Frank Keller - Centre for Cognitive Science, University of Edinburgh

Frank Keller
Are you Frank Keller?

Claim your profile, edit publications, add additional information:

Contact Details

Frank Keller
Centre for Cognitive Science, University of Edinburgh
United Kingdom

Pubs By Year

Pub Categories

Computer Science - Computation and Language (5)
Computer Science - Computer Vision and Pattern Recognition (5)
Mathematical Physics (3)
Mathematics - Mathematical Physics (3)
Mathematics - Quantum Algebra (2)

Publications Authored By Frank Keller

A large amount of recent research has focused on tasks that combine language and vision, resulting in a proliferation of datasets and methods. One such task is action recognition, whose applications include image annotation, scene under- standing and image retrieval. In this survey, we categorize the existing ap- proaches based on how they conceptualize this problem and provide a detailed review of existing datasets, highlighting their di- versity as well as advantages and disad- vantages. Read More

Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotation time by proposing center-click annotations: we ask annotators to click on the center of an imaginary bounding box which tightly encloses the object instance. Read More

When humans read text, they fixate some words and skip others. However, there have been few attempts to explain skipping behavior with computational models, as most existing work has focused on predicting reading times (e.g. Read More

We introduce a new task, visual sense disambiguation for verbs: given an image and a verb, assign the correct sense of the verb, i.e., the one that describes the action depicted in the image. Read More

Training object class detectors typically requires a large set of images in which objects are annotated by bounding-boxes. However, manually drawing bounding-boxes is very time consuming. We propose a new scheme for training object detectors which only requires annotators to verify bounding-boxes produced automatically by the learning algorithm. Read More

Automatic description generation from natural images is a challenging problem that has recently received a large amount of interest from the computer vision and natural language processing communities. In this survey, we classify the existing approaches based on how they conceptualize this problem, viz., models that cast description as either generation problem or as a retrieval problem over a visual or multimodal representational space. Read More

In this paper we define Courant algebroids in a purely algebraic way and study their deformation theory by using two different but equivalent graded Poisson algebras of degree -2. First steps towards a quantization of Courant algebroids are proposed by employing a Fedosov like deformation quantization. Read More

In this paper we set-up a general framework for a formal deformation theory of Dirac structures. We give a parameterization of formal deformations in terms of two-forms obeying a cubic equation. The notion of equivalence is discussed in detail. Read More

In this diploma thesis we discuss the deformation theory of Lie algebroids and Dirac structures. The first chapter gives a short introduction to Dirac structures on manifolds as introduced by Courant in 1990. We also give some physical applications of Dirac structures. Read More

Authors: Frank Keller1
Affiliations: 1Centre for Cognitive Science, University of Edinburgh

This paper investigates the syntax of extraposition in the HPSG framework. We present English and German data (partly taken from corpora), and provide an analysis using lexical rules and a nonlocal dependency. The condition for binding this dependency is formulated relative to the antecedent of the extraposed phrase, which entails that no fixed site for extraposition exists. Read More