CVSSP, University of Surrey

Optional Sidebar Info

Any information can be placed in the sidebar to help your website visitors navigate your site.

To make a boxed heading like the one above, simply apply the H3 tag.

To make a box like this, assign the "sidebarlt" class.

You can do anything with a sidebar box. Insert images, ads or other web content.

Here's a text link.

To make a box like this, assign the "sidebardk" class.

You can do anything with a sidebar box. Insert images, ads or other web content.

Here's a text link.

CVSSP, University of Surrey



Transfer learning techniques are motivated by the fact that people can intelligently apply knowledge learned previously to solve new problems faster or with better solutions in different (but related) domains.
Brief Introduction to Transfer Learning Concept

ACASVA actions dataset

Nazli FarajiDavar and Teofilo deCampos













                     

Player's action recognition is one of the challenges in the ACASVA project. The goal is to classify each action sample into three classes: Non-Hit, Hit and Serve. We have done simple classification experiments [3] and transductive transfer learning experiments [1][2]. The splits of data (for training, validation, testing) are done per game match, please see the references below for further detail.

Following deCampos et al [3], we used HOG3D descriptors extracted on player bounding boxes. Two different sets of feature extraction parameters were used: the 960D parameters (4x4x3x20) optimised for the KTH dataset and the 300D parameters (2x2x5x5x3) optimised for the Hollywood dataset (see Alexander Klaser's page for details). In our preliminary experiments, we found that the KTH parameters (960D) give better results for the tennis dataset.



Datasets:

CityPulse: codes


References

The following papers give further descriptions of this dataset and experiments:

[1] N. FarajiDavar and T. deCampos and J. Kittler and F.Yang
Transductive Transfer Learning for Action Recognition in Tennis Games
In 3rd International Workshop on Video Event Categorization, Tagging and Retrieval for Real-World Applications (VECTaR), in conjunction with 13th Internatinal Conference on Computer Vision, Barcelona, Spain 2011

[2] N. FarajiDavar and T. deCampos and D. Windridge and J. Kittler and W. Christmas
Domain Adaptation in the Context of Sport Video Action Recognition
In Domain Adaptation Workshop, in conjunction with NIPS, Sierra Nevada, Spain 2011

[3] T. deCampos and M. Barnard and K. Mikolajczyk and J. Kittler and F. Yan and W. Christmas and D. Windridge
An evaluation of bags-of-words and spatio-temporal shapes for action recognition
In IEEE Workshop on Applications of Computer Vision (WACV), 2011