An investigation into face pose distributions

S Gong, S McKenna, JJ Collins - Proceedings of the Second …, 1996 - ieeexplore.ieee.org
Visual perception of faces is invariant under many transformations, perhaps the most
problematic of which is pose change (face rotating in depth). We use a variation of Gabor …

Understanding dynamic scenes

A Chella, M Frixione, S Gaglio - Artificial intelligence, 2000 - Elsevier
We propose a framework for the representation of visual knowledge in a robotic agent, with
special attention to the understanding of dynamic scenes. According to our approach …

Recognition of human gestures and behaviour based on motion trajectories

A Psarrou, S Gong, M Walter - Image and Vision Computing, 2002 - Elsevier
Human activities are characterised by the spatio-temporal structure of their motion patterns.
Such structures can be represented as temporal trajectories in a high-dimensional feature …

Comparisons between human and computer recognition of faces

V Bruce, PJB Hancock… - Proceedings Third IEEE …, 1998 - ieeexplore.ieee.org
The paper reviews the characteristics of human face recognition that should be reflected in
any psychologically plausible computational model of face recognition. We then summarise …

Tracking faces

S McKenna, S Gong - Proceedings of the Second International …, 1996 - ieeexplore.ieee.org
Robust tracking and segmentation of faces is a prerequisite for face analysis and
recognition. In this paper we describe an approach to this problem which is well suited to …

[PDF][PDF] Real-time tracking for an integrated face recognition system

S McKenna, S Gong, H Liddell - … Workshop on Parallel Modelling of Neural …, 1995 - Citeseer
A real-time tracking system suitable for surveillance applications was implemented on
pipeline image processing hardware. Motion estimation was performed using a symmetric …

Learning object behaviour models

N Johnson - 1998 - etheses.whiterose.ac.uk
The human visual system is capable of interpreting a remarkable variety of often subtle,
learnt, characteristic behaviours. For instance we can determine the gender of a distant …

A connectionist model of spatial knowledge acquisition in a virtual environment

C Sas, GMP O'Hare, R Reilly - … of MLIRUM'03 Second …, 2003 - researchrepository.ucd.ie
This paper proposes the use of neural networks as a tool for studying navigation within
virtual worlds. Results indicate that network learned to predict the next step for a given …

[PDF][PDF] Learning Gestures for Visually Mediated Interaction.

AJ Howell, H Buxton - BMVC, 1998 - Citeseer
This paper reports initial research on supporting Visually Mediated Interaction (VMI) by
develo** person-specific and generic gesture models for the control of active cameras …

[PDF][PDF] Identifying people caught on video

V Bruce - Psychologist, 1998 - Citeseer
E-mail: vicki. bruce@ stir. ac. uk plications which may affect the accuracy of the witness. For
example, people experience difficulties when identifying faces of people of another race …