Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies

Documenti analoghi

• Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition
  di: Cho, Seungyeon, et al.
  Pubblicazione: (2025)
• Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics
  di: Tse, Tze Ho Elden, et al.
  Pubblicazione: (2025)
• Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter
  di: Liu, Chao, et al.
  Pubblicazione: (2024)
• Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN
  di: Yusuf, Oluwaleke, et al.
  Pubblicazione: (2024)
• ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition
  di: Wang, Chuanchuan, et al.
  Pubblicazione: (2024)