SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition

Documenti analoghi

• LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition
  di: Oraki, Soroush, et al.
  Pubblicazione: (2024)
• LSTC-MDA: A Unified Framework for Long-Short Term Temporal Convolution and Mixed Data Augmentation in Skeleton-Based Action Recognition
  di: Ding, Feng, et al.
  Pubblicazione: (2025)
• Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
  di: Wu, Wenhan, et al.
  Pubblicazione: (2025)
• SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
  di: Li, Sheng-Wei, et al.
  Pubblicazione: (2024)
• Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition
  di: Do, Jeonghyeok, et al.
  Pubblicazione: (2024)