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

Task 3.1: Identification of processing bottlenecks

Usually, the processing load is not evenly distributed throughout the algorithm. Typically, there are only a few places in the algorithm, where optimization of the code results in a significant overall performance improvement. Identification of such critical sections is of crucial importance for any optimization. In this regard, hierarchical compositional models offer certain advantage. Although they are complex, and may require significant processing power at various stages of their implementation, they’re also highly structured, and enable structured approach to parallelization. On the other hand, the problem domain can be decomposed into many subdomains that can be executed independently. Further, the decomposition is possible in the temporal domain as well. Small amounts of communications are needed on the subdomain borders and between time slots of video streams. We expect that the structured nature and fine grained domain decomposition will enable us to identify the critical points.

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.