# LP2DH: A Locality-Preserving Pixel-Difference Hashing Framework for Dynamic Texture Recognition

arXiv: https://arxiv.org/abs/2604.15707 · HTML: https://mlsanity.com/paper/2604.15707/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 75 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [A Survey on Learning to Hash](https://mlsanity.com/paper/1606.00185/) (2016)
- [Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics](https://mlsanity.com/paper/2008.13426/) (2020)
- [Riemannian Hamiltonian methods for min-max optimization on manifolds](https://mlsanity.com/paper/2204.11418/) (2022)
- [Dynamic Facial Expression Recognition under Partial Occlusion with Optical Flow Reconstruction](https://mlsanity.com/paper/2012.13217/) (2020)
- [A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition](https://mlsanity.com/paper/1708.06690/) (2017)
- [Convolutional Neural Network on Three Orthogonal Planes for Dynamic Texture Classification](https://mlsanity.com/paper/1703.05530/) (2017)
- [Fault-Tolerant Control of Linear Quantum Stochastic Systems](https://mlsanity.com/paper/1806.02587/) (2018)
- [Learning Canonical Embeddings for Unsupervised Shape Correspondence with Locally Linear Transformations](https://mlsanity.com/paper/2209.02152/) (2022)
- [Dynamic Texture Recognition using PDV Hashing and Dictionary Learning on Multi-scale Volume Local Binary Pattern](https://mlsanity.com/paper/2111.12315/) (2021)
- [New vector transport operators extending a Riemannian CG algorithm to generalized Stiefel manifold with low-rank applications](https://mlsanity.com/paper/2311.00907/) (2023)

## Abstract (arXiv)

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 (LP2DH) framework that jointly encodes pixel differences in the full spatiotemporal neighbourhood. LP2DH 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 LP2DH 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 HoGF3D'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.