Abstract not found

We present a Bayesian framework for action recognition through ballistic dynamics. Psycho-kinesiological studies indicate that ballistic movements form the natural units for human movement planning. The framework leads to an efficient and robust algorithm for temporally segmenting videos into atomic movements. Individual movements are annotated with person-centric morphological labels called ballistic verbs. This is tested on a dataset of interactive movements, achieving high recognition rates. The approach is also applied on a gesture recognition task, improving a previously reported recognition rate from 84 % to 92%. Consideration of ballistic dynamics enhances the performance of the popular Motion History Image feature. We also illustrate the approach’s general utility on real-world videos. Experiments indicate that the method is robust to view, style and appearance variations. 1.

Abstract — Even seemingly simple reaching task requires complex integration or remapping of reference frames with respect to eye, head and hand. Head-centered reference frame and head movement may play important roles in natural tasks and in the development of reaching. To understand the underlying control mechanism that support smooth reaching in particular and the seamless coordination of head and hand movements more generally, a semi-naturalistic experiment is designed for 1 to 5 years old children, in which children are free to reach or not reach for the ball coming out from the slots on the puppet show. The fine-grained head and hand motion data were recorded. The analysis results show that (1) All the children participants stabilize their heads right before the reach; (2) During the reach, the head and hands move synergistically in the same direction. (3) Large and variable head movements co-occur with more variable and jerky reaches. The coupling of the head and hands may suggest a dynamical integration of multiple reference frames. Keywords- Head stabilization, Head hand coordination, Child reaching, Reference frame