Ye Yan
33 Papers
1 Citations
Ye Yan is an academic researcher. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 1, co-authored 12 publications.
Chat about Author
Papers
Real-time Gaze Tracking with Head-eye Coordination for Head-mounted Displays
Lingling Chen,Yingxi Li,Xi-Xiang Bai,Xiaodong Wang,Yongqiang Hu,Mingwu Song,Liang Xie,Ye Yan,Erwei Yin +8 more
- 01 Oct 2022
TL;DR: In this article , a lightweight multi-modal network (HE-Tracker) is proposed to regress gaze positions by fusing head-movement features with eye features, which achieves comparable accuracy (3.655° in all subjects) and $27 \times$ speedup (48 fps in the specialized AR HMD) compared to the state-of-the-art gaze tracking algorithm.
7
Multimodal Vigilance Estimation with Modality-Pairwise Contrastive Loss.
Meihong Zhang,Zhiguo Luo,Liang Xie,Tiejun Liu,Ye Yan,Dezhong Yao,Shaokai Zhao,Erwei Yin +7 more
- 31 Oct 2023
TL;DR: It is argued that the proposed cross-modality alignment method in the inter-subject case could offer the possibility of reducing the high-cost of data annotation, and further analysis may provide an idea for the application of multimodal vigilance regression.
6
Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigation
Yibo Cui,Liang Xie,Yakun Zhang,Meishan Zhang,Ye Yan,Erwei Yin +5 more
TL;DR: A novel Grounded Entity-Landmark Adaptive (GELA) pre-training paradigm for VLN tasks achieves state-of-the-art results on both tasks, demonstrating its effectiveness and generalizability.
6
Motion Distortion Elimination for LiDAR-Inertial Odometry Under Rapid Motion Conditions
TL;DR: A novel algorithm based on multioutput Gaussian process regression (MOGPR) is proposed in this work to eliminate motion distortion in LiDAR point cloud and the localization accuracy of the LIO algorithm integrating the proposed method is improved by approximately 30%.
5
Online Hand Gesture Detection and Recognition for UAV Motion Planning
TL;DR: In this article , a novel framework based on hand gesture interaction is proposed, to support efficient and robust UAV flight, which includes Gaussian Native Bayes (GNB) and Random Forest (RF) to classify hand gestures based on the Six Degrees of Freedom (6DoF) inertial measurement units (IMUs) of the data glove.