LP$^{2}$DH: A Locality-Preserving Pixel-Difference Hashing Framework for Dynamic Texture Recognition

TL;DR

The paper introduces LP$^{2}$DH, a novel hashing framework for dynamic texture recognition that preserves locality and achieves state-of-the-art accuracy on major benchmarks.

Contribution

It proposes a joint encoding and optimization method that preserves local structure in pixel differences, improving dynamic texture recognition performance.

Findings

Achieved 99.80% accuracy on UCLA benchmark.

Outperformed existing methods on DynTex++ and YUPENN datasets.

Source code is publicly available at the provided GitHub link.

Abstract

Spatiotemporal Local Binary Pattern (STLBP) is a widely used dynamic texture descriptor, but it suffers from extremely high dimensionality. To tackle this, STLBP features are often extracted on three orthogonal planes, which sacrifice inter-plane correlation. In this work, we propose a Locality-Preserving Pixel-Difference Hashing (LP$^{2}$DH) framework that jointly encodes pixel differences in the full spatiotemporal neighbourhood. LP$^{2}$DH transforms Pixel-Difference Vectors (PDVs) into compact binary codes with maximal discriminative power. Furthermore, we incorporate a locality-preserving embedding to maintain the PDVs' local structure before and after hashing. Then, a curvilinear search strategy is utilized to jointly optimize the hashing matrix and binary codes via gradient descent on the Stiefel manifold. After hashing, dictionary learning is applied to encode the binary vectors into codewords, and the resulting histogram is utilized as the final feature representation. The proposed LP$^{2}$DH achieves state-of-the-art performance on three major dynamic texture recognition benchmarks: 99.80% against DT-GoogleNet's 98.93% on UCLA, 98.52% against HoGF$^{3D}$'s 97.63% on DynTex++, and 96.19% compared to STS's 95.00% on YUPENN. The source code is available at: https://github.com/drx770/LP2DH.