What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
Stan Z. Li mainly investigates Artificial intelligence, Pattern recognition, Computer vision, Facial recognition system and Face. His study connects Machine learning and Artificial intelligence. His Pattern recognition research incorporates elements of Histogram, Local binary patterns and Feature.
He combines subjects such as Detector and Benchmark with his study of Computer vision. His biological study spans a wide range of topics, including Artificial neural network, Liveness, Quotient and Biometrics. His Face research is multidisciplinary, incorporating elements of Principal component analysis, Image, Representation and Convolutional neural network.
His most cited work include:
- Person re-identification by Local Maximal Occurrence representation and metric learning (1417 citations)
- Handbook of Face Recognition (1403 citations)
- Markov Random Field Modeling in Image Analysis (1348 citations)
What are the main themes of his work throughout his whole career to date?
Stan Z. Li mainly focuses on Artificial intelligence, Pattern recognition, Computer vision, Facial recognition system and Face. His work in Artificial intelligence addresses subjects such as Machine learning, which are connected to disciplines such as Benchmark. His Pattern recognition study integrates concerns from other disciplines, such as Contextual image classification, Subspace topology and Feature.
His work on Computer vision is being expanded to include thematically relevant topics such as Robustness. His Facial recognition system research focuses on Biometrics and how it relates to Data science. The study incorporates disciplines such as Representation, Modality, Image and Deep learning in addition to Face.
He most often published in these fields:
- Artificial intelligence (80.00%)
- Pattern recognition (51.13%)
- Computer vision (37.36%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (80.00%)
- Facial recognition system (38.68%)
- Face (26.04%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Facial recognition system, Face, Pattern recognition and Machine learning. Stan Z. Li works mostly in the field of Artificial intelligence, limiting it down to topics relating to Computer vision and, in certain cases, Robustness. His research in the fields of Anti spoofing overlaps with other disciplines such as Modalities.
He has researched Face in several fields, including Modality, Image and Code. His Pattern recognition research is multidisciplinary, incorporating perspectives in RGB color model, False positive paradox and Margin. His study in Machine learning is interdisciplinary in nature, drawing from both Perspective and Generalization.
Between 2018 and 2021, his most popular works were:
- Face Alignment in Full Pose Range: A 3D Total Solution (156 citations)
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (128 citations)
- Selective Refinement Network for High Performance Face Detection (56 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
Stan Z. Li spends much of his time researching Artificial intelligence, Face, Machine learning, Pattern recognition and Facial recognition system. His Artificial intelligence research is multidisciplinary, relying on both Generalization and Computer vision. Stan Z. Li interconnects Image and Code in the investigation of issues within Face.
His Machine learning research includes elements of Biometrics, Graph, Graph and Benchmark. His Pattern recognition research incorporates themes from Margin and Cluster analysis. His research investigates the connection between Facial recognition system and topics such as Spoofing attack that intersect with issues in Attack model, Replay attack and RGB color model.
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.
