What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of study are Artificial intelligence, Pattern recognition, Feature extraction, Speech recognition and Handwriting recognition.
His work carried out in the field of Artificial intelligence brings together such families of science as Computer vision and Natural language processing.
His Pattern recognition research incorporates themes from Artificial neural network and Normalization.
His research integrates issues of Feature, Feature, Image processing, Binary image and Contextual image classification in his study of Feature extraction.
His Speech recognition study combines topics in areas such as Segmentation, Discriminative learning, Random subspace method, Character recognition and Pattern recognition.
In his research on the topic of Handwriting recognition, Preprocessor, State and Pen computing is strongly related with Intelligent character recognition.
His most cited work include:
- Action recognition by dense trajectories (1863 citations)
- Dense Trajectories and Motion Boundary Descriptors for Action Recognition (1238 citations)
- Handwritten digit recognition: benchmarking of state-of-the-art techniques (468 citations)
What are the main themes of his work throughout his whole career to date?
Cheng-Lin Liu focuses on Artificial intelligence, Pattern recognition, Feature extraction, Speech recognition and Handwriting recognition.
His research in Artificial intelligence intersects with topics in Machine learning, Computer vision and Natural language processing.
His work carried out in the field of Pattern recognition brings together such families of science as Contextual image classification and Artificial neural network.
The concepts of his Feature extraction study are interwoven with issues in Normalization, Feature, Conditional random field, Support vector machine and Feature vector.
Cheng-Lin Liu combines subjects such as Character recognition, Recurrent neural network, Intelligent word recognition and Discriminative learning with his study of Speech recognition.
His studies in Handwriting recognition integrate themes in fields like Language model, Chinese characters, Intelligent character recognition, Character and Hidden Markov model.
He most often published in these fields:
- Artificial intelligence (94.34%)
- Pattern recognition (64.01%)
- Feature extraction (25.45%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (94.34%)
- Pattern recognition (64.01%)
- Convolutional neural network (15.68%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Pattern recognition, Convolutional neural network, Pattern recognition and Machine learning.
His Artificial intelligence study incorporates themes from Graph, Computer vision and Natural language processing.
Feature extraction is the focus of his Pattern recognition research.
Cheng-Lin Liu interconnects Algorithm and Word in the investigation of issues within Feature extraction.
Cheng-Lin Liu studied Convolutional neural network and Computer engineering that intersect with Word error rate.
His study in Machine learning is interdisciplinary in nature, drawing from both Data stream, Data point, Probabilistic logic and Inference.
Between 2018 and 2021, his most popular works were:
- Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation (49 citations)
- TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting (46 citations)
- BlockQNN: Efficient Block-wise Neural Network Architecture Generation. (40 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Artificial intelligence, Text detection, Pattern recognition, Convolutional neural network and Robustness are his primary areas of study.
His research ties Machine learning and Artificial intelligence together.
His Text detection research includes elements of Categorization and Natural language processing.
His work on Tumor segmentation, Brain tumor segmentation and Image segmentation as part of general Pattern recognition research is often related to Data sampling and Modalities, thus linking different fields of science.
His Convolutional neural network research is multidisciplinary, incorporating perspectives in Computer engineering and Word error rate.
His Robustness study deals with Speech recognition intersecting with Constraint, Chinese characters, Character and Task.
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.
