What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Programming language
His main research concerns Artificial intelligence, Pattern recognition, Convolutional neural network, Machine learning and Parsing.
Artificial intelligence is closely attributed to Computer vision in his research.
His Pattern recognition research incorporates elements of Image resolution, Set and Face.
His Convolutional neural network research includes themes of Categorization, Deep learning and Context model.
He combines subjects such as Smoothing, Pixel, Feature learning and Context with his study of Parsing.
His Semantics study incorporates themes from Benchmark and Natural language processing.
His most cited work include:
- Is Faster R-CNN Doing Well for Pedestrian Detection? (473 citations)
- Toward controlled generation of text (450 citations)
- Scale-Aware Fast R-CNN for Pedestrian Detection (333 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Machine learning, Pattern recognition, Segmentation and Parsing.
His Artificial intelligence study integrates concerns from other disciplines, such as Graph, Computer vision and Natural language processing.
The various areas that Xiaodan Liang examines in his Machine learning study include Inference and Benchmark.
Xiaodan Liang has included themes like Pixel and Boosting in his Pattern recognition study.
Xiaodan Liang works mostly in the field of Segmentation, limiting it down to topics relating to Object and, in certain cases, Class.
As a member of one scientific family, Xiaodan Liang mostly works in the field of Parsing, focusing on Context and, on occasion, Question answering and Representation.
He most often published in these fields:
- Artificial intelligence (75.00%)
- Machine learning (22.35%)
- Pattern recognition (21.97%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (75.00%)
- Machine learning (22.35%)
- Natural language processing (14.77%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Natural language processing, Graph and Context.
His study in the field of Segmentation, Parsing and Natural language is also linked to topics like Block and Network architecture.
His study looks at the relationship between Parsing and topics such as Leverage, which overlap with Feature extraction.
In his study, Probabilistic logic is strongly linked to Robustness, which falls under the umbrella field of Machine learning.
His biological study spans a wide range of topics, including Visualization, Word, Deep learning and Closed captioning.
His Graph research also works with subjects such as
- Domain which connect with Relation, Adaptation, Image, Reduction and Pattern recognition,
- Theoretical computer science and related Binary expression tree, Solver and Object detector.
Between 2019 and 2021, his most popular works were:
- Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation (35 citations)
- Vision-Language Navigation With Self-Supervised Auxiliary Reasoning Tasks (31 citations)
- Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder (23 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
Xiaodan Liang mostly deals with Artificial intelligence, Machine learning, Parsing, Leverage and Architecture.
His Artificial intelligence study frequently links to other fields, such as Graph.
As a part of the same scientific study, Xiaodan Liang usually deals with the Graph, concentrating on Relation and frequently concerns with Reduction and Pattern recognition.
As a part of the same scientific family, he mostly works in the field of Parsing, focusing on Artificial neural network and, on occasion, Normalization, Inpainting, Natural language processing and Parse tree.
His research integrates issues of Multi-objective optimization, Segmentation, Inference and Modular design in his study of Leverage.
In his work, Margin, Consistency, Semantics and Visual language is strongly intertwined with Human–computer interaction, which is a subfield of Natural language.
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.
