What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Yan Yan spends much of his time researching Artificial intelligence, Pattern recognition, Machine learning, Discriminative model and Multi-task learning.
His study in Feature, Convolutional neural network, Training set, Support vector machine and Face is done as part of Artificial intelligence.
In his study, which falls under the umbrella issue of Feature, Noise reduction, Motion, Contrast and Matching is strongly linked to Representation.
His study looks at the relationship between Pattern recognition and topics such as Deep learning, which overlap with Anomaly detection.
His research investigates the link between Machine learning and topics such as Visualization that cross with problems in Semi-supervised learning.
His study looks at the intersection of Discriminative model and topics like Feature extraction with Landmark.
His most cited work include:
- Learning Deep Representations of Appearance and Motion for Anomalous Event Detection (245 citations)
- Fortune teller: predicting your career path (200 citations)
- Detecting anomalous events in videos by learning deep representations of appearance and motion (176 citations)
What are the main themes of his work throughout his whole career to date?
Yan Yan mainly focuses on Artificial intelligence, Pattern recognition, Machine learning, Computer vision and Discriminative model.
Artificial intelligence is represented through his Feature, Deep learning, Image, Pose and Face research.
His Feature selection and Classifier study in the realm of Pattern recognition connects with subjects such as Invariant and Constraint.
Yan Yan regularly ties together related areas like Contextual image classification in his Machine learning studies.
When carried out as part of a general Computer vision research project, his work on Optical flow and Gaze is frequently linked to work in GPS signals, therefore connecting diverse disciplines of study.
His studies deal with areas such as Object and Feature extraction as well as Discriminative model.
He most often published in these fields:
- Artificial intelligence (72.58%)
- Pattern recognition (27.96%)
- Machine learning (24.19%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (72.58%)
- Modal (4.30%)
- Applied mathematics (9.14%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Modal, Applied mathematics, Pattern recognition and Computer vision.
His Artificial intelligence study frequently links to related topics such as Machine learning.
His research integrates issues of Object and Conditional random field in his study of Machine learning.
His biological study deals with issues like Smooth pursuit, which deal with fields such as Statistical algorithm and Robustness.
His work in the fields of Computer vision, such as Enhanced Data Rates for GSM Evolution, Shadow and Image, overlaps with other areas such as Distortion and Market segmentation.
Task and Semantics is closely connected to Discriminative model in his research, which is encompassed under the umbrella topic of Feature.
Between 2019 and 2021, his most popular works were:
- Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation (28 citations)
- Segmenting Objects in Day and Night: Edge-Conditioned CNN for Thermal Image Semantic Segmentation. (11 citations)
- Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation (9 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
Yan Yan mostly deals with Artificial intelligence, Applied mathematics, Duality gap, Convexity and Feature.
His Artificial intelligence research integrates issues from Machine learning and Computer vision.
His work on Margin as part of general Machine learning research is frequently linked to Rank, bridging the gap between disciplines.
Yan Yan combines subjects such as Gradient descent and Stochastic gradient descent with his study of Applied mathematics.
Yan Yan has included themes like Image generation and Generative adversarial network in his Feature study.
The various areas that Yan Yan examines in his Artificial neural network study include Contrast, Computation and Canonical correlation.
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.
