Skip to content
conftrace_

region captioning

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

mask tokenizer (1) residual vector quantizer (1) bounding boxes (1) mask (1) pix2emb (1) zero-shot captioning (1) region understanding (1) referring segmentation (1) large language model (1) dense captioning (1)

Papers

One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework CVPR 2026 SAMTok: Representing Any Mask with Two Words CVPR 2026 NExT-Chat: An LMM for Chat, Detection and Segmentation ICML 2024 RegionGPT: Towards Region Understanding Vision Language Model CVPR 2024