WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting

Documenti analoghi

• Recognition-Synergistic Scene Text Editing
  di: Fang, Zhengyao, et al.
  Pubblicazione: (2025)
• Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
  di: Fang, Zhengyao, et al.
  Pubblicazione: (2026)
• Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation
  di: Su, Jiapeng, et al.
  Pubblicazione: (2024)
• CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Retrieval
  di: Zhao, Xinpeng, et al.
  Pubblicazione: (2024)
• Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration
  di: Feng, Xin, et al.
  Pubblicazione: (2022)