H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 45 Citations 9,085 207 World Ranking 3641 National Ranking 96

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Algorithm

His main research concerns Artificial intelligence, Hash function, Pattern recognition, Data mining and Search engine indexing. His studies deal with areas such as Machine learning, Minimax and Computer vision as well as Artificial intelligence. His Hash function research is multidisciplinary, incorporating elements of Theoretical computer science and Nearest neighbor search.

His work on Nonlinear dimensionality reduction as part of general Pattern recognition research is frequently linked to Tree kernel, thereby connecting diverse disciplines of science. His Data mining study combines topics from a wide range of disciplines, such as Mixture model, Temporal context, Social media mining and Human–computer interaction. His Search engine indexing study integrates concerns from other disciplines, such as Hamming space, Multimedia search, Video tracking and Time complexity.

His most cited work include:

  • l 2,1 -norm regularized discriminative feature selection for unsupervised learning (468 citations)
  • Inter-media hashing for large-scale retrieval from heterogeneous data sources (389 citations)
  • Multiple feature hashing for real-time large scale near-duplicate video retrieval (258 citations)

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

Zi Huang spends much of his time researching Artificial intelligence, Machine learning, Data mining, Hash function and Information retrieval. Zi Huang works mostly in the field of Artificial intelligence, limiting it down to topics relating to Pattern recognition and, in certain cases, Benchmark, as a part of the same area of interest. His Data mining research integrates issues from Ranking, Representation, Noise and Search engine indexing.

His work on Feature hashing as part of general Hash function study is frequently linked to Binary code, bridging the gap between disciplines. The study incorporates disciplines such as Image and Multimedia in addition to Information retrieval. In his work, Curse of dimensionality is strongly intertwined with Feature vector, which is a subfield of Nearest neighbor search.

He most often published in these fields:

  • Artificial intelligence (50.61%)
  • Machine learning (26.32%)
  • Data mining (19.84%)

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

  • Artificial intelligence (50.61%)
  • Machine learning (26.32%)
  • Recommender system (10.93%)

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

Zi Huang focuses on Artificial intelligence, Machine learning, Recommender system, Theoretical computer science and Hash function. While working in this field, he studies both Artificial intelligence and Modal. His study in the field of Feature learning, Leverage and Feature also crosses realms of Modalities.

The concepts of his Recommender system study are interwoven with issues in Adversarial system, Human–computer interaction and Knowledge graph. His Theoretical computer science research is multidisciplinary, incorporating perspectives in Domain adaptation, Subspace topology, Source data and Relation. His Hash function research includes elements of Image retrieval and Feature vector.

Between 2019 and 2021, his most popular works were:

  • Exploiting Subspace Relation in Semantic Labels for Cross-modal Hashing (29 citations)
  • CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language (13 citations)
  • Inductive Structure Consistent Hashing via Flexible Semantic Calibration. (9 citations)

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

  • Artificial intelligence
  • Machine learning
  • Algorithm

His primary scientific interests are in Recommender system, Artificial intelligence, Theoretical computer science, Information retrieval and Graph neural networks. His Recommender system research is multidisciplinary, incorporating elements of Adversarial system and Feature learning. Zi Huang combines subjects such as Machine learning and Computer vision with his study of Artificial intelligence.

Theoretical computer science and Hash function are frequently intertwined in his study. The Hash function study combines topics in areas such as Subspace topology and Feature vector. His Information retrieval research is multidisciplinary, relying on both Sentiment analysis, Interpretability, Pairwise comparison and Personalization.

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

l 2,1 -norm regularized discriminative feature selection for unsupervised learning

Yi Yang;Heng Tao Shen;Zhigang Ma;Zi Huang.
international joint conference on artificial intelligence (2011)

585 Citations

L2,1-Norm Regularized Discriminative Feature Selection for Unsupervised

Yi Yang;Heng Tao Shen;Zhigang Ma;Zi Huang.
international joint conference on artificial intelligence (2011)

572 Citations

Inter-media hashing for large-scale retrieval from heterogeneous data sources

Jingkuan Song;Yang Yang;Yi Yang;Zi Huang.
international conference on management of data (2013)

392 Citations

Multiple feature hashing for real-time large scale near-duplicate video retrieval

Jingkuan Song;Yi Yang;Zi Huang;Heng Tao Shen.
acm multimedia (2011)

278 Citations

Linear cross-modal hashing for efficient multimedia search

Xiaofeng Zhu;Zi Huang;Heng Tao Shen;Xin Zhao.
acm multimedia (2013)

253 Citations

A sparse embedding and least variance encoding approach to hashing

Xiaofeng Zhu;Lei Zhang;Zi Huang.
IEEE Transactions on Image Processing (2014)

226 Citations

Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization

Fumin Shen;Yan Xu;Li Liu;Yang Yang.
IEEE Transactions on Pattern Analysis and Machine Intelligence (2018)

214 Citations

Effective Multiple Feature Hashing for Large-Scale Near-Duplicate Video Retrieval

Jingkuan Song;Yi Yang;Zi Huang;Heng Tao Shen.
IEEE Transactions on Multimedia (2013)

186 Citations

Self-taught dimensionality reduction on the high-dimensional small-sized data

Xiaofeng Zhu;Zi Huang;Yang Yang;Heng Tao Shen.
Pattern Recognition (2013)

169 Citations

Transfer Independently Together: A Generalized Framework for Domain Adaptation

Jingjing Li;Ke Lu;Zi Huang;Lei Zhu.
IEEE Transactions on Systems, Man, and Cybernetics (2019)

166 Citations

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

Contact us

Best Scientists Citing Zi Huang

Heng Tao Shen

Heng Tao Shen

University of Electronic Science and Technology of China

Publications: 96

Yang Yang

Yang Yang

University of Electronic Science and Technology of China

Publications: 92

Fumin Shen

Fumin Shen

University of Electronic Science and Technology of China

Publications: 74

Hongzhi Yin

Hongzhi Yin

University of Queensland

Publications: 65

Xuelong Li

Xuelong Li

Northwestern Polytechnical University

Publications: 65

Jingkuan Song

Jingkuan Song

Columbia University

Publications: 57

Feiping Nie

Feiping Nie

Northwestern Polytechnical University

Publications: 50

Xiaofang Zhou

Xiaofang Zhou

Hong Kong University of Science and Technology

Publications: 49

Yi Yang

Yi Yang

Zhejiang University

Publications: 46

Dacheng Tao

Dacheng Tao

University of Sydney

Publications: 42

Lianli Gao

Lianli Gao

University of Electronic Science and Technology of China

Publications: 40

Ling Shao

Ling Shao

Inception Institute of Artificial Intelligence

Publications: 37

Meng Wang

Meng Wang

Hefei University of Technology

Publications: 35

Qi Tian

Qi Tian

Huawei Technologies (China)

Publications: 33

Philip S. Yu

Philip S. Yu

University of Illinois at Chicago

Publications: 33

Nicu Sebe

Nicu Sebe

University of Trento

Publications: 32

Something went wrong. Please try again later.