no code implementations • CVPR 2020 • Yanru Huang, Feiyu Zhu, Zheni Zeng, Xi Qiu, Yuan Shen, Jia-Nan Wu
We present a novel self quality evaluation metric SQE for parameters optimization in the challenging yet critical multi-object tracking task.
no code implementations • 27 Dec 2017 • Zhimeng Zhang, Jia-Nan Wu, Xuan Zhang, Chi Zhang
Although many methods perform well in single camera tracking, multi-camera tracking remains a challenging problem with less attention.
no code implementations • 4 Dec 2017 • Qizheng He, Jia-Nan Wu, Gang Yu, Chi Zhang
Another contribution is that we show with a deep learning based appearance model, it is easy to associate detections of the same object efficiently and also with high accuracy.
no code implementations • 31 Dec 2015 • Shuchang Zhou, Jia-Nan Wu, Yuxin Wu, Xinyu Zhou
In this paper, we propose and study a technique to reduce the number of parameters and computation time in convolutional neural networks.
no code implementations • 30 Nov 2015 • Cong Yao, Jia-Nan Wu, Xinyu Zhou, Chi Zhang, Shuchang Zhou, Zhimin Cao, Qi Yin
Different from focused texts present in natural images, which are captured with user's intention and intervention, incidental texts usually exhibit much more diversity, variability and complexity, thus posing significant difficulties and challenges for scene text detection and recognition algorithms.
no code implementations • 21 Jul 2015 • Shuchang Zhou, Jia-Nan Wu
In this paper we propose and study a technique to reduce the number of parameters and computation time in fully-connected layers of neural networks using Kronecker product, at a mild cost of the prediction quality.