Login Form

Editors

Activity recognition results on UCF Sports and Holywood2

Table above shows the results, obtained on UCF Sports dataset (http://crcv.ucf.edu/data/UCF_Sports_Action.php). We report recognition rate with respect to the number...


Read More...

Computational efficiency and parallel implementation

The developed algorithms are computationally effective and the compositional processing pipeline is well-suited for implementation on massively parallel architectures. Many...


Read More...

Motion hierarchy structure

Our model is comprised of three processing stages, as shown in the Figure. The task of the lowest stage (layers...


Read More...

Server crash

After experiencing a total server failure, we are back online. We apologize for the inconvenience - we are still in...


Read More...

L1: motion features

Layer L1 provides an input to the compositional hierarchy. Motion, obtained in L0 is encoded using a small dictionary.


Read More...
01234

Dissemination

Work package leader: ABR

This work package will be used for dissemination and exploitation of results of the project and popularization of the topic among students and researchers. At the beginning of the project a web­page with all relevant information about the project will be set up. The page will contain links and key references from the research field and a calendar with events of interest (related conferences, expos, fairs). During the project, the web page will be updated with results in the form of published papers, technical reports, as well as images and videos. News and results will be published in the form of a blog, that will be one way of maximizing the number of returning visitors to our web­page.

We will pay extra attention to mentoring of the students and researchers. They will be encouraged to pursue assignments related to the topics of the project. Students attending courses, related to computer vision will also have access to our implementations which will provide a good platform for their own exploration and learning from the results of this project.

In the project databases of motion categories will be assembled. These will be given to other computer vision researchers with the vision of developing and testing new learning algorithms for motion detection and categorization.

This website uses cookies to manage authentication, navigation, and other functions. By using our website, you agree that we can place these types of cookies on your device.

View e-Privacy Directive Documents

You have declined cookies. This decision can be reversed.

You have allowed cookies to be placed on your computer. This decision can be reversed.