scispace - formally typeset
Search or ask a question
Author

Hong Liu

Bio: Hong Liu is an academic researcher from Peking University. The author has contributed to research in topics: Computer science & Artificial intelligence. 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
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.

668 citations

Book ChapterDOI
Xia Li1, Jianlong Wu1, Zhouchen Lin1, Hong Liu1, Hongbin Zha1 
08 Sep 2018
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.
Abstract: Rain streaks can severely degrade the visibility, which causes many current computer vision algorithms fail to work. So it is necessary to remove the rain from images. We propose a novel deep network architecture based on deep convolutional and recurrent neural networks for single image deraining. As contextual information is very important for rain removal, we first adopt the dilated convolutional neural network to acquire large receptive field. To better fit the rain removal task, we also modify the network. In heavy rain, rain streaks have various directions and shapes, which can be regarded as the accumulation of multiple rain streak layers. We assign different alpha-values to various rain streak layers according to the intensity and transparency by incorporating the squeeze-and-excitation block. Since rain streak layers overlap with each other, it is not easy to remove the rain in one stage. So we further decompose the rain removal into multiple stages. Recurrent neural network is incorporated to preserve the useful information in previous stages and benefit the rain removal in later stages. We conduct extensive experiments on both synthetic and real-world datasets. Our proposed method outperforms the state-of-the-art approaches under all evaluation metrics. Codes and supplementary material are available at our project webpage: https://xialipku.github.io/RESCAN.

539 citations

Journal ArticleDOI
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.

343 citations

Proceedings ArticleDOI
Xia Li1, Zhisheng Zhong1, Jianlong Wu1, Yibo Yang1, Zhouchen Lin1, Hong Liu1 
01 Oct 2019
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.
Abstract: Self-attention mechanism has been widely used for various tasks. It is designed to compute the representation of each position by a weighted sum of the features at all positions. Thus, it can capture long-range relations for computer vision tasks. However, it is computationally consuming. Since the attention maps are computed w.r.t all other positions. In this paper, we formulate 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. By a weighted summation upon these bases, the resulting representation is low-rank and deprecates noisy information from the input. The proposed Expectation-Maximization Attention (EMA) module is robust to the variance of input and is also friendly in memory and computation. Moreover, we set up the bases maintenance and normalization methods to stabilize its training procedure. We conduct extensive experiments on popular semantic segmentation benchmarks including PASCAL VOC, PASCAL Context, and COCO Stuff, on which we set new records.

276 citations

Proceedings ArticleDOI
18 Jun 2018
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.
Abstract: Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks. Following this line of research, in this paper we introduce a novel approach for monocular depth estimation. Similarly to previous works, our method employs a continuous CRF to fuse multi-scale information derived from different layers of a front-end Convolutional Neural Network (CNN). Differently from past works, our approach benefits from a structured attention model which automatically regulates the amount of information transferred between corresponding features at different scales. Importantly, the proposed attention model is seamlessly integrated into the CRF, allowing end-to-end training of the entire architecture. Our extensive experimental evaluation demonstrates the effectiveness of the proposed method which is competitive with previous methods on the KITTI benchmark and outperforms the state of the art on the NYU Depth V2 dataset.

254 citations


Cited by
More filters