Automatic Image Collection of Objects with Similar Function by Learning Human Grasping Forms -- Client Specific Image Gradient Orientation for Unimodal and Multimodal Face Representation -- Multiple-Manifolds Discriminant Analysis for Facial Expression Recognition from Local Patches Set -- Monte Carlo Based Importance Estimation of Localized Feature Descriptors for the Recognition of Facial Expressions -- Noisy Speech Recognition Based on Combined Audio-Visual Classifiers -- Complementary Gaussian Mixture Models for Multimodal Speech Recognition -- Fusion of Text and Audio Semantic Representations Through CCA -- uulmMAD - A Human Action Recognition Dataset for Ground-Truth Evaluation and Investigation of View Invariances -- A Real Time Gesture Recognition System for Human Computer Interaction -- A SIFT-Based Feature Level Fusion of Iris and Ear Biometrics -- Audio-Visual User Identification in HCI Scenarios -- Towards an Adaptive Brain-Computer Interface - An Error Potential Approach -- Online Smart Face Morphing Engine with Prior Constraints and Local Geometry Preservation -- Exploring Alternate Modalities for Tag Recommendation.