What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Statistics
Matej Kristan spends much of his time researching Artificial intelligence, Video tracking, Computer vision, Visualization and Tracking.
His study in the fields of Robustness, Eye tracking and Channel under the domain of Artificial intelligence overlaps with other disciplines such as Filter.
His Video tracking study combines topics from a wide range of disciplines, such as Machine learning and Benchmark.
His studies examine the connections between Computer vision and genetics, as well as such issues in Source code, with regards to RGB color model, Image processing and Data visualization.
Matej Kristan combines subjects such as Equivalence, BitTorrent tracker and Cluster analysis with his study of Visualization.
As a part of the same scientific family, Matej Kristan mostly works in the field of Tracking, focusing on Object and, on occasion, Ground truth.
His most cited work include:
- The Visual Object Tracking VOT2015 Challenge Results (530 citations)
- Discriminative Correlation Filter with Channel and Spatial Reliability (463 citations)
- The Visual Object Tracking VOT2016 Challenge Results (462 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Computer vision, Video tracking, Tracking and Machine learning are his primary areas of study.
His Pattern recognition research extends to the thematically linked field of Artificial intelligence.
His study focuses on the intersection of Computer vision and fields such as Robot with connections in the field of Representation and Human–computer interaction.
His work is dedicated to discovering how Video tracking, Benchmark are connected with Field and other disciplines.
Matej Kristan has included themes like Object, Motion and Identification in his Tracking study.
His studies in Visualization integrate themes in fields like Feature extraction and Eye tracking.
He most often published in these fields:
- Artificial intelligence (82.91%)
- Computer vision (47.86%)
- Video tracking (24.79%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (82.91%)
- Computer vision (47.86%)
- Video tracking (24.79%)
In recent papers he was focusing on the following fields of study:
Matej Kristan mostly deals with Artificial intelligence, Computer vision, Video tracking, Segmentation and Tracking.
His work deals with themes such as Machine learning and Pattern recognition, which intersect with Artificial intelligence.
The various areas that Matej Kristan examines in his Computer vision study include Margin and Discriminative model.
His Video tracking research is multidisciplinary, incorporating perspectives in Robustness and Source code.
His research investigates the connection between Segmentation and topics such as Feature extraction that intersect with problems in Greedy algorithm.
Borrowing concepts from Term, Matej Kristan weaves in ideas under Tracking.
Between 2018 and 2021, his most popular works were:
- The sixth visual object tracking VOT2018 challenge results (299 citations)
- The Seventh Visual Object Tracking VOT2019 Challenge Results (122 citations)
- D3S – A Discriminative Single Shot Segmentation Tracker (28 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Statistics
Matej Kristan mainly focuses on Video tracking, Computer vision, Artificial intelligence, RGB color model and Source code.
His work in Computer vision addresses issues such as Benchmark, which are connected to fields such as Object.
His work on Artificial intelligence deals in particular with Tracking, Robustness, Visualization, Discriminative model and Segmentation.
His Ground truth research incorporates themes from Python and BitTorrent tracker.
His work deals with themes such as Margin, 3D reconstruction and Rotation, which intersect with Projection.
His Minimum bounding box study frequently draws connections between adjacent fields such as Feature extraction.
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.
