Multiview fusion for canonical view generation based on homography constraints
Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks
Discovering Shape Classes using Tree Edit-Distance and Pairwise Clustering
International Journal of Computer Vision
Canonical subsets of image features
Computer Vision and Image Understanding
Geometric reasoning via internet CrowdSourcing
2009 SIAM/ACM Joint Conference on Geometric and Physical Modeling
Accurate shape-based 6-DoF pose estimation of single-colored objects
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Combining different types of scale space interest points using canonical sets
SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Multi-view object representation with modified 2-layer IDP decomposition
WSEAS Transactions on Signal Processing
Knowledge-driven saliency: attention to the unseen
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs
International Journal of Computer Vision
Effective summarization of large-scale web images
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Stable bounded canonical sets and image matching
EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Semantics-driven approach for automatic selection of best views of 3D shapes
EG 3DOR'10 Proceedings of the 3rd Eurographics conference on 3D Object Retrieval
Image collection summarization via dictionary learning for sparse representation
Pattern Recognition
| Hi-index | 0.00 |
Given a collection of sets of 2-D views of 3-D objects and a similarity measure between them, we present a method for summarizing the sets using a small subset called a bounded canonical set (BCS), whose members best represent the members of the original set. This means that members of the BCS are as dissimilar from each other as possible, while at the same time being as similar as possible to the non-BCS members. This paper will extend our earlier work on computing canonical sets [Approximation of canonical sets and their application to 2d view simplification] in several ways: by omitting the need for a multi-objective optimization, by allowing the imposition of cardinality constraints, and by introducing a total similarity function. We evaluate the applicability of BCS to view selection in a view-based object recognition environment.