Skip to Content


International Workshop on Computer vision + ONTology: Applied Cross-disciplinary Technologies (CONTACT 2016)

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, knowledge-based 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).

This semantic layer provides in principle the meaning of the symbolic forms associated to visual entities. In order to develop a principled methodology to ascribe meaning to images and videos, we need ontologies for modelling the domain knowledge, for providing an interpretation of the vocabulary chosen for the visual description of a domain, and for reasoning about the conceptualization of the visual entities.

The process of ascribing meaning to visual elements is a delicate and crucial step in computer vision, an effective modelling of this process is the key to enable a number of applications such that querying image databases, reasoning about images and scenes, inferring information from videos.

The aim of the CONTACT series is to bring together a wide range of researchers in formal ontology on the one side and computer vision and machine learning on the other, to share innovative ideas and solutions for exploiting the potential synergies emerging from the integration of the two domains, 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.

This is the second edition of CONTACT ( and it aims to address specifically scholar in ontology for promoting the applications of techniques developed in ontology and knowledge representation to computer vision.

Important dates:

Submission (abstracts): April 19, 3 May, 2016
Submission (full papers): April 25, 9 May, 2016
Notification: 12 May, 30 May, 2016
Camera ready: 31 May, 15 June 2016

FOIS early registration: 5 June, 2016.
Workshop:  6, July 2016.

Organizing Committee:

Marco Cristani (,,

Céline Hudelot (,,

Daniele Porello (,

about seo | story