B
Bailin Yang
Researcher at Zhejiang Gongshang University
Publications - 48
Citations - 852
Bailin Yang is an academic researcher from Zhejiang Gongshang University. The author has contributed to research in topics: Computer science & Rendering (computer graphics). The author has an hindex of 8, co-authored 38 publications receiving 425 citations.
Papers
More filters
Journal ArticleDOI
LSTM-based traffic flow prediction with missing data
TL;DR: A novel approach that is based on Long Short-Term Memory (LSTM) is proposed that obtains higher accuracy in traffic flow prediction compared with other approaches.
Journal ArticleDOI
Traffic flow prediction using LSTM with feature enhancement
TL;DR: This work proposes an improved approach that connects the high-impact value of remarkably long sequence time steps to the current time step, and these high- impact traffic flow values are captured using the attention mechanism.
Proceedings ArticleDOI
Deep Dual Consecutive Network for Human Pose Estimation
TL;DR: In this article, a multi-frame human pose estimation framework was proposed, which leverages abundant temporal cues between video frames to facilitate keypoint detection and achieved state-of-the-art performance on the PoseTrack2017 and PoseTrack2018 benchmark datasets.
Journal ArticleDOI
Joint temporal context exploitation and active learning for video segmentation
TL;DR: This paper develops an approach to video segmentation that relies on temporal features by modeling the uncertainty of the distribution of different feature mask forms by using those uncertainty values for unsupervised active learning.
Journal ArticleDOI
No-reference synthetic image quality assessment with convolutional neural network and local image saliency
TL;DR: This paper proposes a novel no-reference image quality assessment method for synthetic images based on convolutional neural networks, introducing local image saliency as prediction weights and demonstrates that the proposed metric outperforms traditional 2D image quality metrics and state-of-the-art DIBR-related metrics.