Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
A Simple Aerial Detection Baseline of Multimodal Language Models
Qingyun Li, Yushi Chen, Xinya Shu +4
The multimodal language models (MLMs) based on generative pre-trained Transformer are considered powerful candidates for unifying various domains and tasks. MLMs developed for remo…
cs.CV2024
ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
Ying Zeng, Yushi Chen, Xue Yang +2
Existing oriented object detection methods commonly use metric AP to measure the performance of the model. We argue that AP is inherently unsuitable for oriented obje…