2 code implementations • 10 Jun 2019 • Kaibing Chen, Cheng Cui, Yuning Du, Xianglong Meng, Hui Ren
We present a retrieval based system for landmark retrieval and recognition challenge. There are five parts in retrieval competition system, including feature extraction and matching to get candidates queue; database augmentation and query extension searching; reranking from recognition results and local feature matching.
no code implementations • 12 Jun 2017 • Xinggang Wang, Kaibing Chen, Zilong Huang, Cong Yao, Wenyu Liu
The deep ConvNets based object detectors mainly focus on regressing the coordinates of bounding box, e. g., Faster-R-CNN, YOLO and SSD.