What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Shaogang Gong mainly investigates Artificial intelligence, Machine learning, Pattern recognition, Computer vision and Discriminative model.
Feature extraction, Facial recognition system, Training set, Object and Representation are the primary areas of interest in his Artificial intelligence study.
His study looks at the intersection of Machine learning and topics like Embedding with Semantics.
Shaogang Gong has researched Pattern recognition in several fields, including Model selection and Visual appearance.
His Computer vision research focuses on subjects like Mixture model, which are linked to Color image, Adaptation and Selection.
His Discriminative model study deals with Ranking intersecting with Dynamic time warping.
His most cited work include:
- Facial expression recognition based on Local Binary Patterns: A comprehensive study (1570 citations)
- Reidentification by Relative Distance Comparison (581 citations)
- Person Re-Identification by Support Vector Ranking (536 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Machine learning, Pattern recognition, Computer vision and Discriminative model.
His is involved in several facets of Artificial intelligence study, as is seen by his studies on Facial recognition system, Deep learning, Face, Training set and Unsupervised learning.
His Machine learning research is multidisciplinary, relying on both Embedding and Benchmark.
His Pattern recognition research is multidisciplinary, incorporating perspectives in Image and Robustness.
His study in Face detection, Tracking, Segmentation, Image segmentation and Video tracking is done as part of Computer vision.
His Convolutional neural network research extends to Discriminative model, which is thematically connected.
He most often published in these fields:
- Artificial intelligence (88.28%)
- Machine learning (39.23%)
- Pattern recognition (37.32%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (88.28%)
- Machine learning (39.23%)
- Deep learning (10.77%)
In recent papers he was focusing on the following fields of study:
Shaogang Gong focuses on Artificial intelligence, Machine learning, Deep learning, Training set and Discriminative model.
His study brings together the fields of Pattern recognition and Artificial intelligence.
His work deals with themes such as Class and Inference, which intersect with Machine learning.
His work investigates the relationship between Deep learning and topics such as Feature that intersect with problems in MNIST database, Control and Representation.
His Training set research integrates issues from Leverage and Re identification.
His study in Discriminative model is interdisciplinary in nature, drawing from both Feature learning and Pairwise comparison.
Between 2018 and 2021, his most popular works were:
- Unsupervised Person Re-Identification by Soft Multilabel Learning (104 citations)
- Imbalanced Deep Learning by Minority Class Incremental Rectification (104 citations)
- Unsupervised Tracklet Person Re-Identification (42 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His scientific interests lie mostly in Artificial intelligence, Machine learning, Training set, Discriminative model and Deep learning.
Shaogang Gong undertakes multidisciplinary investigations into Artificial intelligence and Data modeling in his work.
In general Machine learning, his work in Semantic clustering is often linked to Compact space and Stochastic approximation linking many areas of study.
His Training set study combines topics from a wide range of disciplines, such as Object and Iterative method.
His Deep learning research includes themes of Variety and Information retrieval.
His Embedding study combines topics in areas such as Semantics and Set.
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.
