Dynamic Texture Recognition via Nuclear Distances on Kernelized Scattering Histogram Spaces
TL
TL;DR
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.
Abstract
Distance-based dynamic texture recognition is an important research field in multimedia processing with applications ranging from retrieval to segmentation of video data. Based on the conjecture that the most distinctive characteristic of a dynamic texture is the appearance of its individual frames, this work proposes to describe dynamic textures as kernelized spaces of frame-wise feature vectors computed using the Scattering transform. By combining these spaces with a basis-invariant metric, we get a framework that produces competitive results for nearest neighbor classification and state-of-the-art results for nearest class center classification.
References21 items
1
Dynamic Texture Classification Using Unsupervised 3D Filter Learning and Local Binary Encoding
2
Kymatio: Scattering Transforms in Python
3
Completed local structure patterns on three orthogonal planes for dynamic texture recognition
4
Dynamic Texture Recognition Using Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields
5