What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Artificial intelligence, Machine learning, Support vector machine, Discriminative model and Pattern recognition are her primary areas of study.
Her work on Artificial intelligence is being expanded to include thematically relevant topics such as Computer vision.
Her work deals with themes such as Classifier and Video tracking, which intersect with Machine learning.
As part of one scientific family, Barbara Caputo deals mainly with the area of Support vector machine, narrowing it down to issues related to the Material classification, and often Markov random field and Scale variation.
While the research belongs to areas of Discriminative model, Barbara Caputo spends her time largely on the problem of Image retrieval, intersecting her research to questions surrounding Cognitive models of information retrieval.
Her Pattern recognition research includes themes of Contextual image classification and 3D single-object recognition.
Her most cited work include:
- Recognizing human actions: a local SVM approach (2910 citations)
- On the Significance of Real‐World Conditions for Material Classification (264 citations)
- Electromyography data for non-invasive naturally-controlled robotic hand prostheses (246 citations)
What are the main themes of her work throughout her whole career to date?
Barbara Caputo mostly deals with Artificial intelligence, Machine learning, Pattern recognition, Support vector machine and Robot.
Her research links Computer vision with Artificial intelligence.
The Machine learning study combines topics in areas such as Classifier, Segmentation and Benchmark.
The Feature extraction and Kernel method research she does as part of her general Pattern recognition study is frequently linked to other disciplines of science, such as Domain adaptation, therefore creating a link between diverse domains of science.
Her biological study spans a wide range of topics, including Kernel and Automatic image annotation.
Her Robot research incorporates elements of Robustness and Human–computer interaction.
She most often published in these fields:
- Artificial intelligence (87.83%)
- Machine learning (50.57%)
- Pattern recognition (22.05%)
What were the highlights of her more recent work (between 2018-2021)?
- Artificial intelligence (87.83%)
- Machine learning (50.57%)
- Deep learning (9.51%)
In recent papers she was focusing on the following fields of study:
Barbara Caputo focuses on Artificial intelligence, Machine learning, Deep learning, Benchmark and Human–computer interaction.
In her research, she undertakes multidisciplinary study on Artificial intelligence and Domain adaptation.
Barbara Caputo regularly ties together related areas like Image in her Machine learning studies.
Her Benchmark research is multidisciplinary, incorporating elements of Isolation and Object detection.
Her research integrates issues of Psychophysics and Eye tracking in her study of Human–computer interaction.
Her Adaptation study which covers Feature that intersects with Pattern recognition.
Between 2018 and 2021, her most popular works were:
- Domain Generalization by Solving Jigsaw Puzzles (167 citations)
- Domain Generalization by Solving Jigsaw Puzzles. (29 citations)
- AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs (28 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Artificial neural network
Her main research concerns Artificial intelligence, Cognitive neuroscience of visual object recognition, Human–computer interaction, Machine learning and Deep learning.
Barbara Caputo incorporates Artificial intelligence and Domain adaptation in her studies.
Her Cognitive neuroscience of visual object recognition research is multidisciplinary, relying on both Supervised learning and Unsupervised learning.
Her studies in Human–computer interaction integrate themes in fields like Eye tracking and Gaze.
Her work in Categorization addresses issues such as RGB color model, which are connected to fields such as Relation and Pattern recognition.
Her Visualization research is multidisciplinary, incorporating perspectives in Data modeling, Data point and Feature.
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.
