GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based Solutions

Documenti analoghi

• New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration
  di: Yang, Xuzheng, et al.
  Pubblicazione: (2025)
• FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension
  di: Liu, Junzhuo, et al.
  Pubblicazione: (2024)
• Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks
  di: Dong, Qihua, et al.
  Pubblicazione: (2026)
• Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning
  di: Li, Meixuan, et al.
  Pubblicazione: (2024)
• OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling
  di: Xiao, Linhui, et al.
  Pubblicazione: (2024)