Nicolas Ballas
Impact in
-
- Multimodal Machine Learning Applications
- Human Pose and Action Recognition
- Video Analysis and Summarization
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Artificial Intelligence top 2%
- Domain Adaptation and Few-Shot Learning
- Machine Learning and Data Classification
- Anomaly Detection Techniques and Applications
Papers in
-
- Stochastic Gradient Optimization Techniques 7
- Domain Adaptation and Few-Shot Learning 5
- Neural Networks and Applications 4
-
- Human Pose and Action Recognition 8
- Multimodal Machine Learning Applications 4
- Video Analysis and Summarization 4
- Video Surveillance and Tracking Methods 4
- Advanced Neural Network Applications 3
- Co-authors
- Aaron Courville (4 shared papers)Christopher Pal (2 shared papers)Kyunghyun Cho (1 shared paper)Atousa Torabi (1 shared paper)Hugo Larochelle (1 shared paper)Li Yao (1 shared paper)Tegan Maharaj (3 shared papers)Michael Rabbat (6 shared papers)
- Journals
- Multimedia Tools and Applications (1 paper)2021 IEEE/CVF International Conference on Computer Vision (ICCV) (1 paper)Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (1 paper)Edinburgh Research Explorer (University of Edinburgh) (1 paper)arXiv (Cornell University) (3 papers)
- Partner nations
- CanadaUnited StatesGermany
In The Last Decade
Nicolas Ballas
19 papers receiving 1.3k citations
Nicolas Ballas's Hit Papers
Peers
Comparison fields: 5 of 96
- Computer Vision and Pattern Recognition 879
- Artificial Intelligence 641
- Signal Processing 69
- Human-Computer Interaction 31
- Computational Mathematics 3
Countries citing papers authored by Nicolas Ballas
This map shows the geographic impact of Nicolas Ballas'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 Nicolas Ballas with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Nicolas Ballas more than expected).
Fields of papers citing papers by Nicolas Ballas
This network shows the impact of papers produced by Nicolas Ballas. 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 Nicolas Ballas. The network helps show where Nicolas Ballas may publish in the future.
Co-authors
The 25 scholars most cited alongside Nicolas Ballas, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 21 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | Describing Videos by Exploiting Temporal Structure Hit paper breakdown → | 2015 | 597 |
| 2 | A closer look at memorization in deep networks Hit paper breakdown → | 2017 | 348 |
| 3 | Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture Hit paper breakdown → | 2023 | 133 |
| 4 | 2021 | 56 | |
| 5 | 2017 | 51 | |
| 6 | 2018 | 46 | |
| 7 | Deep Nets Don't Learn via Memorization | 2017 | 23 |
| 8 | 2014 | 12 | |
| 9 | SloMo: Improving Communication-Efficient Distributed SGD with Slow Momentum | 2020 | 9 |
| 10 | Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis | 2018 | 9 |
| 11 | 2012 | 6 | |
| 12 | 2024 | 5 | |
| 13 | 2011 | 5 | |
| 14 | On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length | 2019 | 4 |
| 15 | Finding Flatter Minima with SGD | 2018 | 3 |
| 16 | Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning | 2019 | 2 |
| 17 | Space-Time Robust Video Representation for Action Recognition | 2013 | 2 |
| 18 | DNN's Sharpest Directions Along the SGD Trajectory. | 2018 | 1 |
| 19 | SGD Smooths The Sharpest Directions | 2018 | 1 |
| 20 | 2012 | 1 |
About Nicolas Ballas
Nicolas Ballas is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Computer Networks and Communications and Control and Systems Engineering, having authored 21 papers that have together received 1.3k indexed citations. Recurring topics across this work include Human Pose and Action Recognition (8 papers), Stochastic Gradient Optimization Techniques (7 papers), Domain Adaptation and Few-Shot Learning (5 papers), Multimodal Machine Learning Applications (4 papers), Neural Networks and Applications (4 papers), Video Analysis and Summarization (4 papers), Video Surveillance and Tracking Methods (4 papers) and Advanced Neural Network Applications (3 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (879 citations), Artificial Intelligence (641 citations), Signal Processing (69 citations), Human-Computer Interaction (31 citations) and Computational Mathematics (3 citations). Nicolas Ballas has collaborated with scholars based in Canada, United States and Germany. Frequent co-authors include Aaron Courville, Christopher Pal, Kyunghyun Cho, Atousa Torabi, Hugo Larochelle, Li Yao, Tegan Maharaj, Michael Rabbat, Mahmoud Assran and Stanisław Jastrzȩbski. Their work appears in journals such as Multimedia Tools and Applications, 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE, Edinburgh Research Explorer (University of Edinburgh) 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.