What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Statistics
The scientist’s investigation covers issues in Artificial intelligence, Computer vision, Pattern recognition, Gaze and Particle filter.
In his study, Gesture recognition is inextricably linked to Speech recognition, which falls within the broad field of Artificial intelligence.
His Computer vision study combines topics in areas such as Leverage and Markov chain Monte Carlo.
His Pattern recognition research incorporates themes from Contextual image classification, Probabilistic latent semantic analysis and Data mining.
His Gaze research is multidisciplinary, relying on both Cognitive psychology, Set, Prior probability, Visual attention and RGB color model.
His Feature extraction course of study focuses on Machine learning and Semantics.
His most cited work include:
- Robust multiresolution estimation of parametric motion models (536 citations)
- Modeling scenes with local descriptors and latent aspects (338 citations)
- Text detection and recognition in images and video frames (251 citations)
What are the main themes of his work throughout his whole career to date?
Jean-Marc Odobez spends much of his time researching Artificial intelligence, Computer vision, Pattern recognition, Speech recognition and Pose.
Jean-Marc Odobez combines topics linked to Machine learning with his work on Artificial intelligence.
Jean-Marc Odobez has researched Computer vision in several fields, including Head and Robustness.
In his research on the topic of Pattern recognition, Shape context is strongly related with Histogram.
His Speech recognition research includes themes of Humanoid robot, Face and Cluster analysis.
His studies in Pose integrate themes in fields like Convolutional neural network and Hidden Markov model.
He most often published in these fields:
- Artificial intelligence (82.40%)
- Computer vision (45.20%)
- Pattern recognition (33.20%)
What were the highlights of his more recent work (between 2015-2021)?
- Artificial intelligence (82.40%)
- Computer vision (45.20%)
- Pattern recognition (33.20%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Computer vision, Pattern recognition, Convolutional neural network and Gaze.
Artificial intelligence and Machine learning are commonly linked in his work.
He studies 3D pose estimation which is a part of Computer vision.
His study in Pattern recognition is interdisciplinary in nature, drawing from both Artificial neural network, Image, Noise and Adaptation.
His Convolutional neural network research integrates issues from Crowdsourcing, Feature extraction and Feature.
His biological study spans a wide range of topics, including Landmark, Eye tracking and Coding.
Between 2015 and 2021, his most popular works were:
- Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition (247 citations)
- Deep Neural Networks for Multiple Speaker Detection and Localization (67 citations)
- Gaze Estimation in the 3D Space Using RGB-D Sensors (43 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Statistics
Jean-Marc Odobez focuses on Artificial intelligence, Computer vision, Gaze, Face and Pose.
His Artificial intelligence research incorporates elements of Machine learning and Pattern recognition.
His work in the fields of Pattern recognition, such as Discriminative model, intersects with other areas such as Process.
His Computer vision study frequently links to related topics such as Human–computer interaction.
His Gaze study combines topics from a wide range of disciplines, such as Calibration, Landmark, Social cue and Coding.
In Pose, Jean-Marc Odobez works on issues like 3D reconstruction, which are connected to Eye tracking, Head and Natural interaction.
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.
