Free-form deformation of solid geometric models
SIGGRAPH '86 Proceedings of the 13th annual conference on Computer graphics and interactive techniques
WordNet: a lexical database for English
Communications of the ACM
Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
ACM Transactions on Graphics (TOG)
Rotation invariant spherical harmonic representation of 3D shape descriptors
Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on Geometry processing
Automatic three-dimensional modeling from reality
Automatic three-dimensional modeling from reality
Efficient MAP approximation for dense energy functions
ICML '06 Proceedings of the 23rd international conference on Machine learning
Uncovering shared structures in multiclass classification
Proceedings of the 24th international conference on Machine learning
Shape Classification and Analysis: Theory and Practice
Shape Classification and Analysis: Theory and Practice
Semi-supervised metric learning using pairwise constraints
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Exact Matrix Completion via Convex Optimization
Foundations of Computational Mathematics
Global correspondence optimization for non-rigid registration of depth scans
SGP '08 Proceedings of the Symposium on Geometry Processing
Semi-supervised distance metric learning for collaborative image retrieval and clustering
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Style-content separation by anisotropic part scales
ACM SIGGRAPH Asia 2010 papers
Exploring collections of 3D models using fuzzy correspondences
ACM Transactions on Graphics (TOG) - SIGGRAPH 2012 Conference Proceedings
A probabilistic model for component-based shape synthesis
ACM Transactions on Graphics (TOG) - SIGGRAPH 2012 Conference Proceedings
Foundations and Trends® in Machine Learning
Discrete-continuous optimization for large-scale structure from motion
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Combining randomization and discrimination for fine-grained image categorization
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Active co-analysis of a set of shapes
ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH Asia 2012
An optimization approach for extracting and encoding consistent maps in a shape collection
ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH Asia 2012
Learning part-based templates from large collections of 3D shapes
ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
Fine-Grained Crowdsourcing for Fine-Grained Recognition
CVPR '13 Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition
Hi-index | 0.00 |
In this paper we consider the problem of classifying shapes within a given category (e.g., chairs) into finer-grained classes (e.g., chairs with arms, rocking chairs, swivel chairs). We introduce a multi-label (i.e., shapes can belong to multiple classes) semi-supervised approach that takes as input a large shape collection of a given category with associated sparse and noisy labels, and outputs cleaned and complete labels for each shape. The key idea of the proposed approach is to jointly learn a distance metric for each class which captures the underlying geometric similarity within that class, e.g., the distance metric for swivel chairs evaluates the global geometric resemblance of chair bases. We show how to achieve this objective by first geometrically aligning the input shapes, and then learning the class-specific distance metrics by exploiting the feature consistency provided by this alignment. The learning objectives consider both labeled data and the mutual relations between the distance metrics. Given the learned metrics, we apply a graph-based semi-supervised classification technique to generate the final classification results. In order to evaluate the performance of our approach, we have created a benchmark data set where each shape is provided with a set of ground truth labels generated by Amazon's Mechanical Turk users. The benchmark contains a rich variety of shapes in a number of categories. Experimental results show that despite this variety, given very sparse and noisy initial labels, the new method yields results that are superior to state-of-the-art semi-supervised learning techniques.