What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Computer vision, Image and Object.
His study looks at the relationship between Artificial intelligence and fields such as Machine learning, as well as how they intersect with chemical problems.
His Pattern recognition study deals with Feature intersecting with Global optimization, Sparse image and Matching.
His study in the fields of Iterative reconstruction and Active shape model under the domain of Computer vision overlaps with other disciplines such as Order and Interface.
His Image research incorporates elements of E-commerce, World Wide Web and Presentation.
His work deals with themes such as Feature learning, Convolution and Inference, which intersect with Linear classifier.
His most cited work include:
- Learning Spatiotemporal Features with 3D Convolutional Networks (3945 citations)
- A Closer Look at Spatiotemporal Convolutions for Action Recognition (856 citations)
- Efficient object category recognition using classemes (410 citations)
What are the main themes of his work throughout his whole career to date?
Lorenzo Torresani mainly focuses on Artificial intelligence, Pattern recognition, Computer vision, Machine learning and Object.
His study in Artificial intelligence concentrates on Segmentation, Contextual image classification, Pixel, Categorization and Benchmark.
His study in Linear classifier, Support vector machine, Classifier, Feature extraction and Feature learning is carried out as part of his Pattern recognition studies.
His study brings together the fields of Convolution and Feature learning.
Machine learning is closely attributed to Inference in his research.
His study looks at the relationship between Pose and topics such as Leverage, which overlap with Salient and Speech recognition.
He most often published in these fields:
- Artificial intelligence (77.62%)
- Pattern recognition (32.17%)
- Computer vision (23.78%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (77.62%)
- Machine learning (22.38%)
- Contextual image classification (11.89%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Machine learning, Contextual image classification, Leverage and Speech recognition are his primary areas of study.
His Artificial intelligence research includes elements of Natural language processing, Computer vision and Pattern recognition.
His Pattern recognition study frequently links to other fields, such as Deep learning.
His work on Cluster analysis is typically connected to Modal as part of general Machine learning study, connecting several disciplines of science.
In his work, Pose and Image warping is strongly intertwined with Optical flow, which is a subfield of Leverage.
His work in Benchmark addresses subjects such as Temporal database, which are connected to disciplines such as Inference.
Between 2018 and 2021, his most popular works were:
- Video Classification With Channel-Separated Convolutional Networks (101 citations)
- SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition (57 citations)
- HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization (49 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
His primary areas of investigation include Artificial intelligence, Machine learning, Leverage, Contextual image classification and CLIPS.
His work on Speech recognition expands to the thematically related Artificial intelligence.
His work on Cluster analysis as part of general Machine learning study is frequently linked to Modal, bridging the gap between disciplines.
His Leverage research is multidisciplinary, relying on both Optical flow and Pattern recognition.
His Pattern recognition study focuses on Feature extraction in particular.
His CLIPS study combines topics from a wide range of disciplines, such as Transfer of learning, Facial recognition system, Classifier and Feature learning.
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.
