What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Her primary areas of investigation include Artificial intelligence, Pattern recognition, Machine learning, Computer vision and Object.
Her research combines Hash function and Artificial intelligence.
Her studies deal with areas such as Cognitive neuroscience of visual object recognition and Kernel as well as Pattern recognition.
Her research investigates the link between Computer vision and topics such as Convolutional neural network that cross with problems in Robustness, Residual, Reinforcement learning and Inference.
Her Object research includes elements of Ranking, Noise reduction and Training set.
Her Feature extraction research focuses on Visualization and how it connects with Relevance, Relevance feedback and Artificial neural network.
Her most cited work include:
- The pyramid match kernel: discriminative classification with sets of image features (1337 citations)
- Geodesic flow kernel for unsupervised domain adaptation (1293 citations)
- Relative attributes (796 citations)
What are the main themes of her work throughout her whole career to date?
Kristen Grauman mainly investigates Artificial intelligence, Computer vision, Pattern recognition, Machine learning and Object.
Visualization, Image, Cognitive neuroscience of visual object recognition, Convolutional neural network and Segmentation are subfields of Artificial intelligence in which her conducts study.
In general Computer vision, her work in Image segmentation, Object detection, Pixel and Motion is often linked to Frame linking many areas of study.
Kristen Grauman interconnects Histogram and Feature in the investigation of issues within Pattern recognition.
Kristen Grauman works mostly in the field of Machine learning, limiting it down to topics relating to Image retrieval and, in certain cases, Nearest neighbor search, as a part of the same area of interest.
Her Object study combines topics in areas such as Pattern recognition, Training set, Source separation and Reinforcement learning.
She most often published in these fields:
- Artificial intelligence (77.26%)
- Computer vision (31.77%)
- Pattern recognition (27.09%)
What were the highlights of her more recent work (between 2017-2021)?
- Artificial intelligence (77.26%)
- Human–computer interaction (13.38%)
- Computer vision (31.77%)
In recent papers she was focusing on the following fields of study:
Kristen Grauman spends much of her time researching Artificial intelligence, Human–computer interaction, Computer vision, Object and Reinforcement learning.
Her study ties her expertise on Machine learning together with the subject of Artificial intelligence.
Her Human–computer interaction research is multidisciplinary, incorporating elements of Set and Embodied cognition.
As part of one scientific family, Kristen Grauman deals mainly with the area of Computer vision, narrowing it down to issues related to the Robotics, and often RGB color model, Computer graphics and Benchmark.
Her work deals with themes such as Segmentation, Representation and Source separation, which intersect with Object.
Her biological study spans a wide range of topics, including Contrast and Pattern recognition.
Between 2017 and 2021, her most popular works were:
- BlockDrop: Dynamic Inference Paths in Residual Networks (200 citations)
- Learning to Separate Object Sounds by Watching Unlabeled Video (134 citations)
- VizWiz Grand Challenge: Answering Visual Questions from Blind People (132 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
The scientist’s investigation covers issues in Artificial intelligence, Human–computer interaction, Visualization, Object and Reinforcement learning.
Her Artificial intelligence research incorporates themes from Machine learning and Computer vision.
Her research in Machine learning intersects with topics in Embedding and Categorization.
Her Human–computer interaction research is multidisciplinary, relying on both Probabilistic logic, Code and Embodied cognition.
The concepts of her Object study are interwoven with issues in Pixel, Seam carving, Structured prediction, Image retrieval and Pattern recognition.
Her study in Pattern recognition is interdisciplinary in nature, drawing from both Lift and Cognitive neuroscience of visual object recognition.
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.
