Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion

Documenti analoghi

• Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues
  di: Vu, Tuan-Anh, et al.
  Pubblicazione: (2025)
• Self-supervised Video Object Segmentation with Distillation Learning of Deformable Attention
  di: Truong, Quang-Trung, et al.
  Pubblicazione: (2024)
• Color Alignment in Diffusion
  di: Shum, Ka Chun, et al.
  Pubblicazione: (2025)
• Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding
  di: Nguyen-Truong, Hai, et al.
  Pubblicazione: (2024)
• The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
  di: Nguyen, Thanh-Danh, et al.
  Pubblicazione: (2023)