Recognition by Linear Combinations of Models
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Linear Object Classes and Image Synthesis From a Single Example Image
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes
International Journal of Computer Vision
Representation and recognition in vision
Representation and recognition in vision
The visual analysis of human movement: a survey
Computer Vision and Image Understanding
Parameterized modeling and recognition of activities
Computer Vision and Image Understanding
A hierarchical approach to interactive motion editing for human-like figures
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Morphable Models for the Analysis and Synthesis of Complex Motion Patterns
International Journal of Computer Vision - special issue on learning and vision at the center for biological and computational learning, Massachusetts Institute of Technology
| Hi-index | 0.01 |
Biological movements and actions are important visual stimuli. Their recognition is a highly relevant problem for biological as well as for technical systems. In the domain of stationary object recognition the concept of a prototype-based representation of object shape has been quite inspiring for research in computer vision as well as in neuroscience. The paper presents an overview of some recent work aiming at a generalization of such concepts for the domain of complex movements. First, a technical method is presented that allows to represent classes of complex movements by linear combinations of learned example trajectories. Applications of this method in computer vision and computer graphics are briefly discussed. The relevance of prototype-based representations for the recognition of complex movements in the visual cortex is discussed in the second part of the paper. By devising a simple neurophysiologically plausible model it is demonstrated that many experimental findings on the visual recognition of "biological motion" can be accounted for by a neural representation of learned prototypical motion patterns.