DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding

Documenti analoghi

• Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models
  di: He, Hulingxiao, et al.
  Pubblicazione: (2025)
• CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspective
  di: Yang, Zhiwen, et al.
  Pubblicazione: (2025)
• FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models
  di: Xu, Jinglin, et al.
  Pubblicazione: (2024)
• Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
  di: He, Hulingxiao, et al.
  Pubblicazione: (2026)
• FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment
  di: Xu, Jinglin, et al.
  Pubblicazione: (2024)