no code implementations • 8 Oct 2022 • Yi Shi, Jiang Wu, Shixuan Zhao, Gangyao Gao, Tao Deng, Hongmei Yan
The first is the detection head and object distribution matching strategy, which guides the rational configuration of detection head, so as to leverage multi-scale features to effectively detect objects at vastly different scales.
no code implementations • 26 Oct 2020 • Wenbo Liu, Fei Yan, Kuan Tang, Jiyong Zhang, Tao Deng
So we combine the advantages of spatial convolution in spatial information processing and the efficiency of ERFNet in semantic segmentation, propose an end-to-end network to lane detection in a variety of complex scenes.
1 code implementation • 10 Aug 2020 • Jiyong Zhang, Tao Deng, Fei Yan, Wenbo Liu
One is used to extract the information of the most likely low-level features of lane markings.
no code implementations • 28 Jul 2019 • Xiao Yang, Daren Sun, Ruiwei Zhu, Tao Deng, Zhi Guo, Jiao Ding, Shouke Qin, Zongyao Ding, Yanfeng Zhu
Sponsored search has more than 20 years of history, and it has been proven to be a successful business model for online advertising.
1 code implementation • IEEE Transactions on Intelligent Transportation Systems 2019 • Tao Deng, Hongmei Yan, Long Qin, Thuyen Ngo, and B. S. Manjunath
Based on the multiple drivers’ attention allocation dataset, we propose a convolutional-deconvolutional neural network (CDNN) to predict the drivers’ eye fixations.
no code implementations • 13 Dec 2017 • Tao Deng, Xiao-Yang Liu, Feng Qian, Anwar Walid
The recently proposed transform-based tensor model is more appropriate for sensory data processing, as it helps exploit the geometric structures of the three-dimensional target and improve the recovery precision.