Michael Widrich
Impact in
-
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Multimodal Machine Learning Applications
- Artificial Intelligence top 10%
- Domain Adaptation and Few-Shot Learning
- Neural Networks and Applications
Papers in
-
- Machine Learning in Bioinformatics 1
- Protein purification and stability 1
- vaccines and immunoinformatics approaches 1
-
- Reinforcement Learning in Robotics 1
- Co-authors
- Sepp Hochreiter (4 shared papers)Jose A. Arjona-Medina (2 shared papers)Thomas Unterthiner (2 shared papers)Bernhard Nessler (1 shared paper)Andreas Mayr (1 shared paper)Martin Heusel (1 shared paper)Markus Hofmarcher (1 shared paper)Rupesh Durgesh (1 shared paper)
- Journals
- mAbs (1 paper)arXiv (Cornell University) (1 paper)
- Partner nations
- AustriaSwitzerlandUnited States
In The Last Decade
Michael Widrich
4 papers receiving 289 citations
Peers
Comparison fields: 5 of 64
- Computer Vision and Pattern Recognition 161
- Artificial Intelligence 111
- Automotive Engineering 24
- Radiology, Nuclear Medicine and Imaging 44
- Environmental Engineering 16
Countries citing papers authored by Michael Widrich
This map shows the geographic impact of Michael Widrich's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Michael Widrich with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Michael Widrich more than expected).
Fields of papers citing papers by Michael Widrich
This network shows the impact of papers produced by Michael Widrich. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Michael Widrich. The network helps show where Michael Widrich may publish in the future.
Co-authors
The 25 scholars most cited alongside Michael Widrich, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | Speeding up Semantic Segmentation for Autonomous Driving | 2016 | 165 |
| 2 | Hopfield Networks is All You Need | 2021 | 77 |
| 3 | 2022 | 50 | |
| 4 | RUDDER: Return Decomposition for Delayed Rewards | 2019 | 7 |
| 5 | 2006 | 0 |
About Michael Widrich
Michael Widrich is a scholar working on Molecular Biology, Artificial Intelligence, Radiology, Nuclear Medicine and Imaging, Fluid Flow and Transfer Processes and Aerospace Engineering, having authored 5 papers that have together received 299 indexed citations. Recurring topics across this work include Machine Learning in Bioinformatics (1 paper), Advanced Sensor Technologies Research (1 paper), Turbomachinery Performance and Optimization (1 paper), Advanced Combustion Engine Technologies (1 paper), Reinforcement Learning in Robotics (1 paper), Protein purification and stability (1 paper), vaccines and immunoinformatics approaches (1 paper) and Monoclonal and Polyclonal Antibodies Research (1 paper). The work is most often cited by research in Computer Vision and Pattern Recognition (161 citations), Artificial Intelligence (111 citations), Automotive Engineering (24 citations), Radiology, Nuclear Medicine and Imaging (44 citations) and Environmental Engineering (16 citations). Michael Widrich has collaborated with scholars based in Austria, Switzerland and United States. Frequent co-authors include Sepp Hochreiter, Jose A. Arjona-Medina, Thomas Unterthiner, Bernhard Nessler, Andreas Mayr, Martin Heusel, Markus Hofmarcher, Rupesh Durgesh, Günter Klambauer and J. Brandstetter. Their work appears in journals such as mAbs and arXiv (Cornell University).
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.