Book ChapterDOI
Shared Features for Multiclass Object Detection
Reads0
Chats0
TLDR
This work presents a learning procedure, based on boosted decision stumps, that reduces the computational and sample complexity, by finding common features that can be shared across the classes (and/or views).Citations
More filters
Journal ArticleDOI
Learning with Hierarchical-Deep Models
TL;DR: Efficient learning and inference algorithms for the HDP-DBM model are presented and it is shown that it is able to learn new concepts from very few examples on CIFAR-100 object recognition, handwritten character recognition, and human motion capture datasets.
Proceedings ArticleDOI
Unsupervised learning of visual taxonomies
TL;DR: The experiments show that a disorganized collection of images will be organized into an intuitive taxonomy and it is found that the taxonomy allows good image categorization and, in this respect, is superior to the popular LDA model.
Journal ArticleDOI
Object class detection: A survey
TL;DR: A comprehensive survey of the recent technical achievements in object class detection research, covering different aspects of the research, including core techniques: appearance modeling, localization strategies, and supervised classification methods.
Journal ArticleDOI
Friend or Foe: Fine-Grained Categorization With Weak Supervision
TL;DR: This paper investigates the applicability of MIL on an extreme case of weakly supervised learning on the task of fine-grained visual categorization, in which intra-class variance could be larger than inter-class due to the subtle differences between subordinate categories.
Book ChapterDOI
A Multiple Kernel Learning Approach to Joint Multi-class Object Detection
TL;DR: A method to combine the efficiency of single class localization with a subsequent decision process that works jointly for all given object classes is proposed by following a multiple kernel learning (MKL) approach and shows that the subsequent joint decision step clearly improves the accuracy compared to single class detection.
References
More filters
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Proceedings ArticleDOI
Object recognition from local scale-invariant features
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Journal ArticleDOI
Robust Real-Time Face Detection
Paul A. Viola,Michael Jones +1 more
TL;DR: In this paper, a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates is described. But the detection performance is limited to 15 frames per second.
Proceedings ArticleDOI
Robust real-time face detection
Paul A. Viola,Michael Jones +1 more
TL;DR: A new image representation called the “Integral Image” is introduced which allows the features used by the detector to be computed very quickly and a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions.
Journal ArticleDOI
Wrappers for feature subset selection
Ron Kohavi,George H. John +1 more
TL;DR: The wrapper method searches for an optimal feature subset tailored to a particular algorithm and a domain and compares the wrapper approach to induction without feature subset selection and to Relief, a filter approach tofeature subset selection.