SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition

Documenti analoghi

• A Generically Contrastive Spatiotemporal Representation Enhancement for 3D Skeleton Action Recognition
  di: Zhang, Shaojie, et al.
  Pubblicazione: (2023)
• MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation
  di: Wei, Wei, et al.
  Pubblicazione: (2025)
• Kinematics Modeling Network for Video-based Human Pose Estimation
  di: Dang, Yonghao, et al.
  Pubblicazione: (2022)
• ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality
  di: Xu, Guoliang, et al.
  Pubblicazione: (2024)
• A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognition
  di: Yin, Ruoqi, et al.
  Pubblicazione: (2023)