The paper defines UAV reasoning segmentation, releases DRSeg—10,000 aerial images with reasoning QA and masks—and shows its PixDLM baseline beats prior reasoning-segmentation models under fine-tuning.
Title resolution pending
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · external index
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation
The paper defines UAV reasoning segmentation, releases DRSeg—10,000 aerial images with reasoning QA and masks—and shows its PixDLM baseline beats prior reasoning-segmentation models under fine-tuning.