Dr Irene Kotsia, School of Electronic Engineering and Computer Science, Queen Mary, University of London

Biography: Irene Kotsia received the diploma and PhD in Informatics from the Aristotle University o Thessaloniki, Greece in 2002 and 2008, respectively. From 2008 to 2009 she was a Research Associate in Artificial Intelligence and Information Analysis (AIIA) laboratory in the department of Informatics at Aristotle University of Thessaloniki. Since September 2009 she has been a Research Associate with the Multimedia and Vision Research group (MMV) in School of Electronic Engineering and Computer Science, Queen Mary University of London. She has coauthored many journal publications in a number of scientific journals, including IEEE Transactions on Image Processing, IEEE Transactions on Neural Networks and IEEE Transactions on Forensics and Security. Her current research interests lie in the areas of image and signal processing, statistical pattern recognition especially for human actions localization and recognition, facial expression recognition from static images and image sequences as well as in the areas of graphics and animation.

Research Interests: 3D image & video processing and graphics, Machine Learning - Computational Intelligence, Computer Vision, Human Computer Interaction, Ambient Intelligence, Biometry.

Human motion recognition is nowadays one of the most active fields of computer vision, as its applications span several areas, such as retrieval, surveillance and Human-Computer Interaction. Our aim is to be able to localize the motion appearing in an unsegmented image sequence, such as Hollywood movies, and correctly identify it. Once trained, the methods should be able to detect and localise in an unseen image sequence, all the actions that belong to one of the known categories. The methodologies will allow training the models in image sequences in which there is significant background clutter, that is in the presence of multiple objects/actions in the scene and moving cameras. No prior knowledge of the anatomy of the human body is a-priori considered, and therefore the models will be able to identify a large class of action categories, including facial/hand/body actions, animal motion, as well as interaction between humans and objects in their environment (such as drinking a glass of water).

The CP decomposition of tensors. This work aims at addressing the classification and regresion problems within a tensorial framework. We exploit the advantages offered by tensorial representations and propose several tensor learning models. We employ tensors in order to better retain and utilize information about the structure of the high dimensional space the data lie in, for example about the spatial arrangement of the pixel-based features in a 2D image. We formulate our algorithms considering that the weights parameters are expressed as a tensor of multiple modes and employ well known tensor decompositions. In that way the weights tensor in the resulting models can allow simultaneous projections to more than one directions along each mode or can be written as the multiplication of a core tensor with a matrix along each mode. The Tucker decomposition of tensors. The proposed classification algorithms deal with badly scaled data and are able to achieve compression. We also exploit the information provided by the total or the within-class covariance matrix and whiten the data, thus providing invariance to affine transformations in the feature space. Regarding regression, we approach the problem by employing two empirical risk functions both formulated using the Frobenius norm for regularization. We also use the group sparsity norm for regularization, favoring in that way the low rank decomposition of the tensorial weight and achieving the automatic selection of the rank during the learning process.