What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
Aude Oliva spends much of her time researching Artificial intelligence, Computer vision, Cognitive neuroscience of visual object recognition, Categorization and Object.
Artificial intelligence and Pattern recognition are frequently intertwined in her study.
As part of her studies on Computer vision, Aude Oliva frequently links adjacent subjects like Representation.
The various areas that Aude Oliva examines in her Cognitive neuroscience of visual object recognition study include Context, Form perception and Magnetoencephalography.
Her Categorization research incorporates themes from Visual perception, Visual processing, Perception, Scene statistics and Communication.
The Object study combines topics in areas such as Rapid serial visual presentation, Speech recognition, Visual cortex and Robustness.
Her most cited work include:
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope (5467 citations)
- Learning Deep Features for Discriminative Localization (3220 citations)
- Learning Deep Features for Scene Recognition using Places Database (2129 citations)
What are the main themes of her work throughout her whole career to date?
Aude Oliva mostly deals with Artificial intelligence, Computer vision, Perception, Pattern recognition and Communication.
Her work deals with themes such as Machine learning and Scene statistics, which intersect with Artificial intelligence.
Her Computer vision research is multidisciplinary, relying on both Context, Visual search and Visualization.
She works mostly in the field of Perception, limiting it down to topics relating to Cognitive psychology and, in certain cases, Visual memory and Long-term memory, as a part of the same area of interest.
Her work in Pattern recognition covers topics such as Human brain which are related to areas like Visual cortex.
Her Cognitive neuroscience of visual object recognition research is multidisciplinary, incorporating perspectives in Form perception, Visual system and Human visual system model.
She most often published in these fields:
- Artificial intelligence (63.70%)
- Computer vision (30.82%)
- Perception (16.10%)
What were the highlights of her more recent work (between 2018-2021)?
- Artificial intelligence (63.70%)
- Pattern recognition (16.10%)
- Machine learning (7.88%)
In recent papers she was focusing on the following fields of study:
Aude Oliva focuses on Artificial intelligence, Pattern recognition, Machine learning, Object and Key.
Her research on Artificial intelligence frequently links to adjacent areas such as Natural language processing.
Her studies in Pattern recognition integrate themes in fields like Feature, Visual cortex and Human brain.
Her Interpretability study in the realm of Machine learning connects with subjects such as Property.
Object is a primary field of her research addressed under Computer vision.
Her research investigates the connection between Convolutional neural network and topics such as Categorization that intersect with problems in Artificial neural network and Visual memory.
Between 2018 and 2021, her most popular works were:
- What Do Different Evaluation Metrics Tell Us About Saliency Models (261 citations)
- Moments in Time Dataset: One Million Videos for Event Understanding (157 citations)
- Interpreting Deep Visual Representations via Network Dissection (108 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Cognition
Artificial intelligence, Visualization, Machine learning, Human brain and Pattern recognition are her primary areas of study.
Her work on Convolutional neural network, Benchmark and Image as part of general Artificial intelligence study is frequently linked to Action recognition and Object, bridging the gap between disciplines.
Her Convolutional neural network research includes elements of Artificial neural network, Image segmentation and Categorization.
Her Visualization research includes themes of Segmentation, DUAL, Affordance, Salience and Feature extraction.
Her work on Interpretability as part of general Machine learning study is frequently linked to Baseline, Causality and Property, therefore connecting diverse disciplines of science.
Her Pattern recognition study integrates concerns from other disciplines, such as Convolution, Key and Fusion.
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.
