What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Programming language
Yu-Gang Jiang mostly deals with Artificial intelligence, Machine learning, Pattern recognition, Convolutional neural network and Motion.
He merges many fields, such as Artificial intelligence and TRECVID, in his writings.
His research in Machine learning intersects with topics in Annotation, Visualization, Feature extraction and Object detection.
His work on Unsupervised learning as part of general Pattern recognition research is frequently linked to Detector, bridging the gap between disciplines.
His work carried out in the field of Convolutional neural network brings together such families of science as Network architecture, Image, Closed captioning, Semantics and Natural language.
The study incorporates disciplines such as Class and Representation in addition to Motion.
His most cited work include:
- Supervised hashing with kernels (1111 citations)
- Evaluating bag-of-visual-words representations in scene classification (675 citations)
- Towards optimal bag-of-features for object categorization and semantic video retrieval (590 citations)
What are the main themes of his work throughout his whole career to date?
Yu-Gang Jiang spends much of his time researching Artificial intelligence, Machine learning, Pattern recognition, Deep learning and Information retrieval.
His Artificial intelligence study often links to related topics such as Computer vision.
His research integrates issues of Training set, Object detection, Categorization, The Internet and Semantics in his study of Machine learning.
His work deals with themes such as Contextual image classification, Artificial neural network and Image retrieval, which intersect with Pattern recognition.
His Deep learning research is multidisciplinary, incorporating elements of Feature and Benchmark.
His Information retrieval research includes elements of Context and Similarity.
He most often published in these fields:
- Artificial intelligence (70.82%)
- Machine learning (29.96%)
- Pattern recognition (21.79%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (70.82%)
- Machine learning (29.96%)
- Computer vision (11.28%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Machine learning, Computer vision, Pattern recognition and Embedding.
His study in Representation, Deep learning, Image, Closed captioning and Sentence is done as part of Artificial intelligence.
His work on Discriminative model as part of his general Machine learning study is frequently connected to Baseline, thereby bridging the divide between different branches of science.
His work on RGB color model as part of general Computer vision research is frequently linked to Pedestrian detection, thereby connecting diverse disciplines of science.
His Pattern recognition research is multidisciplinary, relying on both Domain, Image retrieval, Task and Benchmark.
His Embedding research incorporates themes from Sketch and Semantics.
Between 2019 and 2021, his most popular works were:
- Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification (25 citations)
- Object Detection from Scratch with Deep Supervision (18 citations)
- Hyperbolic Visual Embedding Learning for Zero-Shot Recognition (14 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
His scientific interests lie mostly in Artificial intelligence, Machine learning, Embedding, Task analysis and Visualization.
Artificial intelligence connects with themes related to Pattern recognition in his study.
As a part of the same scientific family, Yu-Gang Jiang mostly works in the field of Pattern recognition, focusing on Representation and, on occasion, Artificial neural network.
His Machine learning study combines topics in areas such as RGB color model, Object detection, Pascal and Learning object.
His study on Embedding also encompasses disciplines like
- Semantics that connect with fields like Training set, Ranking SVM, Ranking and Margin,
- Manifold which intersects with area such as Vocabulary, Class and Object.
His Deep learning research is multidisciplinary, incorporating perspectives in Speech recognition, Layer, Feature and Component.
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.
