Foundations and Trends® in Computer Graphics and Vision
Efficient Learning of Relational Object Class Models
International Journal of Computer Vision
Learning an Alphabet of Shape and Appearance for Multi-Class Object Detection
International Journal of Computer Vision
Weakly Supervised Object Localization with Stable Segmentations
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Object Class Recognition Using SNoW with a Part Vocabulary
RSFDGrC '07 Proceedings of the 11th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing
Multi-class classification on Riemannian manifolds for video surveillance
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part III
Co-occurrence random forests for object localization and classification
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
A boundary-fragment-model for object detection
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Hi-index | 0.00 |
We propose a new technique for object class recognition, which learns a generative appearance model in a discriminative manner. The technique is based on the intermediate representation of an image as a set of patches, which are extracted using an interest point detector. The learning problem becomes an instance of supervised learning from sets of unordered features. In order to solve this problem, we designed a classifier based on a simple, part based, generative object model. Only the appearance of each part is modeled. When learning the model parameters, we use a discriminative boosting algorithm which minimizes the loss of the training error directly. The models thus learnt have clear probabilistic semantics, and also maintain good classification performance. The performance of the algorithm has been tested using publicly available benchmark data, and shown to be comparable to other state of the art algorithms for this task; our main advantage in these comparisons is speed (order of magnitudes faster) and scalability.