MoTE: Mixture of Task Experts for Multi-Task Video Understanding Paper • 2608.24763 • Published 12 days ago • 2
MoTE: Mixture of Task Experts for Multi-Task Video Understanding Paper • 2608.24763 • Published 12 days ago • 2
HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion Paper • 2608.20093 • Published 17 days ago
google/siglip2-so400m-patch14-384 Zero-Shot Image Classification • 1B • Updated Feb 21, 2025 • 881k • 101