What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Maja Pantic focuses on Artificial intelligence, Facial expression, Facial recognition system, Computer vision and Pattern recognition.
Her Artificial intelligence study typically links adjacent topics like Machine learning.
Her Facial expression study combines topics from a wide range of disciplines, such as Facial muscles, Affective computing, Speech recognition and Affect.
Her research integrates issues of Field, Feature extraction, Protocol and Gesture recognition in her study of Facial recognition system.
She interconnects Graph and Set in the investigation of issues within Computer vision.
Her Support vector machine study in the realm of Pattern recognition connects with subjects such as Gaussian process.
Her most cited work include:
- A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions (2221 citations)
- Automatic analysis of facial expressions: the state of the art (1568 citations)
- Web-based database for facial expression analysis (778 citations)
What are the main themes of her work throughout her whole career to date?
Artificial intelligence, Pattern recognition, Facial expression, Speech recognition and Computer vision are her primary areas of study.
Artificial intelligence is frequently linked to Machine learning in her study.
Her study in Facial expression is interdisciplinary in nature, drawing from both Valence, Affect, Facial muscles, Affective computing and Gesture.
Her research in Affective computing intersects with topics in Emotion recognition, Cognitive psychology and Multimedia.
Maja Pantic has included themes like Feature, End-to-end principle, Modality, Joint and Laughter in her Speech recognition study.
Her Facial recognition system research includes elements of Facial Action Coding System and Gesture recognition.
She most often published in these fields:
- Artificial intelligence (67.37%)
- Pattern recognition (31.49%)
- Facial expression (31.49%)
What were the highlights of her more recent work (between 2018-2021)?
- Artificial intelligence (67.37%)
- Speech recognition (25.76%)
- Deep learning (9.35%)
In recent papers she was focusing on the following fields of study:
Her primary areas of investigation include Artificial intelligence, Speech recognition, Deep learning, Pattern recognition and Face.
Maja Pantic combines subjects such as Machine learning and Computer vision with her study of Artificial intelligence.
Her Speech recognition research includes themes of End-to-end principle, Facial expression and Joint.
Her work investigates the relationship between Facial expression and topics such as Synchronization that intersect with problems in Process.
Her research integrates issues of Block, Receptive field, Kernel and Convolution in her study of Pattern recognition.
The study of Feature extraction is intertwined with the study of Facial recognition system in a number of ways.
Between 2018 and 2021, her most popular works were:
- Automatic Analysis of Facial Actions: A Survey (134 citations)
- TensorLy: tensor learning in python (96 citations)
- Realistic Speech-Driven Facial Animation with GANs (52 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Operating system
Maja Pantic mainly focuses on Artificial intelligence, Deep learning, Speech recognition, Artificial neural network and Pattern recognition.
Maja Pantic focuses mostly in the field of Artificial intelligence, narrowing it down to matters related to Computer vision and, in some cases, Encoder.
The various areas that Maja Pantic examines in her Deep learning study include Geometry, Active shape model, Visual Objects and Geometric transformation.
Her studies in Speech recognition integrate themes in fields like End-to-end principle, Computer graphics, Synchronization and Component.
Her Artificial neural network study integrates concerns from other disciplines, such as Pose and Tensor.
Her Pattern recognition research is multidisciplinary, incorporating perspectives in Separable space, Convolution and Kernel.
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.
