Jingyue Shi

Jingyue Shi

Auto-generated profile, based on publicly available information

Jingyue Shi

School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 August 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
Junhui ZhaoJunhui Zhao
Junhui Zhao
JSJingyue Shi
Jingyue Shi
ZLZhuo Li
Zhuo Li

20 September 2023 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
GHGuanhe Huang
Guanhe Huang
JSJingyue Shi
Jingyue Shi
JXJun Xu
Jun Xu
JLJing Li
Jing Li
SCShengyong Chen
Shengyong Chen
HLHonghai Honghai Liu
Honghai 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.

10 July 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
JSJingyue Shi
Jingyue Shi
Junhui ZhaoJunhui Zhao
Junhui Zhao
ZLZhuo Li
Zhuo Li
Xiaoming WangXiaoming Wang
Xiaoming Wang
XZXiaohuang Zhan
Xiaohuang Zhan
HLHaitao Liu
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.

9 October 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
JSJingyue Shi
Jingyue Shi
Junhui ZhaoJunhui Zhao
Junhui Zhao
Dongming WangDongming Wang
Dongming Wang
HTHong Tang
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.