What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
His scientific interests lie mostly in Artificial intelligence, Computer vision, Object detection, Pattern recognition and Segmentation.
Artificial intelligence and Line are commonly linked in his work.
His work in the fields of Image segmentation, Matching, Cognitive neuroscience of visual object recognition and Video tracking overlaps with other areas such as Graph theory.
Ramakant Nevatia has researched Object detection in several fields, including Motion detection, Tracking, Inference and Scale-space segmentation.
His Pattern recognition study integrates concerns from other disciplines, such as Boosting, Silhouette, Edge detection and Kernel.
The Segmentation study combines topics in areas such as Markov process, Monte Carlo method, Bayesian probability, Markov chain Monte Carlo and Stereopsis.
His most cited work include:
- Global data association for multi-object tracking using network flows (738 citations)
- Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors (718 citations)
- Linear feature extraction and description (601 citations)
What are the main themes of his work throughout his whole career to date?
Ramakant Nevatia mainly investigates Artificial intelligence, Computer vision, Pattern recognition, Object detection and Segmentation.
His work on Machine learning expands to the thematically related Artificial intelligence.
In his work, Support vector machine is strongly intertwined with Histogram, which is a subfield of Pattern recognition.
His research investigates the connection between Object detection and topics such as Boosting that intersect with issues in Face detection.
His research in Segmentation intersects with topics in Stereopsis, Hidden Markov model and Robustness.
He combines subjects such as Pixel, Markov process and Iterative reconstruction with his study of Image segmentation.
He most often published in these fields:
- Artificial intelligence (90.06%)
- Computer vision (67.40%)
- Pattern recognition (24.31%)
What were the highlights of his more recent work (between 2005-2018)?
- Artificial intelligence (90.06%)
- Computer vision (67.40%)
- Pattern recognition (24.31%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Computer vision, Pattern recognition, Object detection and Feature extraction.
His Artificial intelligence study often links to related topics such as Machine learning.
In the field of Computer vision, his study on Segmentation, Tracking, Object-class detection and Video tracking overlaps with subjects such as Focus.
His work on Unsupervised learning as part of general Pattern recognition study is frequently linked to Frame, bridging the gap between disciplines.
His Object detection study combines topics in areas such as Optical flow, Boosting and Face detection.
The various areas that Ramakant Nevatia examines in his Feature extraction study include Pixel and Information retrieval.
Between 2005 and 2018, his most popular works were:
- Global data association for multi-object tracking using network flows (738 citations)
- Robust Object Tracking by Hierarchical Association of Detection Responses (477 citations)
- Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching (408 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
Ramakant Nevatia focuses on Artificial intelligence, Computer vision, Pattern recognition, Object detection and Discriminative model.
Feature extraction, Classifier, Face detection, Boosting and Tracking are the core of his Artificial intelligence study.
Ramakant Nevatia works mostly in the field of Feature extraction, limiting it down to topics relating to Histogram and, in certain cases, Statistical classification and Normalization, as a part of the same area of interest.
His study in the field of Segmentation, Object-class detection and Video tracking also crosses realms of Initialization.
His Pattern recognition research is multidisciplinary, relying on both Action recognition and Feature.
In his study, Markov process, Sampling, Monte Carlo method and Visibility is inextricably linked to Motion detection, which falls within the broad field of Object detection.
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.
