Discriminative Object Class Models of Appearance and Shape by Correlatons

  title={Discriminative Object Class Models of Appearance and Shape by Correlatons},
  author={Silvio Savarese and John M. Winn and Antonio Criminisi},
  journal={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
  • S. Savarese, J. Winn, A. Criminisi
  • Published 17 June 2006
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
This paper presents a new model of object classes which incorporates appearance and shape information jointly. Modeling objects appearance by distributions of visual words has recently proven successful. Here appearancebased models are augmented by capturing the spatial arrangement of visual words. Compact spatial modeling without loss of discrimination is achieved through the introduction of adaptive vector quantized correlograms, which we call correlatons. Efficiency is further improved by… 
Shape and Appearance Context Modeling
In this work we develop appearance models for computing the similarity between image regions containing deformable objects of a given class in realtime. We introduce the concept of shape and
A geometric constrained HCRF for object recognition
  • Yingtuan Hou, Xuetao Zhang
  • Mathematics
    2015 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)
  • 2015
In the present paper, a discriminative model for object recognition based on the Hidden Conditional Random Fields (HCRF) model is proposed. It impose the constraints on the positions of object parts
Learning spatial relations and shapes for structural object description and scene recognition
The Force Histogram Decomposition is presented, a graph-based hierarchical descriptor that allows to characterize the spatial relations and shape information between the pairwise structural subparts of objects and a novel bags-of-features framework is proposed, in order to produce discriminative structural features that are tailored for particular object classification tasks.
Spatial encoding of visual words for image classification
A unified representation that enhances BoVWs with explicit local and global structure models is presented that outperforms the conventional models and compares favorably to more sophisticated scene classification techniques.
Part-based object detection into a hierarchy of image segmentations combining color and topology
A novel part-based approach for automatic object detection using 2D images that encodes the visual structures of the object to be detected and the image by a 2D combinatorial map and a Combinatorial pyramid, respectively.
Describing Visual Scene through EigenMaps
—We propose a novel approach to describe and recognize visual scene categories. Inspired by the success of Bag of Words approach, we represent a scene image using a collection of EigenMaps, which
Structural Context for Object Categorization
This newly proposed descriptor can provide more discriminative representation of the object category, being invariant to intra-class difference, scale change, illumination variation, clutter noise, partial occlusion, small range of deformation, rotation and viewpoint change.
Semantic Image Segmentation and Web-Supervised Visual Learning
A compact model is introduced, where each class is modelled by a single histogram of visual-words, in contrast to common nearest-neighbour approaches which model each class by storing exemplar histograms, and segmentation algorithms based on these histograms are introduced.
Spatial histograms of soft pairwise similar patches to improve the bag-of-visual-words model
A novel way to incorporate both distance and angle information in the BoVW representation to provide a computationally efficient representation adding relative spatial information between visual words and to use a soft pairwise voting scheme based on the distance in the descriptor space.
Implicit Scene Context for Object Segmentation and Classification
The aim is to learn object-context from the background class of partially labeled images which is called implicit scene context (ISC), a CRF set up on image super-pixels that are clustered into multiple classes.


Object class recognition by unsupervised scale-invariant learning
  • R. Fergus, P. Perona, Andrew Zisserman
  • Mathematics, Computer Science
    2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).
Object Class Recognition Using Discriminative Local Features
In this paper, we introduce a scale-invariant feature selection method that learns to recognize and detect object classes from images of natural scenes. The first step of our method consists of
Unsupervised Learning of Models for Recognition
A method to learn object class models from unlabeled and unsegmented cluttered cluttered scenes for the purpose of visual object recognition that achieves very good classification results on human faces and rear views of cars.
Pictorial Structures for Object Recognition
A computationally efficient framework for part-based modeling and recognition of objects, motivated by the pictorial structure models introduced by Fischler and Elschlager, that allows for qualitative descriptions of visual appearance and is suitable for generic recognition problems.
A Fragment-Based Approach to Object Representation and Classification
Experimental results of detecting face and car views show that the fragment-based approach can generalize well to a variety of novel image views within a class while maintaining low mis-classification error rates.
Object categorization by learned universal visual dictionary
An optimally compact visual dictionary is learned by pair-wise merging of visual words from an initially large dictionary, and a novel statistical measure of discrimination is proposed which is optimized by each merge operation.
Contour-based learning for object detection
The major contributions are the application of boosted local contour-based features for object detection in a partially supervised learning framework, and an efficient new boosting procedure for simultaneously selecting features and estimating per-feature parameters.
Extending Pictorial Structures for Object Recognition
The goal of this paper is to recognize various deformable objects from images by extending the class of generative probabilistic models known as pictorial structures, particularly suited to represent articulated structures.
Visual categorization with bags of keypoints
This bag of keypoints method is based on vector quantization of affine invariant descriptors of image patches and shows that it is simple, computationally efficient and intrinsically invariant.
Discovering object categories in image collections
Given a set of images containing multiple object categories, we seek to discover those categories and their image locations without supervision. We achieve this using generative models from the