conftrace_

region description

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

vision-language model (2) compositional image captioning (1) region-based description (1) multimodal task (1) dense captioning (1) compositional reasoning (1) fine-grained understanding (1) spatial understanding (1) multimodal large language model (1) object localization (1)

Papers

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity CVPR 2025 Spatial Preference Rewarding for MLLMs Spatial Understanding ICCV 2025 FlexCap: Describe Anything in Images in Controllable Detail NeurIPS 2024