Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation

Documenti analoghi

• Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorders
  di: Duan, Shuchao, et al.
  Pubblicazione: (2025)
• Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms
  di: Liu, Jingjing, et al.
  Pubblicazione: (2025)
• GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain
  di: Adeli, Vida, et al.
  Pubblicazione: (2025)
• Asymmetric Co-Training for Source-Free Few-Shot Domain Adaptation
  di: Li, Gengxu, et al.
  Pubblicazione: (2025)
• Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training
  di: Reddy, Arun, et al.
  Pubblicazione: (2023)