Francis Dutil
- Artificial Intelligence
- Computer Vision and Pattern Recognition top 10%
- Radiology, Nuclear Medicine and Imaging
- Signal Processing
- Control and Systems Engineering
- Co-authors
- Aaron CourvilleSai RajeswarChris PalSandeep SubramanianMohammad HavaeiQicheng LaoThomas FevensLisa Di Jorio
- Topics
- Multimodal Machine Learning Applications (7 papers)Domain Adaptation and Few-Shot Learning (4 papers)Topic Modeling (3 papers)
- Cited by
- Computer Vision and Pattern RecognitionArtificial IntelligenceComputer Graphics and Computer-Aided Design
- Journals
- Pattern RecognitionarXiv (Cornell University)Neural Information Processing Systems
- Partner nations
- CanadaUnited KingdomUnited States
In The Last Decade
Francis Dutil
9 papers receiving 120 citations
Peers
Comparison fields: 5 of 43
- Artificial Intelligence 83
- Computer Vision and Pattern Recognition 71
- Radiology, Nuclear Medicine and Imaging 7
- Signal Processing 6
- Control and Systems Engineering 5
Countries citing papers authored by Francis Dutil
This map shows the geographic impact of Francis Dutil'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 Francis Dutil with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Francis Dutil more than expected).
Fields of papers citing papers by Francis Dutil
This network shows the impact of papers produced by Francis Dutil. 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 Francis Dutil. The network helps show where Francis Dutil may publish in the future.
Co-authorship network of co-authors of Francis Dutil
This figure shows the co-authorship network connecting the top 25 collaborators of Francis Dutil. A scholar is included among the top collaborators of Francis Dutil based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Francis Dutil. Francis Dutil is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 4 | |
| 2 | Saliency is a Possible Red Herring When Diagnosing Poor Generalization | 3 |
| 3 | 12 | |
| 4 | Underwhelming Generalization Improvements From Controlling Feature Attribution | 1 |
| 5 | GradMask: Reduce Overfitting by Regularizing Saliency. | 3 |
| 6 | 19 | |
| 7 | Plan, Attend, Generate: Planning for Sequence-to-Sequence Models | 6 |
| 8 | 75 | |
| 9 | 2 |
About Francis Dutil
Francis Dutil is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Radiology, Nuclear Medicine and Imaging, having authored 9 papers that have together received 125 indexed citations. Recurring topics across this work include Multimodal Machine Learning Applications (7 papers), Domain Adaptation and Few-Shot Learning (4 papers) and Topic Modeling (3 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (71 citations), Artificial Intelligence (83 citations) and Computer Graphics and Computer-Aided Design (3 citations). Francis Dutil has collaborated with scholars based in Canada, United Kingdom and United States. Frequent co-authors include Aaron Courville, Sai Rajeswar, Chris Pal, Sandeep Subramanian, Mohammad Havaei, Qicheng Lao, Thomas Fevens, Lisa Di Jorio, Yoshua Bengio and Adam Trischler. Their work appears in journals such as Pattern Recognition, arXiv (Cornell University) and Neural Information Processing Systems.
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.