Zhangping He — accepted AI-conference papers

2021

Learning a Proposal Classifier for Multiple Object Tracking

Peng Dai, Renliang Weng, Wongun Choi, Changshui Zhang, Zhangping He, Wei Ding

CVPR 2021poster

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. However, it is not trivial to solve the data-association problem in an end-to-end fashion. In this paper, we propose a novel proposal-based learnable framework, which mod…

Cited by 140 PDF ↗code ↗Scholar ↗

2018

Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss

Zhangping He, Zhendong Zhang, Cheolkon Jung

ICASSP 2018accepted

In this paper, we propose deep feature embedding learning for person re-identification (re-id) using lifted structured loss. Although triplet loss has been commonly used in deep neural networks for person re-id, the triplet loss-based framework is not effective in fully using the batch information.…

Cited by 0 Source ↗Scholar ↗