We investigate experimentally that equal bit ratios are indeed preferable and show that our method leads to optimization benefits.
Frequency information lies at the base of discriminating between textures, and therefore between different objects.
We use scale-space theory to obtain a self-similar parametrization of filters and make use of the N-Jet: a truncated Taylor series to approximate a filter by a learned combination of Gaussian derivative filters.
A common heuristic is uniformly sampling a small number of video frames and using these to recognize the action.
Here, we reduce the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features.
Ranked #3 on Line Segment Detection on wireframe dataset (sAP5 metric)
Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and preferential processing given relevant stimuli.
We design these complex filters to resemble complex Gabor filters, typically employed for phase-information extraction.
This enables each center to adjust the kernel space in its vicinity in correspondence with the topology of the targets --- a multi-modal approach.
This method introduces an efficient manner of learning action categories without the need of feature estimation.