LP²DH jointly hashes spatiotemporal pixel-difference vectors with locality preservation and Stiefel-manifold optimization to produce compact binary features that achieve state-of-the-art accuracy on UCLA, DynTex++, and YUPENN dynamic texture benchmarks.
Riemannian hamiltonian methods for min-max optimization on manifolds,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LP$^{2}$DH: A Locality-Preserving Pixel-Difference Hashing Framework for Dynamic Texture Recognition
LP²DH jointly hashes spatiotemporal pixel-difference vectors with locality preservation and Stiefel-manifold optimization to produce compact binary features that achieve state-of-the-art accuracy on UCLA, DynTex++, and YUPENN dynamic texture benchmarks.