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
Enhanced skeleton visualization for view invariant human action recognition
Mengyuan Liu,Hong Liu,Chen Chen +2 more
TL;DR: Enhanced skeleton visualization method encodes spatio-temporal skeletons as visual and motion enhanced color images in a compact yet distinctive manner and consistently achieves the highest accuracies on four datasets, including the largest and most challenging NTU RGB+D dataset for skeleton-based action recognition.
Book ChapterDOI
Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining
TL;DR: A novel deep network architecture based on deep convolutional and recurrent neural networks for single image deraining based on contextual information is proposed and outperforms the state-of-the-art approaches under all evaluation metrics.
Journal ArticleDOI
Attention-guided CNN for image denoising.
TL;DR: An attention-guided denoising convolutional neural network (ADNet), mainly including a sparse block (SB), a feature enhancement block (FEB), an attention block (AB) and a reconstruction block (RB) for image Denoising.
Proceedings ArticleDOI
Expectation-Maximization Attention Networks for Semantic Segmentation
TL;DR: This paper forms the attention mechanism into an expectation-maximization manner and iteratively estimate a much more compact set of bases upon which the attention maps are computed, which is robust to the variance of input and is also friendly in memory and computation.
Proceedings ArticleDOI
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
TL;DR: In this article, a continuous CRF is employed to fuse multi-scale information derived from different layers of a front-end Convolutional Neural Network (CNN) for monocular depth estimation.