What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
Slobodan Ilic mainly investigates Artificial intelligence, Computer vision, Object detection, Pattern recognition and Pose.
His study in Robustness, Feature extraction, Point cloud, Deep learning and Reprojection error is done as part of Artificial intelligence.
His Robustness research incorporates elements of Pixel and Probabilistic logic.
His biological study spans a wide range of topics, including Surface, Prior probability and Missing data.
His Pattern recognition study incorporates themes from Pairwise comparison, Face, Structure from motion and Bundle adjustment.
His study in Pose is interdisciplinary in nature, drawing from both RGB color model and Object.
His most cited work include:
- Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes (636 citations)
- Model globally, match locally: Efficient and robust 3D object recognition (501 citations)
- Gradient Response Maps for Real-Time Detection of Textureless Objects (377 citations)
What are the main themes of his work throughout his whole career to date?
Slobodan Ilic focuses on Artificial intelligence, Computer vision, Pose, Pattern recognition and Robustness.
Many of his studies on Computer vision involve topics that are commonly interrelated, such as Surface.
His 3D pose estimation study, which is part of a larger body of work in Pose, is frequently linked to Frame, bridging the gap between disciplines.
His work carried out in the field of Pattern recognition brings together such families of science as Cognitive neuroscience of visual object recognition and Representation.
His Robustness research is multidisciplinary, incorporating perspectives in Video tracking, Pixel and Machine learning.
His Object detection study combines topics from a wide range of disciplines, such as Edge detection and Image texture.
He most often published in these fields:
- Artificial intelligence (98.16%)
- Computer vision (77.30%)
- Pose (33.13%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (98.16%)
- Computer vision (77.30%)
- Pose (33.13%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Computer vision, Pose, Object and Image.
His biological study spans a wide range of topics, including Point and Pattern recognition.
Computer vision and Artificial neural network are commonly linked in his work.
His Pose research is multidisciplinary, relying on both Object detection, MNIST database, Deep learning and Robustness.
His study in Object detection is interdisciplinary in nature, drawing from both Embedding and Discriminative model.
His Object research focuses on Link and how it connects with Homogeneous space.
Between 2018 and 2021, his most popular works were:
- DPOD: 6D Pose Object Detector and Refiner (93 citations)
- 3D Local Features for Direct Pairwise Registration (40 citations)
- DPOD: Dense 6D Pose Object Detector in RGB images (32 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
His primary areas of investigation include Pose, Artificial intelligence, Computer vision, Deep learning and RGB color model.
His Pose study integrates concerns from other disciplines, such as Object, Object detection, Image and Robustness.
His Object research incorporates themes from Symmetry, Normalization, Link and Rotation.
His studies in Robustness integrate themes in fields like MNIST database, Machine learning and Decoding methods.
His study in the fields of Feature extraction and Matching under the domain of Artificial intelligence overlaps with other disciplines such as Local reference frame, Scheme and Focus.
His research in Feature extraction intersects with topics in Artificial neural network and Quaternion.
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.
