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, Convolutional neural network, Computer vision and Machine learning are his primary areas of study.
His Artificial intelligence study focuses mostly on Parsing, Artificial neural network, Feature learning, Feature extraction and Object detection.
His studies in Pattern recognition integrate themes in fields like Matching, Pixel, Image and Feature.
His Convolutional neural network research is multidisciplinary, relying on both RGB color model and Context model.
His work on Image processing as part of general Computer vision study is frequently linked to Clothing, therefore connecting diverse disciplines of science.
In the subject of general Machine learning, his work in Deep learning is often linked to Structure, Consistency and Active learning, thereby combining diverse domains of study.
His most cited work include:
- NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results (555 citations)
- Deep feature learning with relative distance comparison for person re-identification (497 citations)
- Is Faster R-CNN Doing Well for Pedestrian Detection? (473 citations)
What are the main themes of his work throughout his whole career to date?
Liang Lin mainly investigates Artificial intelligence, Pattern recognition, Computer vision, Machine learning and Convolutional neural network.
As part of his studies on Artificial intelligence, he often connects relevant areas like Graph.
His Pattern recognition research includes themes of Object detection and Feature.
His Machine learning study incorporates themes from Adversarial system, Classifier, Robustness and Benchmark.
Liang Lin has included themes like Pascal and Deep learning in his Convolutional neural network study.
His Artificial neural network research includes elements of Feature and Pose.
He most often published in these fields:
- Artificial intelligence (89.37%)
- Pattern recognition (40.62%)
- Computer vision (25.21%)
What were the highlights of his more recent work (between 2020-2021)?
- Artificial intelligence (89.37%)
- Natural language processing (10.21%)
- Representation (9.17%)
In recent papers he was focusing on the following fields of study:
Liang Lin spends much of his time researching Artificial intelligence, Natural language processing, Representation, Question answering and Feature.
His work deals with themes such as Machine learning and Pattern recognition, which intersect with Artificial intelligence.
Many of his research projects under Pattern recognition are closely connected to Focus with Focus, tying the diverse disciplines of science together.
In the field of Natural language processing, his study on Parsing overlaps with subjects such as Structure.
His Representation study integrates concerns from other disciplines, such as Context, Key and Closed captioning.
His Feature study combines topics from a wide range of disciplines, such as Bernoulli distribution, Discriminative model, Outlier and Similarity.
Between 2020 and 2021, his most popular works were:
- Interpretable Visual Question Answering by Reasoning on Dependency Trees (9 citations)
- Weakly Supervised Person Re-ID: Differentiable Graphical Learning and a New Benchmark (2 citations)
- Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval. (1 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His main research concerns Artificial intelligence, Natural language processing, Structure, Graph and Feature learning.
Liang Lin undertakes interdisciplinary study in the fields of Artificial intelligence and Action recognition through his works.
His studies deal with areas such as Context, Contrast, Representation, Snippet and Frame as well as Graph.
His work investigates the relationship between Visualization and topics such as Parsing that intersect with problems in Question answering and Artificial neural network.
The Motion study combines topics in areas such as Deep learning, Transformer, Relation and Pattern recognition.
The concepts of his Data set study are interwoven with issues in Graphical model, Machine learning, Image, Benchmark and Supervised learning.
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.
