Learn More
Modern visual recognition systems are often limited in their ability to scale to large numbers of object categories. This limitation is in part due to the increasing difficulty of acquiring sufficient training data in the form of labeled images as the number of object categories grows. One remedy is to leverage data from other sources – such as text data –(More)
Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image transformation. In other cases the semantic embedding space is established by an independent natural language processing task, and then the image transformation into that space is(More)
Recognition of three dimensional (3D) objects in noisy and cluttered scenes is a challenging problem in 3D computer vision. One approach that has been successful in past research is the regional shape descriptor. In this paper, we introduce two new regional shape descriptors: 3D shape contexts and harmonic shape contexts. We evaluate the performance of(More)
We address the problem of visual category recognition by learning an image-to-image distance function that attempts to satisfy the following property: the distance between images from the same category should be less than the distance between images from different categories. We use patch-based feature vectors common in object recognition work as a basis(More)
(x − x)A(x − x) Mahalanobis distance: Previous work on learning metrics has focused on learning a single distance metric for all instances. One of our primary contributions is to learn a distance function for every training image. Most visual categorization approaches make use of machine learning after computing distances between images (e.g. SVM with(More)
In this paper we study how to perform object classification in a principled way that exploits the rich structure of real world labels. We develop a new model that allows encoding of flexible relations between labels. We introduce Hierarchy and Exclusion (HEX) graphs, a new formalism that captures semantic relations between any two labels applied to the same(More)
The last two years have witnessed the introduction and rapid expansion of products based upon large, systematically-gathered, street-level image collections, such as Google Street View, EveryScape, and Mapjack. In the process of gathering images of public spaces, these projects also capture license plates, faces, and other information considered sensitive(More)