One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

Documenti analoghi

• CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones
  di: Pacini, Giacomo, et al.
  Pubblicazione: (2025)
• Is CLIP the main roadblock for fine-grained open-world perception?
  di: Bianchi, Lorenzo, et al.
  Pubblicazione: (2024)
• Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
  di: Pacini, Giacomo, et al.
  Pubblicazione: (2026)
• The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
  di: Bianchi, Lorenzo, et al.
  Pubblicazione: (2023)
• OmniCaptioner: One Captioner to Rule Them All
  di: Lu, Yiting, et al.
  Pubblicazione: (2025)