What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
His main research concerns Artificial intelligence, Hash function, Machine learning, Data mining and Pattern recognition.
The Hash function study combines topics in areas such as Binary code, Theoretical computer science and Search engine indexing.
In general Machine learning study, his work on Regularization, Artificial neural network and Collaborative filtering often relates to the realm of Personalization, thereby connecting several areas of interest.
His research in Data mining intersects with topics in Semi-supervised learning and Training set.
His studies deal with areas such as Data point, Quantization and Categorization as well as Pattern recognition.
His research integrates issues of Dynamic perfect hashing, Universal hashing and Locality-sensitive hashing in his study of Feature hashing.
His most cited work include:
- A Survey on Learning to Hash (485 citations)
- Inter-media hashing for large-scale retrieval from heterogeneous data sources (389 citations)
- Hashing for Similarity Search: A Survey (364 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, Hash function and Binary code.
Artificial intelligence is closely attributed to Computer vision in his research.
Jingkuan Song has researched Pattern recognition in several fields, including Artificial neural network, Embedding and Deep learning.
His work focuses on many connections between Machine learning and other disciplines, such as Training set, that overlap with his field of interest in Semi-supervised learning.
In his work, Nearest neighbor search is strongly intertwined with Theoretical computer science, which is a subfield of Hash function.
His study in Binary code is interdisciplinary in nature, drawing from both Hamming space and Algorithm, Quantization.
He most often published in these fields:
- Artificial intelligence (66.25%)
- Pattern recognition (30.00%)
- Machine learning (26.25%)
What were the highlights of his more recent work (between 2020-2021)?
- Artificial intelligence (66.25%)
- Face aging (1.88%)
- Rejuvenation (1.88%)
In recent papers he was focusing on the following fields of study:
Jingkuan Song mainly investigates Artificial intelligence, Face aging, Rejuvenation, Adversarial system and Pattern recognition.
The various areas that Jingkuan Song examines in his Artificial intelligence study include Hash function, Predicate and Natural language processing.
His work deals with themes such as Binary code, Modality, Similarity, Machine learning and Big data, which intersect with Hash function.
His work deals with themes such as Computer security, Code and Boosting, which intersect with Adversarial system.
His studies deal with areas such as Autoencoder, Relation and Image retrieval as well as Pattern recognition.
His work carried out in the field of Feature brings together such families of science as Image, Natural language, Task and Set.
Between 2020 and 2021, his most popular works were:
- Push & Pull: Transferable Adversarial Examples With Attentive Attack (0 citations)
- EvoGAN: an evolutionary GAN for face aging and rejuvenation (0 citations)
- Staircase Sign Method for Boosting Adversarial Attacks. (0 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Jingkuan Song mostly deals with Adversarial system, Computer security, Push pull, Face aging and Transformation.
His Adversarial system study combines topics in areas such as Algorithm, Boosting and Code.
His Face aging studies intersect with other subjects such as Construct and Rejuvenation.
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.
