What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Jinhui Tang mostly deals with Artificial intelligence, Pattern recognition, Machine learning, Image retrieval and Discriminative model.
Artificial intelligence and Graph are frequently intertwined in his study.
His study in Pattern recognition is interdisciplinary in nature, drawing from both Subspace topology, Artificial neural network, Sparse matrix, Optimization problem and Robustness.
Jinhui Tang interconnects Training set, Categorization and Semantic gap in the investigation of issues within Machine learning.
His studies in Image retrieval integrate themes in fields like Annotation, Deep learning and Information retrieval.
His Discriminative model research is multidisciplinary, relying on both Cluster analysis, Algorithm design and Computer vision.
His most cited work include:
- NUS-WIDE: a real-world web image database from National University of Singapore (1753 citations)
- Correlative multi-label video annotation (412 citations)
- Unified Video Annotation via Multigraph Learning (412 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Pattern recognition, Machine learning, Computer vision and Image are his primary areas of study.
His studies in Feature extraction, Discriminative model, Image retrieval, Convolutional neural network and Robustness are all subfields of Artificial intelligence research.
The Discriminative model study combines topics in areas such as Feature learning and Feature selection.
The various areas that Jinhui Tang examines in his Image retrieval study include Annotation and Information retrieval.
His Pattern recognition research integrates issues from Contextual image classification, Subspace topology, Feature and Graph.
His research in Machine learning intersects with topics in Training set, Categorization and TRECVID.
He most often published in these fields:
- Artificial intelligence (73.48%)
- Pattern recognition (38.34%)
- Machine learning (22.36%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (73.48%)
- Pattern recognition (38.34%)
- Image (14.06%)
In recent papers he was focusing on the following fields of study:
Jinhui Tang mainly focuses on Artificial intelligence, Pattern recognition, Image, Machine learning and Convolutional neural network.
Artificial intelligence is closely attributed to Natural language processing in his study.
The study incorporates disciplines such as Object detection, Representation, Feature and Image retrieval in addition to Pattern recognition.
His Image research is multidisciplinary, incorporating perspectives in Pixel and Filter.
His work in Machine learning addresses subjects such as Embedding, which are connected to disciplines such as Theoretical computer science.
His Convolutional neural network study incorporates themes from Feature, DUAL, Pairwise comparison, Computer vision and Collaborative filtering.
Between 2017 and 2021, his most popular works were:
- Single Image Dehazing via Conditional Generative Adversarial Network (138 citations)
- Deep Collaborative Embedding for Social Image Understanding (119 citations)
- Robust Structured Nonnegative Matrix Factorization for Image Representation (115 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Jinhui Tang spends much of his time researching Artificial intelligence, Pattern recognition, Image retrieval, Convolutional neural network and Visualization.
His is doing research in Deep learning, Discriminative model, Image restoration, Image and Feature extraction, both of which are found in Artificial intelligence.
Many of his research projects under Pattern recognition are closely connected to Locality-sensitive hashing and Coherence with Locality-sensitive hashing and Coherence, tying the diverse disciplines of science together.
The concepts of his Image retrieval study are interwoven with issues in Data mining, Information retrieval and k-nearest neighbors algorithm.
In his research, Hidden Markov model and Context model is intimately related to Feature, which falls under the overarching field of Convolutional neural network.
His work focuses on many connections between Visualization and other disciplines, such as Feature learning, that overlap with his field of interest in Classifier, Knowledge engineering, Computer vision, Cosine similarity and Knowledge transfer.
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.
