D-Index & Metrics Best Publications

D-Index & Metrics

Discipline name D-index D-index (Discipline H-index) only includes papers and citation values for an examined discipline in contrast to General H-index which accounts for publications across all disciplines. Citations Publications World Ranking National Ranking
Computer Science D-index 39 Citations 6,832 189 World Ranking 4795 National Ranking 455

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Statistics
  • Computer vision

His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Computer vision, Deep learning and Image restoration. His Artificial intelligence study typically links adjacent topics like Machine learning. His research investigates the link between Pattern recognition and topics such as Image processing that cross with problems in Artificial neural network.

His Computer vision study incorporates themes from Visualization and Distortion. His Deep learning research is multidisciplinary, incorporating perspectives in Modal and Benchmark. His study in Image restoration is interdisciplinary in nature, drawing from both Convolutional neural network, Feature detection and Filter.

His most cited work include:

  • An end-to-end spatio-temporal attention model for human action recognition from skeleton data (404 citations)
  • Deep Joint Rain Detection and Removal from a Single Image (314 citations)
  • Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (201 citations)

What are the main themes of his work throughout his whole career to date?

Jiaying Liu mainly investigates Artificial intelligence, Computer vision, Pattern recognition, Algorithm and Image. Jiaying Liu regularly links together related areas like Machine learning in his Artificial intelligence studies. His work on Face, Motion estimation, Color constancy and Noise reduction as part of general Computer vision research is frequently linked to Process, bridging the gap between disciplines.

His study looks at the intersection of Pattern recognition and topics like Image restoration with Image texture. His Algorithm research incorporates themes from Real-time computing, Coding, Harmonic Vector Excitation Coding and Distortion. His study looks at the relationship between Pixel and topics such as Image scaling, which overlap with Stairstep interpolation.

He most often published in these fields:

  • Artificial intelligence (76.21%)
  • Computer vision (35.32%)
  • Pattern recognition (30.48%)

What were the highlights of his more recent work (between 2019-2021)?

  • Artificial intelligence (76.21%)
  • Computer vision (35.32%)
  • Machine learning (8.55%)

In recent papers he was focusing on the following fields of study:

His main research concerns Artificial intelligence, Computer vision, Machine learning, Pattern recognition and Coding. His Machine vision, Visualization, Benchmark, Face and Noise study are his primary interests in Artificial intelligence. His work deals with themes such as Interpretability and Detector, which intersect with Computer vision.

His study on Overfitting, Feature vector, Feature and Feature learning is often connected to Jigsaw as part of broader study in Machine learning. His research investigates the connection between Pattern recognition and topics such as Adaptation that intersect with issues in Joint. Frame is closely connected to Feature extraction in his research, which is encompassed under the umbrella topic of Coding.

Between 2019 and 2021, his most popular works were:

  • Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (80 citations)
  • Single Image Deraining: From Model-Based to Data-Driven and Beyond. (32 citations)
  • LR3M: Robust Low-Light Enhancement via Low-Rank Regularized Retinex Model (18 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Computer vision
  • Statistics

His primary areas of study are Artificial intelligence, Computer vision, Visualization, Machine learning and Pattern recognition. Artificial intelligence connects with themes related to Coding in his study. His work on Motion estimation and Feature extraction is typically connected to Streak, Popularity and Training as part of general Computer vision study, connecting several disciplines of science.

His studies deal with areas such as Color constancy, Coherence, Histogram, Noise reduction and Robustness as well as Visualization. When carried out as part of a general Machine learning research project, his work on Regularization, Feature learning, Feature vector and Overfitting is frequently linked to work in Jigsaw, therefore connecting diverse disciplines of study. The Coarse to fine research Jiaying Liu does as part of his general Pattern recognition study is frequently linked to other disciplines of science, such as Redundancy, therefore creating a link between diverse domains of science.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

An end-to-end spatio-temporal attention model for human action recognition from skeleton data

Sijie Song;Cuiling Lan;Junliang Xing;Wenjun Zeng.
national conference on artificial intelligence (2017)

511 Citations

Deep Joint Rain Detection and Removal from a Single Image

Wenhan Yang;Robby T. Tan;Jiashi Feng;Jiaying Liu.
computer vision and pattern recognition (2017)

397 Citations

Attentive Generative Adversarial Network for Raindrop Removal from A Single Image

Rui Qian;Robby T. Tan;Wenhan Yang;Jiajun Su.
computer vision and pattern recognition (2018)

295 Citations

Deep Retinex Decomposition for Low-Light Enhancement

Chen Wei;Wenjing Wang;Wenhan Yang;Jiaying Liu.
british machine vision conference (2018)

266 Citations

Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model

Mading Li;Jiaying Liu;Wenhan Yang;Xiaoyan Sun.
IEEE Transactions on Image Processing (2018)

220 Citations

Demystifying Neural Style Transfer

Yanghao Li;Naiyan Wang;Jiaying Liu;Xiaodi Hou.
international joint conference on artificial intelligence (2017)

211 Citations

Revisiting Batch Normalization For Practical Domain Adaptation

Yanghao Li;Naiyan Wang;Jianping Shi;Jiaying Liu.
arXiv: Computer Vision and Pattern Recognition (2016)

174 Citations

Adaptive Batch Normalization for practical domain adaptation

Yanghao Li;Naiyan Wang;Jianping Shi;Xiaodi Hou.
Pattern Recognition (2018)

160 Citations

Online Human Action Detection Using Joint Classification-Regression Recurrent Neural Networks

Yanghao Li;Cuiling Lan;Junliang Xing;Wenjun Zeng.
european conference on computer vision (2016)

138 Citations

Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution

Wenhan Yang;Jiashi Feng;Jianchao Yang;Fang Zhao.
IEEE Transactions on Image Processing (2017)

131 Citations

Best Scientists Citing Jiaying Liu

Siwei Ma

Siwei Ma

Peking University

Publications: 41

Shiqi Wang

Shiqi Wang

City University of Hong Kong

Publications: 35

Zhangyang Wang

Zhangyang Wang

The University of Texas at Austin

Publications: 30

Wen Gao

Wen Gao

Peking University

Publications: 29

Ming-Hsuan Yang

Ming-Hsuan Yang

University of California, Merced

Publications: 28

Dacheng Tao

Dacheng Tao

University of Sydney

Publications: 23

Deyu Meng

Deyu Meng

Xi'an Jiaotong University

Publications: 23

Feng Wu

Feng Wu

University of Science and Technology of China

Publications: 21

Alex C. Kot

Alex C. Kot

Nanyang Technological University

Publications: 21

Sam Kwong

Sam Kwong

City University of Hong Kong

Publications: 21

Ling-Yu Duan

Ling-Yu Duan

Peking University

Publications: 19

Wenjun Zeng

Wenjun Zeng

Microsoft (United States)

Publications: 18

Ce Zhu

Ce Zhu

University of Electronic Science and Technology of China

Publications: 18

Nicu Sebe

Nicu Sebe

University of Trento

Publications: 18

Qi Tian

Qi Tian

Huawei Technologies (China)

Publications: 17

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking d-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us
Something went wrong. Please try again later.