X
Xiangbo Lin
Researcher at Dalian University of Technology
Publications - 27
Citations - 211
Xiangbo Lin is an academic researcher from Dalian University of Technology. The author has contributed to research in topics: Computer science & Pose. The author has an hindex of 5, co-authored 19 publications receiving 145 citations.
Papers
More filters
Proceedings ArticleDOI
CrossInfoNet: Multi-Task Information Sharing Based Hand Pose Estimation
TL;DR: The proposed CrossInfoNet decomposes hand pose estimation task into palm pose estimation sub-task and finger pose estimationsub-task, and adopts two-branch crossconnection structure to share the beneficial complementary information between the sub-tasks.
Book ChapterDOI
HBE: Hand Branch Ensemble Network for Real-time 3D Hand Pose Estimation
TL;DR: The experimental results demonstrate that the novel three-branch Convolutional Neural Networks named Hand Branch Ensemble network achieves comparable or better performance to state-of-the-art methods with less training data, shorter training time and faster frame rate.
Proceedings ArticleDOI
A novel framework for low-light colour image enhancement and denoising
Wenshuai Yin,Xiangbo Lin,Yi Sun +2 more
TL;DR: Experimental results indicate that the algorithm is effective for low illumination compensation, colour restoration and noise reduction, and a saturation enhancement function was proposed to ensure more natural colours.
Book ChapterDOI
An Edge Sensing Fuzzy Local Information C-Means Clustering Algorithm for Image Segmentation
TL;DR: A variation of fuzzy local information c-means (FLICM) algorithm for image segmentation is presented by introducing a novel tradeoff factor and an effective kernel metric, providing higher segmenting accuracy than other competitive algorithms.
Journal ArticleDOI
A multi-branch hand pose estimation network with joint-wise feature extraction and fusion
TL;DR: The proposed network is a unified structure and function model that is more appropriate for hand pose estimation that can directly perform training and predicting from end-to-end and achieves performance comparable to state-of-the-art methods.