FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs

Documenti analoghi

• Positional Bias in Multimodal Embedding Models: Do They Favor the Beginning, the Middle, or the End?
  di: Wu, Kebin, et al.
  Pubblicazione: (2025)
• LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts
  di: Cao, Anh-Quan, et al.
  Pubblicazione: (2024)
• Medical Image Synthesis via Fine-Grained Image-Text Alignment and Anatomy-Pathology Prompting
  di: Chen, Wenting, et al.
  Pubblicazione: (2024)
• TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation
  di: Lin, Haokun, et al.
  Pubblicazione: (2025)
• FG-CLIP: Fine-Grained Visual and Textual Alignment
  di: Xie, Chunyu, et al.
  Pubblicazione: (2025)