What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Operating system
His primary scientific interests are in Artificial intelligence, Pattern recognition, Visualization, Data mining and Contextual image classification.
His Artificial intelligence research is multidisciplinary, incorporating elements of Machine learning and Computer vision.
His Pattern recognition research focuses on subjects like Image, which are linked to Consistency, Sparse approximation, Selection, Tracking and Process.
The concepts of his Visualization study are interwoven with issues in Classifier, Discriminative model, Knowledge extraction and Kernel.
His Data mining study combines topics in areas such as OPTICS algorithm, Scalability, Cluster analysis, Semantic gap and Key.
His Feature extraction research includes elements of Image processing, Semantics and Image segmentation.
His most cited work include:
- Automatic image segmentation by integrating color-edge extraction and seeded region growing (495 citations)
- Multi-modal Factorized Bilinear Pooling with Co-attention Learning for Visual Question Answering (215 citations)
- iPrivacy: Image Privacy Protection by Identifying Sensitive Objects via Deep Multi-Task Learning (214 citations)
What are the main themes of his work throughout his whole career to date?
Jianping Fan mainly focuses on Artificial intelligence, Pattern recognition, Information retrieval, Machine learning and Computer vision.
His study in Classifier, Contextual image classification, Discriminative model, Feature extraction and Visualization is done as part of Artificial intelligence.
His work carried out in the field of Feature extraction brings together such families of science as Boosting and Feature.
His Pattern recognition study incorporates themes from Image, Automatic image annotation and Cluster analysis.
Jianping Fan has researched Information retrieval in several fields, including Semantics, Multimedia, Web page and Image retrieval.
His research integrates issues of Multi-task learning and Data mining in his study of Machine learning.
He most often published in these fields:
- Artificial intelligence (59.73%)
- Pattern recognition (34.13%)
- Information retrieval (19.11%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (59.73%)
- Pattern recognition (34.13%)
- Discriminative model (12.29%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Pattern recognition, Discriminative model, Machine learning and Deep learning.
His study in Convolutional neural network, Visualization, Classifier, Feature extraction and Contextual image classification falls under the purview of Artificial intelligence.
His studies deal with areas such as Task analysis, Knowledge extraction and Semantic gap as well as Visualization.
The various areas that he examines in his Classifier study include Information retrieval and Image sharing.
Jianping Fan interconnects Artificial neural network, Image, Feature and Cluster analysis in the investigation of issues within Pattern recognition.
His research in Machine learning intersects with topics in Multi-task learning, Ontology, Data mining and Visual recognition.
Between 2016 and 2021, his most popular works were:
- Multi-modal Factorized Bilinear Pooling with Co-attention Learning for Visual Question Answering (215 citations)
- iPrivacy: Image Privacy Protection by Identifying Sensitive Objects via Deep Multi-Task Learning (214 citations)
- Beyond Bilinear: Generalized Multimodal Factorized High-Order Pooling for Visual Question Answering (209 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Operating system
Jianping Fan mostly deals with Artificial intelligence, Machine learning, Pattern recognition, Classifier and Visualization.
His research on Artificial intelligence frequently connects to adjacent areas such as Bilinear interpolation.
His Machine learning research is multidisciplinary, relying on both Multi-task learning, Object detection, Segmentation and Data mining.
His Pattern recognition research includes themes of Margin, Backpropagation and Feature.
His Classifier research is multidisciplinary, incorporating perspectives in Text mining, Embedding, Deep learning and Information retrieval.
The study incorporates disciplines such as Artificial neural network and Mixture model in addition to Visualization.
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.
