Coding time-varying signals using sparse, shift-invariant representations
Proceedings of the 1998 conference on Advances in neural information processing systems II
Efficient Coding of Time-Relative Structure Using Spikes
Neural Computation
A primitive based generative model to infer timing information in unpartitioned handwriting data
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation
International Journal of Robotics Research
Decomposition and dictionary learning for 3D trajectories
Signal Processing
| Hi-index | 0.00 |
We interpret biological motion trajectories as being composed of sequences of sub-blocks or motion primitives. Such primitives, together with the information, when they occur during an observed trajectory, provide a compact representation of movement in terms of events that is invariant to temporal shifts. Based on this representation, we present a model for the generation of motion trajectories that consists of two layers. In the lower layer, a trajectory is generated by activating a number of motion primitives from a learned dictionary, according to a given set of activation times and amplitudes. In the upper layer, the process generating the activation times is modeled by a group of Integrate-and-Fire neurons that emits spikes, dependent on a given class of trajectories, that activate the motion primitives in the lower layer. We learn the motion primitives together with their activation times and amplitudes in an unsupervised manner from unpartitioned data, with a variant of shift-NMF that is extended to support the event-like encoding. We present our model on the generation of handwritten character trajectories and show that we can generate good reconstructions of characters with shared primitives for all characters modeled.