What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Computer vision, Machine learning and Feature extraction.
His study in Convolutional neural network, Deep learning, Support vector machine, Image segmentation and Segmentation is done as part of Artificial intelligence.
His biological study spans a wide range of topics, including Neocognitron, Character recognition, Image and Minimum bounding box.
Lianwen Jin combines subjects such as Contextual image classification, Feature, Robustness and Benchmark with his study of Pattern recognition.
Lianwen Jin has researched Machine learning in several fields, including Smoothing and Covariance matrix.
Lianwen Jin studied Feature extraction and Feature that intersect with Cognitive neuroscience of visual object recognition, Intelligent word recognition and Pixel.
His most cited work include:
- Activity recognition from acceleration data based on discrete consine transform and SVM (200 citations)
- Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection (169 citations)
- Person Re-Identification by Regularized Smoothing KISS Metric Learning (143 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Pattern recognition, Computer vision, Feature extraction and Convolutional neural network.
His biological study spans a wide range of topics, including Machine learning and Speech recognition.
His Speech recognition research focuses on subjects like Linear discriminant analysis, which are linked to Dimensionality reduction.
His work on Discriminative model as part of general Pattern recognition research is frequently linked to Path, bridging the gap between disciplines.
His Feature extraction research focuses on Robustness and how it relates to Text recognition.
The various areas that Lianwen Jin examines in his Convolutional neural network study include Artificial neural network, Character, Image and Feature learning.
He most often published in these fields:
- Artificial intelligence (87.00%)
- Pattern recognition (54.67%)
- Computer vision (21.00%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (87.00%)
- Pattern recognition (54.67%)
- Text recognition (6.00%)
In recent papers he was focusing on the following fields of study:
Lianwen Jin mainly focuses on Artificial intelligence, Pattern recognition, Text recognition, Image and Machine learning.
As part of his studies on Artificial intelligence, Lianwen Jin often connects relevant subjects like Natural language processing.
Lianwen Jin is interested in Convolutional neural network, which is a field of Pattern recognition.
His research integrates issues of Attention network and Robustness in his study of Text recognition.
In the subject of general Machine learning, his work in Ground truth is often linked to Novelty, thereby combining diverse domains of study.
His Feature study combines topics from a wide range of disciplines, such as Speech recognition, Representation and Handwriting.
Between 2018 and 2021, his most popular works were:
- MORAN: A Multi-Object Rectified Attention Network for scene text recognition (123 citations)
- Curved scene text detection via transverse and longitudinal sequence connection (60 citations)
- Aggregation Cross-Entropy for Sequence Recognition (37 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His primary areas of study are Artificial intelligence, Pattern recognition, Text recognition, Image and Object.
The Artificial intelligence study combines topics in areas such as Machine learning and Natural language processing.
His Pattern recognition research integrates issues from Transformer and Gesture recognition.
His Text recognition study also includes
- Attention network, which have a strong connection to Feature,
- Robustness which intersects with area such as Annotation.
Lianwen Jin usually deals with Image and limits it to topics linked to Speech recognition and Character.
As a part of the same scientific family, Lianwen Jin mostly works in the field of Object, focusing on Sensitivity and, on occasion, Feature and Variation.
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.
