Learning graphs to model visual objects across different depictive styles
Files
(Restricted Access)
Date
2014
Authors
Wu, Q.
Cai, H.
Hall, P.
Editors
Fleet, D.
Pajdia, T.
Schiele, B.
Tuytelaars, T.
Pajdia, T.
Schiele, B.
Tuytelaars, T.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Lecture Notes in Artificial Intelligence, 2014 / Fleet, D., Pajdia, T., Schiele, B., Tuytelaars, T. (ed./s), vol.VII, iss.PART 7, pp.313-328
Statement of Responsibility
Qi Wu, Hongping Cai, and Peter Hall
Conference Name
13th European Conference on Computer Vision (ECCV) (6 Sep 2014 - 12 Sep 2014 : Zurich, Switzerland)
Abstract
Visual object classification and detection are major problems in contemporary computer vision. State-of-art algorithms allow thousands of visual objects to be learned and recognized, under a wide range of variations including lighting changes, occlusion, point of view and different object instances. Only a small fraction of the literature addresses the problem of variation in depictive styles (photographs, drawings, paintings etc.). This is a challenging gap but the ability to process images of all depictive styles and not just photographs has potential value across many applications. In this paper we model visual classes using a graph with multiple labels on each node; weights on arcs and nodes indicate relative importance (salience) to the object description. Visual class models can be learned from examples from a database that contains photographs, drawings, paintings etc. Experiments show that our representation is able to improve upon Deformable Part Models for detection and Bag of Words models for classification.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© Springer International Publishing Switzerland 2014