29 citations
3 papers
cs.CV2020★ 29 cited
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
Hongkai Zhang, Hong Chang, Bingpeng Ma +2
Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we f…
cs.CV2019★ 9 cited
Grid-GCN for Fast and Scalable Point Cloud Learning
Qiangeng Xu, Xudong Sun, Cho-Ying Wu +2
Due to the sparsity and irregularity of the point cloud data, methods that directly consume points have become popular. Among all point-based models, graph convolutional networks (…
cs.CV2017★ 4 cited
Multi-shot Pedestrian Re-identification via Sequential Decision Making
Jianfu Zhang, Naiyan Wang, Liqing Zhang
Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing…