HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models

Documenti analoghi

• HarmoVid: Relightful Video Portrait Harmonization
  di: Choi, Jun Myeong, et al.
  Pubblicazione: (2026)
• Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
  di: Wu, Shihan, et al.
  Pubblicazione: (2024)
• OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance
  di: Zeng, Haoxi, et al.
  Pubblicazione: (2026)
• HarmoQ: Harmonized Post-Training Quantization for High-Fidelity Image
  di: Wang, Hongjun, et al.
  Pubblicazione: (2025)
• MoralCLIP: Contrastive Alignment of Vision-and-Language Representations with Moral Foundations Theory
  di: Condez, Ana Carolina, et al.
  Pubblicazione: (2025)