What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
His primary areas of study are Artificial intelligence, Pattern recognition, Computer vision, Feature extraction and Contextual image classification.
His Pooling, RGB color model and Parsing study in the realm of Artificial intelligence interacts with subjects such as Scale and Pipeline.
Yuanqing Lin is studying Convolutional neural network, which is a component of Pattern recognition.
In general Computer vision study, his work on Pixel, Cognitive neuroscience of visual object recognition and Segmentation often relates to the realm of Viola–Jones object detection framework and Object-class detection, thereby connecting several areas of interest.
Yuanqing Lin works mostly in the field of Feature extraction, limiting it down to topics relating to Training set and, in certain cases, Robustness, Algorithm, Image retrieval and Triplet loss.
In his study, which falls under the umbrella issue of Contextual image classification, Support vector machine, Stochastic gradient descent and Machine learning is strongly linked to Classifier.
His most cited work include:
- Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers (391 citations)
- Large-scale image classification: Fast feature extraction and SVM training (293 citations)
- Regionlets for Generic Object Detection (277 citations)
What are the main themes of his work throughout his whole career to date?
Yuanqing Lin mainly focuses on Artificial intelligence, Pattern recognition, Computer vision, Object detection and Convolutional neural network.
His study brings together the fields of Machine learning and Artificial intelligence.
His work carried out in the field of Pattern recognition brings together such families of science as Image and Cognitive neuroscience of visual object recognition.
His work in the fields of Segmentation, Point cloud, Pose and Pixel overlaps with other areas such as Viola–Jones object detection framework.
His Object detection research includes themes of Pascal and Minimum bounding box.
His work in Convolutional neural network covers topics such as Artificial neural network which are related to areas like Pooling.
He most often published in these fields:
- Artificial intelligence (78.08%)
- Pattern recognition (53.42%)
- Computer vision (30.14%)
What were the highlights of his more recent work (between 2015-2018)?
- Artificial intelligence (78.08%)
- Pattern recognition (53.42%)
- Machine learning (20.55%)
In recent papers he was focusing on the following fields of study:
Yuanqing Lin spends much of his time researching Artificial intelligence, Pattern recognition, Machine learning, Convolutional neural network and Discriminative model.
While the research belongs to areas of Artificial intelligence, Yuanqing Lin spends his time largely on the problem of Computer vision, intersecting his research to questions surrounding Robustness.
Particularly relevant to Feature extraction is his body of work in Pattern recognition.
Yuanqing Lin combines subjects such as Algorithm, Triplet loss and Image retrieval with his study of Feature extraction.
Yuanqing Lin usually deals with Machine learning and limits it to topics linked to Contextual image classification and Similarity, Relevance, Representation and Cognitive neuroscience of visual object recognition.
He interconnects Object, Kernel, Artificial neural network and Feature in the investigation of issues within Convolutional neural network.
Between 2015 and 2018, his most popular works were:
- Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers (391 citations)
- Deep Metric Learning with Angular Loss (244 citations)
- The ApolloScape Dataset for Autonomous Driving (232 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
Yuanqing Lin mainly investigates Artificial intelligence, Convolutional neural network, Pattern recognition, Feature extraction and Image retrieval.
In most of his Artificial intelligence studies, his work intersects topics such as Computer vision.
His work on Object, Pose and 3D pose estimation is typically connected to Viola–Jones object detection framework and Object-class detection as part of general Computer vision study, connecting several disciplines of science.
His research in Convolutional neural network intersects with topics in Similarity and Feature.
His Feature extraction research is multidisciplinary, relying on both Pascal and Detector.
His Image retrieval study incorporates themes from Embedding, Representation, Machine learning, Relevance and Contextual image classification.
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.
