Cognitive Image Understanding: Image representations and Multimodal learning

Project Information

COGNIMUND

Grant agreement ID: 240530

Project closed

Start date 1 February 2010

End date 31 January 2015

Funded under

• Specific programme: "Ideas" implementing the Seventh Framework Programme of the European Community for research, technological development and demonstration activities (2007 to 2013)

Total cost € 1 538 380,00

EU contribution € 1 538 380,00

Coordinated by

KATHOLIEKE UNIVERSITEIT LEUVEN
Belgium

Objective

One of the primary and most appealing goals of computer vision is to automatically understand the content of images on a cognitive level. Ultimately we want to have computers interpret images as we humans do, recognizing all the objects, scenes, and people as well as their relations as they appear in natural images or video. With this project, I want to advance the state of the art in this field in two directions, which I believe to be crucial to build the next generation of image understanding tools. First, novel more robust yet descriptive image representations will be designed, that incorporate the intrinsic structure of images. These should already go a long way towards removing irrelevant sources of variability while capturing the essence of the image content. I believe the importance of further research into image representations is currently underestimated within the research community, yet I claim this is a crucial step with lots of opportunities good learning cannot easily make up for bad features. Second, weakly supervised methods to learn from multimodal input (especially the combination of images and text) will be investigated, making it possible to leverage the large amount of weak annotations available via the internet. This is essential if we want to scale the methods to a larger number of object categories (several hundreds instead of a few tens). As more data can be used for training, such weakly supervised methods might in the end even come on par with or outperform supervised schemes. Here we will call upon the latest results in semi-supervised learning, datamining, and computational linguistics.

Fields of science

• humanities › languages and literature › linguistics
• natural sciences › computer and information sciences › artificial intelligence › machine learning › semisupervised learning
• natural sciences › computer and information sciences › internet
• natural sciences › computer and information sciences › artificial intelligence › computer vision

Programme(s)

• FP7-IDEAS-ERC - Specific programme: "Ideas" implementing the Seventh Framework Programme of the European Community for research, technological development and demonstration activities (2007 to 2013)

Topic(s)

• ERC-SG-PE6 - ERC Starting Grant - Computer science and informatics

Call for proposal

ERC-2009-StG
See other projects for this call

Funding Scheme

ERC-SG - ERC Starting Grant

Host institution

KATHOLIEKE UNIVERSITEIT LEUVEN

• EU contribution: € 1 538 380,00
• Address: OUDE MARKT 13 ; 3000 Leuven ; Belgium
• Region: Vlaams Gewest › Prov. Vlaams-Brabant › Arr. Leuven
• Activity type: Higher or Secondary Education Establishments
• Administrative Contact: Stijn Delauré (Dr.)
• Principal investigator: Tinne Tuytelaars (Prof.)
• Total cost: No data

Beneficiaries (1)

KATHOLIEKE UNIVERSITEIT LEUVEN

Belgium

• EU contribution: € 1 538 380,00
• Address: OUDE MARKT 13 ; 3000 Leuven
• Region: Vlaams Gewest › Prov. Vlaams-Brabant › Arr. Leuven
• Activity type: Higher or Secondary Education Establishments
• Administrative Contact: Stijn Delauré (Dr.)
• Principal investigator: Tinne Tuytelaars (Prof.)
• Total cost: No data