What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Machine learning, Convolutional neural network and Feature extraction.
His study ties his expertise on Computer vision together with the subject of Artificial intelligence.
His Pattern recognition study integrates concerns from other disciplines, such as Regularization and Generative grammar.
His Machine learning research includes themes of Image, Inference and State.
The Convolutional neural network study combines topics in areas such as Pose and Crowd analysis.
His biological study spans a wide range of topics, including Text mining, Histogram and Relevance feedback.
His most cited work include:
- StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks (1197 citations)
- Cross-scene crowd counting via deep convolutional neural networks (715 citations)
- Saliency detection by multi-context deep learning (689 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Pattern recognition, Computer vision, Feature and Image.
Hongsheng Li frequently studies issues relating to Machine learning and Artificial intelligence.
His study on Feature extraction is often connected to Process as part of broader study in Pattern recognition.
His work on Object, Video tracking, Depth map and Monocular as part of his general Computer vision study is frequently connected to Frame, thereby bridging the divide between different branches of science.
His Feature research is multidisciplinary, relying on both Pyramid, Embedding, Representation and Feature learning.
His Image study integrates concerns from other disciplines, such as Variation, Key, Discriminative model and Natural language processing.
He most often published in these fields:
- Artificial intelligence (87.35%)
- Pattern recognition (39.53%)
- Computer vision (24.90%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (87.35%)
- Pattern recognition (39.53%)
- Image (19.76%)
In recent papers he was focusing on the following fields of study:
Hongsheng Li spends much of his time researching Artificial intelligence, Pattern recognition, Image, Computer vision and Feature.
Hongsheng Li focuses mostly in the field of Artificial intelligence, narrowing it down to topics relating to Machine learning and, in certain cases, Contextual image classification.
His work in the fields of Pattern recognition, such as Discriminative model, overlaps with other areas such as Process.
His studies in Image integrate themes in fields like Generalization and Robustness.
Hongsheng Li has included themes like Embedding and Deep learning in his Computer vision study.
His research in Feature intersects with topics in Pixel and Voxel.
Between 2019 and 2021, his most popular works were:
- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection (84 citations)
- From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network. (66 citations)
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (62 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
His primary areas of study are Artificial intelligence, Object detection, Computer vision, Pattern recognition and Code.
His work investigates the relationship between Artificial intelligence and topics such as Machine learning that intersect with problems in Training set.
The Object detection study combines topics in areas such as Minimum bounding box and Transformer.
Hongsheng Li focuses mostly in the field of Computer vision, narrowing it down to matters related to Lidar and, in some cases, Depth map, Projection and Map projection.
His work carried out in the field of Pattern recognition brings together such families of science as Generalization and Noise.
His Code study combines topics in areas such as Artificial neural network, Cognitive neuroscience of visual object recognition and Contextual image classification.
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.
