Open-Vocabulary Scene Text Recognition via Pseudo-Image Labeling and Margin Loss

Documenti analoghi

• CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection
  di: Choi, Hojun, et al.
  Pubblicazione: (2025)
• Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labeling
  di: Furuya, Takahiko
  Pubblicazione: (2026)
• Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning
  di: Li, Hongxi, et al.
  Pubblicazione: (2026)
• DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
  di: Liu, Haijing, et al.
  Pubblicazione: (2025)
• GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts
  di: Milacski, Zoltán Á., et al.
  Pubblicazione: (2024)