H
Hong Liu
Researcher at Peking University
Publications - 121
Citations - 4997
Hong Liu is an academic researcher from Peking University. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 27, co-authored 102 publications receiving 3060 citations. Previous affiliations of Hong Liu include Chongqing University of Technology & Central South University.
Papers
More filters
Journal ArticleDOI
An Adaptive Method Based on Multiscale Dilated Convolutional Network for Binaural Speech Source Localization
TL;DR: Experimental results show the proposed method can adaptively locate speech sources in simulated noisy and reverberant environments.
Journal ArticleDOI
Noise-free representation based classification and face recognition experiments
TL;DR: This paper proposes a new representation based classification method that can effectively and simultaneously reduce noise in the test and training samples and then exploits them to determine the label of the test sample.
Proceedings ArticleDOI
Hierarchical RRT for humanoid robot footstep planning with multiple constraints in complex environments
Hong Liu,Qing Sun,Tianwei Zhang +2 more
TL;DR: A novel approach based on hierarchical RRT is used to plan the footstep for humanoid robots according to three basic constraints: a transition model based gait generator, an inverted pendulum based balance controller and a collision detection based path planner.
Proceedings ArticleDOI
Affine correspondence based head pose estimation for a sequence of images by using a 3D model
TL;DR: Experimental results show that the proposed method can accurately recover head poses in a wide range of head motion and be improved by applying a modified KLT technique to speed up the convergence during the face feature tracking process.
Proceedings ArticleDOI
Automatic seal image retrieval method by using shape features of Chinese characters
Hong Liu,Ye Lu,Qi Wu,Hongbin Zha +3 more
TL;DR: A new retrieval method based on Chinese characters' shape features based on position code to decide which two seal images have the most similarity is introduced in this paper.