We introduce an extension of bag-of-words image representations to encode spatial layout. Using the Fisher kernel framework we derive a representation that encodes the spatial mean and the variance of image regions associated with visual words. We extend this representation by using a Gaussian mixture model to encode spatial layout, and show that this model is related to a soft-assign version o...

Local features have repeatedly shown their effectiveness for object recognition during the last years, and they have consequently become the preferred descriptor for this type of problems. The solution of the correspondence problem is traditionally approached with exact or approximate techniques. In this paper we are interested in methods that solve the correspondence problem via the definition...

Spatial pyramid matching (SPM) has been an important approach to image categorization. This method partitions the image into increasingly fine sub-regions and computes histograms of local features at each sub-region. Although SPM is an efficient extension of an unordered bag-of-features image representation, it still measures the similarity between sub-regions by application of the ba...

Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification methods can learn complex decision boundaries, but a kernel over unordered set inputs must somehow solve for correspondences – generally a computationally expensive task that becomes impractical for large set sizes. We ...

Discriminative learning is challenging when examples are sets of local image features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification methods can learn complex decision boundaries, but a kernel similarity measure for unordered set inputs must somehow solve for correspondences – generally a computationally expensive task that becomes imprac...

By always mapping data from lower dimensional space into higher or even infinite dimensional space, kernel k-means is able to organize data into groups when data of different clusters are not linearly separable. However, kernel k-means incurs the large scale computation due to the representation theorem, i.e. keeping an extremely large kernel matrix in memory when using popular Gaussian and spa...

This project focuses on automating the classification of 4700+ photographs from 29 insect species, developing ideas in computer vision and machine learning. Autonomous categorization aims at reducing the manual cost and the number of mistakes even when compared to experts. Therefore, to be competitive, improving accuracy is important. Challenges to accuracy in the 29-category dataset are presen...

In this paper we present an object search behavior for a mobile domestic robot that reduces the search space by applying a novel kind of spatial attention system. Different visual cues are mapped in a SLAM-like manner in order to identify hypotheses for possible object locations. These locations are scanned for known objects using a recognition method consisting of two complementary pathways – ...

This chapter deals with the problem of whole-image categorization. We may want to classify a photograph based on a high-level semantic attribute (e.g., indoor or outdoor), scene type (forest, street, office, etc.), or object category (car, face, etc.). Our philosophy is that such global image tasks can be approached in a holistic fashion: It should be possible to develop image representations t...