What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Xiao Liu mainly investigates Artificial intelligence, Feature extraction, Pattern recognition, Feature and Computer vision.
His Artificial intelligence research incorporates elements of Algorithm and Machine learning.
His studies deal with areas such as Triplet loss, Training set and Image retrieval as well as Feature extraction.
His work deals with themes such as Artificial neural network, Backpropagation, Pooling, Categorization and Kernel, which intersect with Pattern recognition.
Within one scientific family, Xiao Liu focuses on topics pertaining to Image under Feature, and may sometimes address concerns connected to Translation and Face.
His study in the field of Tracking system and Segmentation is also linked to topics like Graph and Graph theory.
His most cited work include:
- Deep Metric Learning with Angular Loss (244 citations)
- Deep Speaker: an End-to-End Neural Speaker Embedding System (223 citations)
- Kernel Pooling for Convolutional Neural Networks (197 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Pattern recognition, Computer vision, Image and Machine learning are his primary areas of study.
All of his Artificial intelligence and Feature, Discriminative model, Feature extraction, Reinforcement learning and Benchmark investigations are sub-components of the entire Artificial intelligence study.
His research in Feature extraction tackles topics such as Data mining which are related to areas like Classifier and Stability.
The various areas that Xiao Liu examines in his Pattern recognition study include 3D pose estimation and Convolution.
In general Computer vision, his work in Tracking and Fingerprint is often linked to Position and Process linking many areas of study.
He has researched Image in several fields, including Semantic annotation and Back projection.
He most often published in these fields:
- Artificial intelligence (84.78%)
- Pattern recognition (38.04%)
- Computer vision (33.70%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (84.78%)
- Computer vision (33.70%)
- Image (20.65%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Computer vision, Image, Pattern recognition and Feature.
His work on Reinforcement learning, Feature extraction and Human motion as part of his general Artificial intelligence study is frequently connected to Ground and Sliding window protocol, thereby bridging the divide between different branches of science.
Xiao Liu combines subjects such as Visualization and Encoding with his study of Feature extraction.
His work on Tracking as part of general Computer vision study is frequently linked to Position, Current and Space, bridging the gap between disciplines.
His Pattern recognition research is multidisciplinary, relying on both 3D pose estimation, Convolution and Projection.
His biological study spans a wide range of topics, including Fingerprint, Translation, Filter and Image quality.
Between 2018 and 2021, his most popular works were:
- STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing (83 citations)
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation (78 citations)
- Image Inpainting With Learnable Bidirectional Attention Maps (52 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
Xiao Liu focuses on Artificial intelligence, Pattern recognition, Feature, Convolution and Encoder.
While working on this project, Xiao Liu studies both Artificial intelligence and Task analysis.
Pattern recognition and Deep learning are commonly linked in his work.
His research investigates the link between Feature and topics such as Image that cross with problems in Pixel.
His Convolution research is multidisciplinary, incorporating elements of Inpainting, Representation, Filter and Filling-in.
His Reinforcement learning study combines topics from a wide range of disciplines, such as Ranking and 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.
