What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
His main research concerns Artificial intelligence, Pattern recognition, Computer vision, Object detection and Contextual image classification.
His study in Detector extends to Artificial intelligence with its themes.
The Pattern recognition study combines topics in areas such as Pascal and Feature.
As part of one scientific family, Qixiang Ye deals mainly with the area of Object detection, narrowing it down to issues related to the Feature learning, and often Entropy, Graphical model and Orientation.
His Contextual image classification research incorporates elements of Algorithm and Cognitive neuroscience of visual object recognition.
His study looks at the intersection of Feature extraction and topics like Segmentation with Information retrieval, Text mining and Text detection.
His most cited work include:
- Text Detection and Recognition in Imagery: A Survey (500 citations)
- Fast and robust text detection in images and video frames (298 citations)
- Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification (235 citations)
What are the main themes of his work throughout his whole career to date?
Qixiang Ye focuses on Artificial intelligence, Pattern recognition, Computer vision, Object detection and Object.
Many of his studies on Artificial intelligence involve topics that are commonly interrelated, such as Machine learning.
Qixiang Ye has included themes like Image and Pascal in his Pattern recognition study.
His work on Video tracking, Pixel and Histogram is typically connected to Pedestrian detection as part of general Computer vision study, connecting several disciplines of science.
As a member of one scientific family, Qixiang Ye mostly works in the field of Object, focusing on Benchmark and, on occasion, Algorithm.
Qixiang Ye interconnects Visualization and Image segmentation in the investigation of issues within Feature extraction.
He most often published in these fields:
- Artificial intelligence (85.56%)
- Pattern recognition (51.87%)
- Computer vision (32.62%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (85.56%)
- Pattern recognition (51.87%)
- Object detection (23.53%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Pattern recognition, Object detection, Object and Representation.
His Artificial intelligence study is mostly concerned with Discriminative model, Feature learning, Feature, Benchmark and Convolutional neural network.
His Pattern recognition research focuses on Segmentation in particular.
His Object detection research includes themes of Algorithm and Detector.
His Object study is concerned with Computer vision in general.
His study in the fields of Feature extraction under the domain of Computer vision overlaps with other disciplines such as Pedestrian detection.
Between 2018 and 2021, his most popular works were:
- Towards Optimal Structured CNN Pruning via Generative Adversarial Learning (117 citations)
- FreeAnchor: Learning to Match Anchors for Visual Object Detection (78 citations)
- C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection (75 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His primary areas of study are Artificial intelligence, Pattern recognition, Object detection, Discriminative model and Object.
His study in Feature learning, Representation, Image, Feature and Convolutional neural network is carried out as part of his studies in Artificial intelligence.
His Pattern recognition study combines topics in areas such as Regularization, Categorization, Contextual image classification, Pascal and Visualization.
He focuses mostly in the field of Discriminative model, narrowing it down to matters related to Feature extraction and, in some cases, Cluster analysis.
His Object research is multidisciplinary, incorporating perspectives in Matching, Detector and Benchmark.
His work in the fields of Pixel overlaps with other areas such as Scale.
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.
