Indexed by:
Abstract:
针对可变形部件模型(deformable parts model,DPM)同等对待各部件,无法体现不同部件对识别过程的贡献度差异的不足,提出一种权重系数可变形模型(weighted coefficient deformable parts model,WCDPM),对DPM中的各部件赋予权重,强调区分度较高的部件在识别过程的作用,弱化区分度低的部件对识别的影响,提高细粒度识别精度.同时给出了模型的训练过程和权重系数的学习方法.在Airplan OID和Oxford-IIIT Pet两个数据集上进行实验,验证了该方法的有效性.
Keyword:
Reprint Author's Address:
Email:
Source :
北京工业大学学报
Year: 2017
Issue: 07
Volume: 43
Page: 1023-1030
Cited Count:
WoS CC Cited Count: 0
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 1
Affiliated Colleges: