3 papers
cs.CV2026
SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition
Soroush Oraki, Feng Ding, Jie Liang
Zero-shot skeleton-based action recognition (ZSAR) aims to recognize action classes without any training skeletons from those classes, relying instead on auxiliary semantics from t…
cs.CV2025
LSTC-MDA: A Unified Framework for Long-Short Term Temporal Convolution and Mixed Data Augmentation in Skeleton-Based Action Recognition
Feng Ding, Haisheng Fu, Soroush Oraki +1
Skeleton-based action recognition faces two longstanding challenges: the scarcity of labeled training samples and difficulty modeling short- and long-range temporal dependencies. T…
cs.CV2024
LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition
Soroush Oraki, Harry Zhuang, Jie Liang
The complexity of state-of-the-art Transformer-based models for skeleton-based action recognition poses significant challenges in terms of computational efficiency and resource uti…