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 35 Citations 6,523 103 World Ranking 6010 National Ranking 2922

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Artificial neural network

His primary areas of investigation include Artificial intelligence, Machine learning, Language model, Adversarial system and Natural language processing. His research ties Pattern recognition and Artificial intelligence together. In the field of Machine learning, his study on Leverage overlaps with subjects such as Upper and lower bounds.

His study looks at the intersection of Language model and topics like Commonsense reasoning with Embedding, Matching and Representation. His Adversarial system study also includes fields such as

  • Feature together with Discriminative model and Variety,
  • Generative grammar which intersects with area such as Image generation, Boosting, Similitude and Natural language. As part of one scientific family, Zhe Gan deals mainly with the area of Natural language processing, narrowing it down to issues related to the Image, and often Text corpus.

His most cited work include:

  • AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks (567 citations)
  • Semantic Compositional Networks for Visual Captioning (250 citations)
  • Variational autoencoder for deep learning of images, labels and captions (220 citations)

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

Zhe Gan mainly focuses on Artificial intelligence, Machine learning, Natural language processing, Language model and Question answering. Zhe Gan frequently studies issues relating to Pattern recognition and Artificial intelligence. His Machine learning study deals with Generative grammar intersecting with Boosting.

His Natural language processing research includes elements of Visualization and Coreference. His Language model study combines topics in areas such as Commonsense reasoning, Inference and Transformer. Zhe Gan has included themes like Matching, Theoretical computer science and Feature learning in his Question answering study.

He most often published in these fields:

  • Artificial intelligence (73.29%)
  • Machine learning (27.33%)
  • Natural language processing (24.84%)

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

  • Artificial intelligence (73.29%)
  • Language model (22.36%)
  • Question answering (16.15%)

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

Zhe Gan spends much of his time researching Artificial intelligence, Language model, Question answering, Transformer and Natural language processing. His research investigates the link between Artificial intelligence and topics such as Machine learning that cross with problems in Robustness. While the research belongs to areas of Language model, Zhe Gan spends his time largely on the problem of Inference, intersecting his research to questions surrounding Natural language.

His research in Question answering intersects with topics in Sentence, Theoretical computer science, Feature learning and Closed captioning. His study focuses on the intersection of Transformer and fields such as Information integration with connections in the field of Deep learning and Encoding. Within one scientific family, Zhe Gan focuses on topics pertaining to Coreference under Natural language processing, and may sometimes address concerns connected to Margin and Relation.

Between 2019 and 2021, his most popular works were:

  • FreeLB: Enhanced Adversarial Training for Natural Language Understanding (74 citations)
  • UNITER: UNiversal Image-TExt Representation Learning (69 citations)
  • Discourse-Aware Neural Extractive Text Summarization (39 citations)

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

  • Artificial intelligence
  • Machine learning
  • Artificial neural network

His scientific interests lie mostly in Artificial intelligence, Language model, Question answering, Inference and Natural language processing. His Artificial intelligence study frequently links to other fields, such as Machine learning. In his research on the topic of Question answering, Benchmark is strongly related with Feature learning.

His work deals with themes such as Generative grammar, Task analysis and Theoretical computer science, which intersect with Inference. His studies examine the connections between Natural language processing and genetics, as well as such issues in Coreference, with regards to Relation. His work in Commonsense reasoning covers topics such as Embedding which are related to areas like Adversarial system.

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

AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

Tao Xu;Pengchuan Zhang;Qiuyuan Huang;Han Zhang.
computer vision and pattern recognition (2018)

583 Citations

Patient Knowledge Distillation for BERT Model Compression

Siqi Sun;Yu Cheng;Zhe Gan;Jingjing Liu.
empirical methods in natural language processing (2019)

299 Citations

UNITER: UNiversal Image-TExt Representation Learning

Yen-Chun Chen;Linjie Li;Licheng Yu;Ahmed El Kholy.
european conference on computer vision (2020)

284 Citations

Adversarial feature matching for text generation

Yizhe Zhang;Zhe Gan;Kai Fan;Zhi Chen.
international conference on machine learning (2017)

245 Citations

Semantic Compositional Networks for Visual Captioning

Zhe Gan;Chuang Gan;Xiaodong He;Yunchen Pu.
computer vision and pattern recognition (2017)

230 Citations

StyleNet: Generating Attractive Visual Captions with Styles

Chuang Gan;Zhe Gan;Xiaodong He;Jianfeng Gao.
computer vision and pattern recognition (2017)

202 Citations

UNITER: Learning UNiversal Image-TExt Representations

Yen-Chun Chen;Linjie Li;Licheng Yu;Ahmed El Kholy.
(2019)

196 Citations

Variational autoencoder for deep learning of images, labels and captions

Yunchen Pu;Zhe Gan;Ricardo Henao;Xin Yuan.
neural information processing systems (2016)

167 Citations

Relation-Aware Graph Attention Network for Visual Question Answering

Linjie Li;Zhe Gan;Yu Cheng;Jingjing Liu.
international conference on computer vision (2019)

137 Citations

Learning Deep Sigmoid Belief Networks with Data Augmentation

Zhe Gan;Ricardo Henao;David E. Carlson;Lawrence Carin.
international conference on artificial intelligence and statistics (2015)

123 Citations

Best Scientists Citing Zhe Gan

Lawrence Carin

Lawrence Carin

King Abdullah University of Science and Technology

Publications: 78

Jianfeng Gao

Jianfeng Gao

Microsoft (United States)

Publications: 50

Chunyuan Li

Chunyuan Li

Microsoft (United States)

Publications: 35

William Yang Wang

William Yang Wang

University of California, Santa Barbara

Publications: 31

Bo Chen

Bo Chen

Xidian University

Publications: 26

Xiaodan Liang

Xiaodan Liang

Sun Yat-sen University

Publications: 26

Qun Liu

Qun Liu

Huawei Technologies (China)

Publications: 24

Devi Parikh

Devi Parikh

Facebook (United States)

Publications: 22

Xu Sun

Xu Sun

University of Nottingham Ningbo China

Publications: 22

Mohit Bansal

Mohit Bansal

University of North Carolina at Chapel Hill

Publications: 22

Yi Yang

Yi Yang

Zhejiang University

Publications: 21

Wei Liu

Wei Liu

Tencent (China)

Publications: 21

Furu Wei

Furu Wei

Microsoft (United States)

Publications: 20

Lei Zhang

Lei Zhang

International Digital Economy Academy

Publications: 20

Michel Galley

Michel Galley

Microsoft (United States)

Publications: 20

Nan Duan

Nan Duan

Microsoft (United States)

Publications: 19

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.