What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Algorithm
His primary areas of investigation include Computer vision, Artificial intelligence, Algorithm, Search algorithm and Motion estimation.
His Image processing, Image quality and Feature extraction study in the realm of Computer vision connects with subjects such as Distortion.
His work in the fields of Perspective overlaps with other areas such as Radiometry, Human skin and Optical imaging.
The Search algorithm study combines topics in areas such as Computational complexity theory, Motion compensation, Data compression, Motion vector and Speedup.
His Motion estimation research integrates issues from Matching, Binary search algorithm, Beam stack search and Gradient descent.
His study in Binary search algorithm is interdisciplinary in nature, drawing from both Beam search, Interpolation search and Quarter-pixel motion.
His most cited work include:
- A novel four-step search algorithm for fast block motion estimation (1410 citations)
- A novel cross-diamond search algorithm for fast block motion estimation (336 citations)
- Normalized partial distortion search algorithm for block motion estimation (160 citations)
What are the main themes of his work throughout his whole career to date?
Lai-Man Po spends much of his time researching Artificial intelligence, Computer vision, Algorithm, Motion estimation and Pattern recognition.
His work on Data compression, Image quality, Image processing and Convolutional neural network as part of general Artificial intelligence study is frequently connected to Distortion, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
His Algorithm research focuses on Mathematical optimization and how it connects with Rate–distortion theory.
His work deals with themes such as Motion vector, Speedup, Block-matching algorithm and Search algorithm, which intersect with Motion estimation.
His work on Binary search algorithm and Beam stack search as part of general Search algorithm research is often related to Diamond, thus linking different fields of science.
Lai-Man Po focuses mostly in the field of Pattern recognition, narrowing it down to matters related to Image retrieval and, in some cases, Similarity measure.
He most often published in these fields:
- Artificial intelligence (70.20%)
- Computer vision (51.01%)
- Algorithm (42.42%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (70.20%)
- Pattern recognition (23.74%)
- Convolutional neural network (6.06%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Pattern recognition, Convolutional neural network, Computer vision and Deep learning.
Lai-Man Po integrates Artificial intelligence with Process in his research.
His Pattern recognition study combines topics from a wide range of disciplines, such as Artificial neural network, Liveness and Video copy detection.
He has included themes like Activity recognition, Face Presentation, Robustness and Biometrics in his Convolutional neural network study.
In general Computer vision, his work in Image restoration and PenTile matrix family is often linked to Track, Domain and Consistency linking many areas of study.
His research integrates issues of Pooling, Data mining and Feature vector in his study of Image quality.
Between 2017 and 2021, his most popular works were:
- LiveNet: Improving features generalization for face liveness detection using convolution neural networks (40 citations)
- Block-based adaptive ROI for remote photoplethysmography (19 citations)
- AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results (12 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Algorithm
- Computer vision
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Image, Convolutional neural network and Liveness.
His research on Artificial intelligence often connects related areas such as Computer vision.
His work on Feature, Structural similarity, Image resolution and Gamma correction as part of general Computer vision research is frequently linked to Metric, thereby connecting diverse disciplines of science.
His research in Convolutional neural network intersects with topics in Autoencoder, Face Presentation, Classifier, Stereo camera and Robustness.
His work carried out in the field of Face brings together such families of science as Region of interest, Thresholding and Cluster analysis.
His biological study spans a wide range of topics, including Image quality, Convolution, Deep learning and Task.
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.
