Search UTSePress Research

Browse

Now showing items 4-8 of 8

Maximum-likelihood dimensionality reduction in Gaussian mixture models with an application to object classification

Piccardi Massimo; Gunes Hatice; Otoom Ahmed (IEEE, 2008)

Accurate classification of objects of interest for video surveillance is difficult due to occlusions, deformations and variable views/illumination. The adopted feature sets tend to overcome these issues by including many ...
Mixtures of Normalized Linear Projections

Otoom Ahmed; Concha Oscar; Gunes Hatice; Piccardi Massimo (Springer, 2009)

High dimensional spaces pose a challenge to any classification task. In fact, these spaces contain much redundancy and it becomes crucial to reduce the dimensionality of the data to improve analysis, density modeling, and ...
Observer Annotation of Affective Display and Evaluation of Expressivity: Face vs. Face-and-body

Gunes Hatice; Piccardi Massimo (Australian Computer Society, 2006)

A first step in developing and testing a robust affective multimodal system is to obtain or access data representing human multimodal expressive behaviour. Collected affect data has to be further annotated in order to ...
Towards Automatic Abandoned Object Classification in Visual Surveillance Systems

Otoom Ahmed; Gunes Hatice; Piccardi Massimo (National Cheng Kung University, 2007)
Video object encoder using selective local-space support vector machines

Tsai Po-Hsiang; Jan Tony; Gunes Hatice (IEEE, 2004)

NA

Now showing items 4-8 of 8