Computer vision + ONTology Applied Cross-disciplinary Technologies @ ECCV 2014, Zurich, September 7, 2014.
Image and video understanding is the process of converting elementary visual entities (pixels, voxels) to symbolic forms of knowledge (textual tags, predicates), by means of various kinds of models (statistical classifiers, neural networks, expert systems, etc.). It represents the highest processing level in a computer vision system, operating usually on top of a basic processing layer, which extracts intermediate image representations (patches, volumes). Due to the unconstrained nature of photographic images and videos, and the lack of fully reliable low-level features, the process of image understanding may be helped grounding it with a prior semantic model describing any domain knowledge, which may operate during both learning and inference. This semantic layer is usually represented by means of an ontology, intended as a set of primitive concepts and relations expressed by axioms providing an interpretation to the vocabulary chosen for the visual description of a domain.
After the early steps in the eighties, the research domain that cross-pollinates computer vision and formal ontology stagnated, limited probably by the lack of available domain ontologies. However, more recently, with the creation of shared resources as ImageNet, TinyImage, Labelme, on the computer vision side, and WordNet on the formal ontology side, the area exploded, leading to an exponential growth in the scientific community.
The aim of CONTACT 2014 is to bring together a wide range of researchers in computer vision and machine learning on one side, and formal ontology on the other, to share innovative ideas and solutions for exploiting the potential synergies emerging from the integration of the two domains, for object and event recognition, scene, image and video understanding, with the long term goals of promoting the development of a proper visual ontology and a better understanding of how such a visual ontology could be used for visual inference.
CONTACT 2014 will be the first of a series of events which will have an interesting yet unique characteristic: in order to gradually connect the communities of computer vision and formal ontologies in a tight relationship, the CONTACT workshop will be hosted iteratively in a major computer vision conference (as ECCV is) and in a major ontology conference (as FOIS - Formal Ontologies for Information Systems): this way, the cross-fertilization will take place by involving the best of the two communities, with alternative emphasis on one facet or the other.