SHREC'08 entry: Training set expansion via autotags

Goldfeder, Corey; Feng, Haoyun; Allen, Peter K.

Training a 3D model classifier on a small dataset is very challenging. However, large datasets of partially classified models are now commonly available online. We use an external training set of models with associated text tags to automatically assign tags to both training and query models. The similarity between these tags, used in conjunction with a standard shape descriptor, yields a multiclassifier that outperforms the standalone shape descriptor.


Also Published In

IEEE International Conference on Shape Modeling and Applications 2008: Stony Brook, New York, USA, June 4-6, 2008: Proceedings

More About This Work

Academic Units
Computer Science
Published Here
October 31, 2012