What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Optics
His primary areas of investigation include Artificial intelligence, Computer vision, Pattern recognition, Segmentation and Pixel.
His research in Image processing, Dimensionality reduction, Object detection, Convolutional neural network and Object are components of Artificial intelligence.
His Dimensionality reduction study also includes
- Facial recognition system that connect with fields like Nonlinear dimensionality reduction and Linear discriminant analysis,
- Graph embedding together with Directed graph.
Stephen Lin works mostly in the field of Computer vision, limiting it down to concerns involving Computer graphics and, occasionally, Inverse problem and Computational science.
His biological study spans a wide range of topics, including Geometrical optics and Conditional random field.
The study incorporates disciplines such as Recurrent neural network, Image texture, Specular reflection, Vignetting and Diffuse reflection in addition to Pixel.
His most cited work include:
- Graph Embedding and Extensions: A General Framework for Dimensionality Reduction (2213 citations)
- Deformable ConvNets V2: More Deformable, Better Results (396 citations)
- 3D shape regression for real-time facial animation (314 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Computer vision, Pattern recognition, Image and Pixel.
His Artificial intelligence study frequently involves adjacent topics like Machine learning.
His research integrates issues of Specular reflection, Computer graphics and Reflectivity in his study of Computer vision.
His work deals with themes such as Facial recognition system and Kernel, which intersect with Pattern recognition.
His Rendering research focuses on subjects like Radiance, which are linked to Scattering.
His studies deal with areas such as Representation and Benchmark as well as Object.
He most often published in these fields:
- Artificial intelligence (84.67%)
- Computer vision (58.24%)
- Pattern recognition (22.61%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (84.67%)
- Computer vision (58.24%)
- Object detection (9.58%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Computer vision, Object detection, Segmentation and Object.
His Artificial intelligence research incorporates elements of Machine learning and Pattern recognition.
His Convolutional neural network study in the realm of Pattern recognition connects with subjects such as Visual impairment.
His work on Motion estimation, Pose and Pixel as part of general Computer vision research is often related to Process, thus linking different fields of science.
His research in Segmentation intersects with topics in Similarity and Feature learning.
His research on Object also deals with topics like
- Representation which intersects with area such as Algorithm,
- Point, which have a strong connection to Distance transform and Orientation.
Between 2018 and 2021, his most popular works were:
- Deformable ConvNets V2: More Deformable, Better Results (396 citations)
- GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond (190 citations)
- RepPoints: Point Set Representation for Object Detection (149 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
His primary areas of study are Artificial intelligence, Computer vision, Pixel, Pattern recognition and Object detection.
His Artificial intelligence study deals with Machine learning intersecting with Metric.
His Computer vision research includes elements of Convolution and Closure.
His Pixel study combines topics from a wide range of disciplines, such as Feature, Inference and Pattern matching.
His research investigates the link between Object detection and topics such as Segmentation that cross with problems in Salient, Artificial neural network and Pascal.
He has researched Object in several fields, including Representation and Benchmark.
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.
