Seeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understanding

Documenti analoghi

• Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions
  di: Chang, Jinyi, et al.
  Pubblicazione: (2025)
• Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models
  di: Tong, Yujun, et al.
  Pubblicazione: (2026)
• Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion
  di: Yang, Yuqi, et al.
  Pubblicazione: (2026)
• Fine-Grained Knowledge Structuring and Retrieval for Visual Question Answering
  di: Zhang, Zhengxuan, et al.
  Pubblicazione: (2025)
• Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection
  di: Qin, Haotian, et al.
  Pubblicazione: (2025)