id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
fcis-31256	Qiu, Dechuan; Shan, Yongfu; Wang, Yingchao; Qin, Lihao; Li, Na	Lightweight Recognition Method for Korla Pear Based on NanoDet-Plus	2025	4	.pdf	application/pdf	2580	134	38	Specifically, mAP@0.5 assesses average precision based on predictions overlapping at least 50% with ground-truth bounding boxes, providing a baseline for model accuracy. Therefore, this study chooses MobileNetV3-Large as the core architecture because of its better balance between computational efficiency and detection accuracy, as shown in Fig.	cache/fcis-31256.pdf	txt/fcis-31256.txt