Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid

Documenti analoghi

• Bridging the Gap Between End-to-End and Two-Step Text Spotting
  di: Huang, Mingxin, et al.
  Pubblicazione: (2024)
• Progressive Evolution from Single-Point to Polygon for Scene Text
  di: Deng, Linger, et al.
  Pubblicazione: (2023)
• VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization
  di: Liu, Yuliang, et al.
  Pubblicazione: (2024)
• SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting
  di: Huang, Mingxin, et al.
  Pubblicazione: (2024)
• ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining
  di: Peng, Dezhi, et al.
  Pubblicazione: (2023)