JSJingyue Shi

Jingyue Shi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jingyue Shi has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • V2V Cooperative Perception With Adaptive Communication Loss for Autonomous Driving

    by Jingyue Shi, Junhui Zhao, Li Zhuo, Xiaoming Wang, Xiaohuang Zhan, Haitao Liu

    Bird’s eye view (BEV) perception provides autonomous vehicles with a unified space closer to the actual physical world by projecting sensor data onto a unified two-dimensional plane. However, occlusion can impede the perceptual range and ability of single-vehicle in complex traffic scenarios. Moreover, most collaborative perception methods assume ideal vehicle-to-vehicle (V2V) communication, ignoring feature loss during sharing. To alleviate these problems, we propose a multi-vehicle collaborative BEV perception network with adaptive communication loss, called AccBEV, based on conditional variational inference. Specifically, the AccBEV backbone is a transformer-based variable flow transformation network designed to reduce environmental characteristic loss due to occlusion in single-vehicle perception. Additionally, an adaptive lossy channel module is designed to repair feature loss caused by varying signal-to-noise ratio (SNR) communication. The performance of AccBEV is evaluated on the OPV2V and NuScenes datasets. The results demonstrate that AccBEV has state-of-the-art performance in both single-and multi-vehicle collaborative perception, which demonstrates AccBEV’s superiority in real-world traffic scenarios and different communication states.


  • Lane Detection by Variational Auto-Encoder With Normalizing Flow for Autonomous Driving

    by Jingyue Shi, Junhui Zhao, Dongming Wang, Hong Tang

    Mainstream lane detection methods often lack flexibility, accuracy, and efficiency in challenging scenarios, especially with occlusion and extreme lighting. To address this, we reframe lane detection as a variational inference problem. Specifically, we propose a Variational Lane Detection Network (VLD-Net) using a Conditional Variational Auto-Encoder (CVAE) as the generative network to produce multiple lane maps as candidates, supervised by the ground-truth lane map. To build a more complex, expressive probability distribution, we incorporate normalizing flows into lane map generation, enhancing realism. Additionally, we develop a Lane-Attention Fusion (LAF) module using attention mechanisms to adaptively fuse generated candidate lane maps. LAF also includes a lane local feature aggregator to enhance local lane keypoint correlation. Experimental results on TuSimple and CULane datasets show our method outperforms previous approaches in challenging scenarios.


  • Gaze Estimation by Attention-Induced Hierarchical Variational Auto-Encoder

    by Guanhe Huang, Jingyue Shi, Jun Xu, Jing Li, Shengyong Chen, Yingjun Du, Xiantong Zhen, Honghai Liu

    Appearance-based gaze estimation has been widely studied recently with promising performance. The majority of appearance-based gaze estimation methods are developed under the deterministic frameworks. However, the deterministic gaze estimation methods suffer from large performance drop upon challenging eye images in low-resolution, darkness, partial occlusions, etc. To alleviate this problem, in this article, we alternatively reformulate the appearance-based gaze estimation problem under a generative framework. Specifically, we propose a variational inference model, that is, variational gaze estimation network (VGE-Net), to generate multiple gaze maps as complimentary candidates simultaneously supervised by the ground-truth gaze map. To achieve robust estimation, we adaptively fuse the gaze directions predicted on these candidate gaze maps by a regression network through a simple attention mechanism. Experiments on three benchmarks, that is, MPIIGaze, EYEDIAP, and Columbia, demonstrate that our VGE-Net outperforms state-of-the-art gaze estimation methods, especially on challenging cases. Comprehensive ablation studies also validate the effectiveness of our contributions. The code will be publicly released.