tao-generate-referring-expressions

【数据与研究】Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the user wants to generate referring-expression annotations from images with KITTI labels, build region descriptions, …

独立 GitHub 快照 · 自动分类 · 以原作者文档为准