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.
Dynamic texture classification using directional binarized random fea- tures,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.
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.
-
Breaking Global Self-Attention Bottlenecks in Transformer-based Spiking Neural Networks with Local Structure-Aware Self-Attention
LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.