What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Artificial intelligence, Pattern recognition, Contextual image classification, Cognitive neuroscience of visual object recognition and Computer vision are his primary areas of study.
His research investigates the connection between Artificial intelligence and topics such as Machine learning that intersect with issues in Benchmark.
His research investigates the connection with Pattern recognition and areas like Object which intersect with concerns in Automatic image annotation.
His Contextual image classification study incorporates themes from Question answering, WordNet, Natural language processing and Visual reasoning.
As a part of the same scientific study, Li-Jia Li usually deals with the WordNet, concentrating on Ontology and frequently concerns with Image retrieval.
His research in Cognitive neuroscience of visual object recognition focuses on subjects like Image, which are connected to Representation, Semantic feature and Graphical model.
His most cited work include:
- ImageNet: A large-scale hierarchical image database (22839 citations)
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations (1730 citations)
- Progressive Neural Architecture Search (842 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Machine learning, Pattern recognition, Object and Computer vision.
His study in Artificial intelligence concentrates on Object detection, Cognitive neuroscience of visual object recognition, Contextual image classification, Convolutional neural network and Training set.
The Contextual image classification study combines topics in areas such as WordNet, Feature detection, Graphical model and Image retrieval, Automatic image annotation.
His study on Artificial neural network and Leverage is often connected to Thoracic disease and Scheme as part of broader study in Machine learning.
The study incorporates disciplines such as Image, Noise and Feature in addition to Pattern recognition.
His Information retrieval study integrates concerns from other disciplines, such as Image based and The Internet.
He most often published in these fields:
- Artificial intelligence (71.01%)
- Machine learning (31.88%)
- Pattern recognition (28.99%)
What were the highlights of his more recent work (between 2017-2019)?
- Artificial intelligence (71.01%)
- Pattern recognition (28.99%)
- Artificial neural network (10.14%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Pattern recognition, Artificial neural network, Object detection and Theoretical computer science.
In Artificial intelligence, Li-Jia Li works on issues like Machine learning, which are connected to Annotation.
The various areas that Li-Jia Li examines in his Pattern recognition study include Image, Similarity, Image retrieval and Generative grammar, Generative model.
Li-Jia Li has included themes like Contextual image classification, Embedding, Representation and Categorization in his Image retrieval study.
He has researched Artificial neural network in several fields, including Computer engineering and Benchmark.
His Visualization study combines topics in areas such as Question answering, Information retrieval, Metadata and Knowledge extraction.
Between 2017 and 2019, his most popular works were:
- Progressive Neural Architecture Search (842 citations)
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices (510 citations)
- MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels (320 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, Artificial neural network, Leverage, Computer engineering and Speedup.
He frequently studies issues relating to Machine learning and Artificial intelligence.
Machine learning is frequently linked to Benchmark in his study.
Li-Jia Li is interested in Overfitting, which is a field of Artificial neural network.
His Leverage study combines topics from a wide range of disciplines, such as Annotation, Mobile device and Medical imaging.
His Computer engineering research is multidisciplinary, relying on both Pixel and Compression.
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.
