What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
His primary areas of study are Artificial intelligence, Pattern recognition, Feature extraction, Feature and Machine learning.
His Computer vision research extends to the thematically linked field of Artificial intelligence.
His work on Nonlinear dimensionality reduction is typically connected to Graph theory as part of general Pattern recognition study, connecting several disciplines of science.
His Feature extraction research includes themes of Point cloud, Autoencoder and Neural coding.
His Feature research focuses on subjects like Image, which are linked to Semantics.
His Image retrieval study incorporates themes from Relevance and Search engine.
His most cited work include:
- Multimodal Deep Autoencoder for Human Pose Recovery (379 citations)
- Click Prediction for Web Image Reranking Using Multimodal Sparse Coding (375 citations)
- Adaptive Hypergraph Learning and its Application in Image Classification (299 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Pattern recognition, Machine learning, Computer vision and Discriminative model.
His is involved in several facets of Artificial intelligence study, as is seen by his studies on Feature extraction, Deep learning, Feature, Convolutional neural network and Classifier.
His Feature extraction research is multidisciplinary, relying on both Autoencoder and Neural coding.
The Pattern recognition study combines topics in areas such as Hypergraph, Subspace topology, Contextual image classification, Pairwise comparison and Image retrieval.
His work on Artificial neural network as part of his general Machine learning study is frequently connected to Multi-task learning, thereby bridging the divide between different branches of science.
Within one scientific family, Jun Yu focuses on topics pertaining to Feature vector under Computer vision, and may sometimes address concerns connected to Search engine, Animation and Cluster analysis.
He most often published in these fields:
- Artificial intelligence (82.93%)
- Pattern recognition (45.12%)
- Machine learning (27.44%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (82.93%)
- Machine learning (27.44%)
- Discriminative model (21.34%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Discriminative model, Pattern recognition and Hash function.
His research investigates the connection with Artificial intelligence and areas like Computer vision which intersect with concerns in Range.
His work in Machine learning tackles topics such as Representation which are related to areas like Similarity.
His research in Discriminative model intersects with topics in Contextual image classification, Subspace topology and Natural language processing.
Jun Yu combines subjects such as Object detector and Predicate with his study of Pattern recognition.
The various areas that Jun Yu examines in his Feature extraction study include Text mining and Translation, Image translation.
Between 2019 and 2021, his most popular works were:
- Spatial Pyramid-Enhanced NetVLAD With Weighted Triplet Loss for Place Recognition (126 citations)
- Multimodal Transformer With Multi-View Visual Representation for Image Captioning (79 citations)
- SPRNet: Single-Pixel Reconstruction for One-Stage Instance Segmentation (25 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His primary areas of investigation include Artificial intelligence, Pattern recognition, Feature extraction, Question answering and Encoder.
His biological study spans a wide range of topics, including Machine learning and Computer vision.
His Pattern recognition research is multidisciplinary, incorporating perspectives in Contextual image classification, Linear regression and Projection.
His research investigates the connection between Feature extraction and topics such as Discriminative model that intersect with problems in Theoretical computer science and Embedding.
His research in Question answering focuses on subjects like Natural language, which are connected to Knowledge extraction, Semantic reasoner, Inference engine and Human–computer interaction.
His studies deal with areas such as Pyramid, Deep learning and Pyramid as well as Artificial neural network.
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.
