3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in dynamic-texture-recognition-7
No benchmarks available.
Use these libraries to find dynamic-texture-recognition-7 models and implementations
No datasets available.
No subtasks available.
A novel hierarchical spatiotemporal orientation representation for spacetime image analysis designed to combine the benefits of the multilayer architecture of ConvNets and a more controlled approach to spacetime analysis is presented.
This work proposes to describe dynamic textures as kernelized spaces of frame-wise feature vectors computed using the Scattering transform, resulting in a framework that produces competitive results for nearest neighbor classification and state-of-the-art results for closest class center classification.
Adding a benchmark result helps the community track progress.