Yunsup Lee, Mark Murphy, Kurt Keutzer
- 3D: Shape, Geometry, and Stereo (poster)
- 15. Diagram Techniques for Multiple View Geometry (PDF). Alberto Ruiz, Pedro E. Lopez-de-Teruel

Không có nhận xét nào:
Đăng nhận xét