A survey of advances in vision-based human motion capture and analysis
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Fusing gait and face cues for human gender recognition
Neurocomputing
IEICE - Transactions on Information and Systems
| Hi-index | 0.00 |
We present a computational framework capable of labelingthe effort of an action corresponding to the perceivedlevel of exertion by the performer (low - high). The approachinitially factorizes examples (at different efforts) ofan action into its three-mode principal components to reducethe dimensionality. Then a learning phase is introducedto compute expressive-feature weights to adjust themodel's estimation of effort to conform to given perceptuallabels for the examples. Experiments are demonstrated recognizingthe efforts of a person carrying bags of differentweight and for multiple people walking at different paces.