What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Lingxi Xie focuses on Artificial intelligence, Pattern recognition, Code, Segmentation and Contextual image classification.
His work is dedicated to discovering how Artificial intelligence, Machine learning are connected with Encoding and other disciplines.
Lingxi Xie has included themes like Object and Object detection in his Pattern recognition study.
His Code research is multidisciplinary, relying on both Stability, Regularization and Network architecture.
His study in the field of Image segmentation also crosses realms of Variable and Fraction.
The Contextual image classification study combines topics in areas such as Visual Word and Image texture.
His most cited work include:
- Genetic CNN (372 citations)
- CenterNet: Keypoint Triplets for Object Detection (359 citations)
- Adversarial Examples for Semantic Segmentation and Object Detection (326 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Pattern recognition, Machine learning, Contextual image classification and Segmentation.
His research investigates the connection between Artificial intelligence and topics such as Computer vision that intersect with issues in Adversarial system.
In his research on the topic of Pattern recognition, Convolutional neural network is strongly related with Convolution.
His study looks at the relationship between Machine learning and fields such as Training set, as well as how they intersect with chemical problems.
His work in Contextual image classification tackles topics such as Range which are related to areas like Fuzzy logic.
His work on Object detection as part of general Object study is frequently linked to Class, bridging the gap between disciplines.
He most often published in these fields:
- Artificial intelligence (82.68%)
- Pattern recognition (43.58%)
- Machine learning (21.23%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (82.68%)
- Machine learning (21.23%)
- Pattern recognition (43.58%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Pattern recognition, Discriminative model and Code.
His Artificial intelligence study incorporates themes from Key and Computer vision.
Lingxi Xie has researched Machine learning in several fields, including Contextual image classification and Training set.
His study in Pattern recognition is interdisciplinary in nature, drawing from both Object detection and Quantization.
Lingxi Xie combines subjects such as Regularization and Facial expression with his study of Discriminative model.
His Code research incorporates elements of Network architecture and Computer engineering.
Between 2019 and 2021, his most popular works were:
- PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search (93 citations)
- Unsupervised Person Re-Identification via Softened Similarity Learning (23 citations)
- Pruning from Scratch (17 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Lingxi Xie spends much of his time researching Artificial intelligence, Pattern recognition, Code, Computer engineering and Stability.
His Artificial intelligence research is multidisciplinary, incorporating elements of Machine learning and Computer vision.
His research in the fields of Segmentation overlaps with other disciplines such as Image.
His Code study frequently involves adjacent topics like Image segmentation.
Lingxi Xie interconnects Variation and Gradient estimation in the investigation of issues within Stability.
The study incorporates disciplines such as Precision and recall, Monocular and Bounding overwatch in addition to Object.
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.
