What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
The scientist’s investigation covers issues in Artificial intelligence, Pattern recognition, Computer vision, Feature extraction and Electroencephalography.
His research on Artificial intelligence frequently connects to adjacent areas such as Multilinear map.
His studies deal with areas such as Matrix decomposition, Theoretical computer science and Generative model as well as Pattern recognition.
Object detection, Human visual system model, Image, Kadir–Brady saliency detector and Saliency map are among the areas of Computer vision where the researcher is concentrating his efforts.
His research integrates issues of Machine vision, Residual and Salience in his study of Image.
His Feature extraction research incorporates themes from Neurophysiology, Central nervous system, Support vector machine, Signal processing and Wavelet transform.
His most cited work include:
- Saliency Detection: A Spectral Residual Approach (2735 citations)
- Dynamic visual attention: searching for coding length increments (439 citations)
- Bayesian CP Factorization of Incomplete Tensors with Automatic Rank Determination (249 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Pattern recognition, Computer vision, Feature extraction and Image.
Liqing Zhang has researched Artificial intelligence in several fields, including Machine learning, Speech recognition and Electroencephalography.
His research investigates the link between Pattern recognition and topics such as Brain–computer interface that cross with problems in Human–computer interaction.
His research investigates the connection between Computer vision and topics such as Sketch that intersect with issues in Information retrieval.
His study in Feature extraction is interdisciplinary in nature, drawing from both Speaker recognition, Representation, Linear subspace and Feature.
His work in the fields of Composite image filter overlaps with other areas such as Domain.
He most often published in these fields:
- Artificial intelligence (66.91%)
- Pattern recognition (42.55%)
- Computer vision (17.09%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (66.91%)
- Image (13.45%)
- Pattern recognition (42.55%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Image, Pattern recognition, Machine learning and Computer vision.
His Image study combines topics in areas such as Pooling and Harmonization.
His Pattern recognition research incorporates elements of Contextual image classification, Static image and Shot.
He has included themes like Recurrent neural network, Feature extraction, Representation and Projection in his Contextual image classification study.
His work on Discriminative model as part of general Machine learning research is often related to Memory module and Quality, thus linking different fields of science.
His research on Computer vision often connects related areas such as Sequence.
Between 2018 and 2021, his most popular works were:
- DoveNet: Deep Image Harmonization via Domain Verification (17 citations)
- Zero-Shot Learning via Category-Specific Visual-Semantic Mapping and Label Refinement (13 citations)
- Multi-Attribute Transfer via Disentangled Representation. (11 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
Liqing Zhang mostly deals with Artificial intelligence, Image, Pattern recognition, Domain and Machine learning.
His Deep learning, Embedding and Projection study, which is part of a larger body of work in Artificial intelligence, is frequently linked to Merge and Rate of return on a portfolio, bridging the gap between disciplines.
Image is a subfield of Computer vision that he explores.
His work on Inpainting, Enhanced Data Rates for GSM Evolution and Image gradient as part of general Computer vision study is frequently linked to Construct, therefore connecting diverse disciplines of science.
He studies Feature vector, a branch of Pattern recognition.
His work on Discriminative model is typically connected to Memory module as part of general Machine learning study, connecting several disciplines of science.
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.
