Nicolas Ballas

7.5k total citations · 3 hit papers
21 papers, 1.3k citations indexed

About

Nicolas Ballas is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Electrical and Electronic Engineering. According to data from OpenAlex, Nicolas Ballas has authored 21 papers receiving a total of 1.3k indexed citations (citations by other indexed papers that have themselves been cited), including 13 papers in Artificial Intelligence, 12 papers in Computer Vision and Pattern Recognition and 2 papers in Electrical and Electronic Engineering. Recurrent topics in Nicolas Ballas's work include Human Pose and Action Recognition (8 papers), Stochastic Gradient Optimization Techniques (7 papers) and Domain Adaptation and Few-Shot Learning (5 papers). Nicolas Ballas is often cited by papers focused on Human Pose and Action Recognition (8 papers), Stochastic Gradient Optimization Techniques (7 papers) and Domain Adaptation and Few-Shot Learning (5 papers). Nicolas Ballas collaborates with scholars based in Canada, United States and Germany. Nicolas Ballas's co-authors include Aaron Courville, Christopher Pal, Atousa Torabi, Li Yao, Kyunghyun Cho, Hugo Larochelle, Tegan Maharaj, Michael Rabbat, Stanisław Jastrzȩbski and Asja Fischer and has published in prestigious journals such as Multimedia Tools and Applications, 2021 IEEE/CVF International Conference on Computer Vision (ICCV) and Edinburgh Research Explorer.

In The Last Decade

Nicolas Ballas

19 papers receiving 1.2k citations

Hit Papers

Describing Videos by Exploiting Temporal Structure 2015 2026 2018 2022 2015 2017 2023 100 200 300 400 500

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Nicolas Ballas Canada 10 869 633 67 51 47 21 1.3k
Xiaoshan Yang China 21 969 1.1× 553 0.9× 65 1.0× 47 0.9× 62 1.3× 84 1.4k
Byeongho Heo South Korea 13 809 0.9× 678 1.1× 73 1.1× 36 0.7× 46 1.0× 26 1.2k
Donggyu Joo South Korea 7 757 0.9× 641 1.0× 57 0.9× 32 0.6× 38 0.8× 11 1.2k
Nicolas Thome France 17 860 1.0× 574 0.9× 67 1.0× 45 0.9× 79 1.7× 43 1.3k
Salah Rifai Canada 5 462 0.5× 541 0.9× 130 1.9× 51 1.0× 34 0.7× 7 931
Mahsa Baktashmotlagh Australia 15 482 0.6× 580 0.9× 38 0.6× 67 1.3× 45 1.0× 39 945
Sung Ju Hwang South Korea 21 834 1.0× 812 1.3× 77 1.1× 31 0.6× 39 0.8× 81 1.4k
Deli Zhao China 18 708 0.8× 798 1.3× 94 1.4× 51 1.0× 45 1.0× 57 1.5k

Countries citing papers authored by Nicolas Ballas

Since Specialization
Citations

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

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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-authorship network of co-authors of Nicolas Ballas

This figure shows the co-authorship network connecting the top 25 collaborators of Nicolas Ballas. A scholar is included among the top collaborators of Nicolas Ballas 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 Nicolas Ballas. Nicolas Ballas is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Pramanick, Shraman, Guangxing Han, Rui Hou, et al.. (2024). Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model. 14076–14088. 3 indexed citations
2.
Assran, Mahmoud, Mathilde Caron, Ishan Misra, et al.. (2021). Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 8423–8432. 54 indexed citations
3.
Wang, Jianyu, et al.. (2020). SloMo: Improving Communication-Efficient Distributed SGD with Slow Momentum. International Conference on Learning Representations. 9 indexed citations
4.
Wang, Jianyu, et al.. (2020). Lookahead Converges to Stationary Points of Smooth Non-convex Functions. 106. 8604–8608. 1 indexed citations
5.
Assran, Mahmoud, Joshua Romoff, Nicolas Ballas, Joëlle Pineau, & Michael Rabbat. (2019). Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning. arXiv (Cornell University). 32. 13299–13309. 2 indexed citations
6.
Jastrzȩbski, Stanisław, Zachary Kenton, Nicolas Ballas, et al.. (2019). On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length. Edinburgh Research Explorer. 4 indexed citations
7.
Jastrzȩbski, Stanisław, Zachary Kenton, Nicolas Ballas, et al.. (2018). DNN's Sharpest Directions Along the SGD Trajectory.. arXiv (Cornell University). 1 indexed citations
8.
George, Thomas, César Laurent, Xavier Bouthillier, Nicolas Ballas, & Pascal Vincent. (2018). Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis. Neural Information Processing Systems. 31. 9550–9560. 9 indexed citations
9.
Jastrzȩbski, Stanisław, Zachary Kenton, Devansh Arpit, et al.. (2018). Finding Flatter Minima with SGD. International Conference on Learning Representations. 3 indexed citations
10.
Jastrzȩbski, Stanisław, et al.. (2018). SGD Smooths The Sharpest Directions. 1 indexed citations
11.
Assran, Mahmoud, Nicolas Loizou, Nicolas Ballas, & Michael Rabbat. (2018). Stochastic Gradient Push for Distributed Deep Learning. arXiv (Cornell University). 344–353. 46 indexed citations
12.
Krueger, David, Nicolas Ballas, Stanisław Jastrzȩbski, et al.. (2017). Deep Nets Don't Learn via Memorization. PolyPublie (École Polytechnique de Montréal). 23 indexed citations
13.
Arpit, Devansh, Stanisław Jastrzȩbski, Nicolas Ballas, et al.. (2017). A closer look at memorization in deep networks. Jagiellonian University Repository (Jagiellonian University). 70. 233–242. 344 indexed citations breakdown →
14.
Maharaj, Tegan, Nicolas Ballas, Anna Rohrbach, Aaron Courville, & Christopher Pal. (2017). A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering. PolyPublie (École Polytechnique de Montréal). 7359–7368. 48 indexed citations
15.
Yao, Li, Atousa Torabi, Kyunghyun Cho, et al.. (2015). Describing Videos by Exploiting Temporal Structure. PolyPublie (École Polytechnique de Montréal). 4507–4515. 593 indexed citations breakdown →
16.
Yan, Yan, et al.. (2014). Evaluation of semi-supervised learning method on action recognition. Multimedia Tools and Applications. 74(2). 523–542. 13 indexed citations
17.
Ballas, Nicolas, et al.. (2013). Space-Time Robust Video Representation for Action Recognition. 2 indexed citations
18.
Ballas, Nicolas, et al.. (2012). Trajectory signature for action recognition in video. 1429–1432. 6 indexed citations
19.
Ballas, Nicolas, et al.. (2012). A new point process model for trajectory-based events annotation. Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE. 8300. 83000B–83000B. 1 indexed citations
20.
Ballas, Nicolas, et al.. (2011). Trajectories based descriptor for dynamic events annotation. 13–18. 5 indexed citations

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.

Explore authors with similar magnitude of impact

Rankless by CCL
2026