What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Junjie Yan mostly deals with Artificial intelligence, Feature extraction, Computer vision, Object detection and Pattern recognition.
In his study, which falls under the umbrella issue of Artificial intelligence, Classifier is strongly linked to Machine learning.
The various areas that Junjie Yan examines in his Feature extraction study include Embedding, Speech recognition and Spotting.
His Object detection research integrates issues from Pedestrian detection, Convolutional neural network, Spoofing attack and Image texture.
His Convolutional neural network study combines topics in areas such as Contextual image classification and Word error rate.
Junjie Yan has included themes like Video tracking, Tracking and Eye tracking in his Deep learning study.
His most cited work include:
- High Performance Visual Tracking with Siamese Region Proposal Network (723 citations)
- Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion (482 citations)
- SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks (397 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, Object detection, Pattern recognition and Machine learning.
His study in Face, Feature extraction, Artificial neural network, Image and Feature is carried out as part of his studies in Artificial intelligence.
His Object, Pixel and Object-class detection study in the realm of Computer vision interacts with subjects such as Electronic equipment and Basis.
His Object detection research incorporates elements of Viola–Jones object detection framework, Pascal, Benchmark, Algorithm and Convolutional neural network.
His work on Discriminative model, Feature vector and Residual neural network as part of general Pattern recognition study is frequently linked to Process, therefore connecting diverse disciplines of science.
The Deep learning, Feature and Support vector machine research he does as part of his general Machine learning study is frequently linked to other disciplines of science, such as Process, therefore creating a link between diverse domains of science.
He most often published in these fields:
- Artificial intelligence (78.26%)
- Computer vision (30.87%)
- Object detection (25.65%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (78.26%)
- Computer vision (30.87%)
- Object detection (25.65%)
In recent papers he was focusing on the following fields of study:
Junjie Yan mainly investigates Artificial intelligence, Computer vision, Object detection, Image and Machine learning.
His Pattern recognition research extends to the thematically linked field of Artificial intelligence.
His work in the fields of Pattern recognition, such as Discriminative model, Feature extraction and Classifier, intersects with other areas such as Scale invariance.
His study in the fields of Image based and Face detection under the domain of Computer vision overlaps with other disciplines such as Electronic equipment.
His studies deal with areas such as Embedding, Bridging, Pascal, Benchmark and Convolutional neural network as well as Object detection.
His biological study deals with issues like Key, which deal with fields such as Hyperparameter and Data-driven.
Between 2019 and 2021, his most popular works were:
- Equalization Loss for Long-Tailed Object Recognition (41 citations)
- BlockQNN: Efficient Block-wise Neural Network Architecture Generation. (40 citations)
- Towards Unified INT8 Training for Convolutional Neural Network (18 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
The scientist’s investigation covers issues in Artificial intelligence, Object detection, Pattern recognition, Machine learning and Pascal.
His work is dedicated to discovering how Artificial intelligence, Computer vision are connected with Pedestrian detection and other disciplines.
His research integrates issues of Quantization and Scale in his study of Object detection.
His biological study spans a wide range of topics, including Margin, Facial recognition system, Face and Rotation.
His Machine learning study integrates concerns from other disciplines, such as Probabilistic logic and Frequency domain.
His Pascal research is multidisciplinary, incorporating perspectives in Pyramid, Segmentation, Deep learning and Hierarchical search.
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.
