CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images

Documenti analoghi

• HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning
  di: Hossain, Md Aminur, et al.
  Pubblicazione: (2026)
• Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
  di: He, Jingyang, et al.
  Pubblicazione: (2026)
• ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning
  di: Vujinovic, Aleksandar, et al.
  Pubblicazione: (2025)
• 3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
  di: Hu, Naiwen, et al.
  Pubblicazione: (2024)
• CR-JEPA: Cross-Modal Joint-Embedding Predictive Learning for Remote Sensing Image Retrieval
  di: Hossain, Md Aminur, et al.
  Pubblicazione: (2026)