Avatar of Truong-Binh Duong

Truong-Binh Duong

AI VIETNAM

AI researcher working on multimodal learning, vision-language models, and robust visual reasoning

  • About
  • Publications
  • Research
  • CV

#text-rich images

Content tagged with "text-rich images"

Describe Anything Model for Visual Question Answering on Text-Rich Images
2025-10-01 Yen-Linh Vu*, Dinh-Thang Duong*, Truong-Binh Duong, et al. VisionDocs Workshop at ICCV 2025
#Vision-Language Models #Text-Rich Images #Visual Question Answering #Document Intelligence

An investigation of region-level descriptions from the Describe Anything Model for visual question answering on text-rich images.

View
© 2026 Truong-Binh Duong.