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, Machine learning, Computer vision, Pattern recognition and Benchmark.
His study in Data mining extends to Artificial intelligence with its themes.
His Machine learning research incorporates elements of Robust statistics and Content-based image retrieval.
In general Computer vision study, his work on Channel, Color mapping, Color image and Image processing often relates to the realm of Disjoint sets, thereby connecting several areas of interest.
His Pattern recognition study combines topics from a wide range of disciplines, such as Point cloud and Representation.
His work is dedicated to discovering how Feature extraction, Solver are connected with Object and other disciplines.
His most cited work include:
- Image smoothing via L0 gradient minimization (796 citations)
- RMPE: Regional Multi-person Pose Estimation (518 citations)
- Visual Relationship Detection with Language Priors (481 citations)
What are the main themes of his work throughout his whole career to date?
Cewu Lu mainly focuses on Artificial intelligence, Object, Machine learning, Computer vision and Code.
Artificial intelligence is often connected to Pattern recognition in his work.
His biological study spans a wide range of topics, including Semantics, Theoretical computer science and Human–computer interaction.
His studies in Computer vision integrate themes in fields like Robot and Robustness.
His work carried out in the field of Benchmark brings together such families of science as Image and Real-time computing.
His research in Object detection intersects with topics in Feature extraction, Pascal and Convolutional neural network.
He most often published in these fields:
- Artificial intelligence (79.25%)
- Object (29.56%)
- Machine learning (23.90%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (79.25%)
- Object (29.56%)
- Code (19.50%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Object, Code, Computer vision and Machine learning are his primary areas of study.
Cewu Lu performs multidisciplinary study on Artificial intelligence and GRASP in his works.
His study in Object is interdisciplinary in nature, drawing from both Theoretical computer science, Aggregate and Graphics.
Machine learning and Modality are frequently intertwined in his study.
His Deep learning research is multidisciplinary, relying on both Object detection, Information redundancy, Reeb graph and Algorithm.
His Pose research includes themes of RGB color model and Monocular.
Between 2019 and 2021, his most popular works were:
- TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model (23 citations)
- Recursive Social Behavior Graph for Trajectory Prediction (20 citations)
- Detailed 2D-3D Joint Representation for Human-Object Interaction (20 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
Cewu Lu mainly investigates Artificial intelligence, Object, Machine learning, Robustness and Computer vision.
His research on Artificial intelligence frequently connects to adjacent areas such as Task analysis.
Cewu Lu works mostly in the field of Object, limiting it down to topics relating to Graphics and, in certain cases, Data mining, as a part of the same area of interest.
His research in the fields of Leverage overlaps with other disciplines such as Interaction information.
He interconnects Depth map, Polygon mesh and Silhouette in the investigation of issues within Robustness.
In his work, Feature extraction is strongly intertwined with Supervised learning, which is a subfield of Semantics.
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.
