An LLM generates scene-specific object names that are fed to YOLO-World, enabling label-free open-world detection evaluated with new CAAP and SNAP metrics.
Mdetr- modulated detection for end-to-end multi-modal understand- ing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
LLM-Guided Agentic Object Detection for Open-World Understanding
An LLM generates scene-specific object names that are fed to YOLO-World, enabling label-free open-world detection evaluated with new CAAP and SNAP metrics.