What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Computer vision
The scientist’s investigation covers issues in Artificial intelligence, Computer vision, Pattern recognition, Facial recognition system and Particle filter.
By researching both Artificial intelligence and Gabor wavelet, Li Bai produces research that crosses academic boundaries.
His study in the field of Eye tracking, Image processing and Object detection also crosses realms of Q-ball.
His research in Pattern recognition intersects with topics in Sensor fusion, Face, Face detection and Metric.
His Facial recognition system study combines topics from a wide range of disciplines, such as Authentication, The Internet, Measure and Pattern recognition.
His research investigates the connection between Particle filter and topics such as Sparse approximation that intersect with problems in Resampling, Linear least squares, Subspace topology and Benchmark.
His most cited work include:
- Cosine similarity metric learning for face verification (406 citations)
- A review on Gabor wavelets for face recognition (385 citations)
- Minimum error bounded efficient ℓ1 tracker with occlusion detection. (300 citations)
What are the main themes of his work throughout his whole career to date?
Li Bai focuses on Artificial intelligence, Computer vision, Pattern recognition, Segmentation and Image segmentation.
Li Bai brings together Artificial intelligence and Gabor wavelet to produce work in his papers.
His work deals with themes such as Optical coherence tomography and Curvature, which intersect with Computer vision.
His Pattern recognition research incorporates themes from Contextual image classification and Feature.
His Image segmentation study combines topics in areas such as Active shape model and Intensity.
His Image research includes themes of Algorithm and Fast Fourier transform.
He most often published in these fields:
- Artificial intelligence (50.41%)
- Computer vision (35.54%)
- Pattern recognition (24.38%)
What were the highlights of his more recent work (between 2014-2020)?
- Artificial intelligence (50.41%)
- Computer vision (35.54%)
- Segmentation (12.40%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Computer vision, Segmentation, Pattern recognition and Image segmentation.
Li Bai has included themes like Kalman filter, Optical coherence tomography and Computer graphics in his Computer vision study.
The Segmentation study combines topics in areas such as Image processing, Binary image and Channel.
His study in the field of Classifier is also linked to topics like Forensic anthropology.
He combines subjects such as Color constancy and Filter with his study of Image segmentation.
Li Bai has researched Image in several fields, including Algorithm and Fast Fourier transform.
Between 2014 and 2020, his most popular works were:
- Deep Learning in Visual Computing and Signal Processing (62 citations)
- Denoising optical coherence tomography using second order total generalized variation decomposition (60 citations)
- Implementation of high‐order variational models made easy for image processing (55 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Computer vision
His primary scientific interests are in Artificial intelligence, Computer vision, Image, Segmentation and Algorithm.
Li Bai connects Artificial intelligence with Robot learning in his study.
Li Bai studies Feature extraction which is a part of Computer vision.
His Feature extraction research is multidisciplinary, relying on both Fractal dimension, Fractal, Multifractal system and Image denoising.
His research in Algorithm focuses on subjects like Mathematical optimization, which are connected to Nonlinear system and Inpainting.
His studies in Pattern recognition integrate themes in fields like Graph, Similarity, Human visual system model, Pairwise comparison and Kadir–Brady saliency detector.
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.
