Aurélien Lucchi

12.6k total citations · 2 hit papers
52 papers, 8.1k citations indexed

About

Aurélien Lucchi is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Statistical and Nonlinear Physics. According to data from OpenAlex, Aurélien Lucchi has authored 52 papers receiving a total of 8.1k indexed citations (citations by other indexed papers that have themselves been cited), including 23 papers in Artificial Intelligence, 17 papers in Computer Vision and Pattern Recognition and 8 papers in Statistical and Nonlinear Physics. Recurrent topics in Aurélien Lucchi's work include Stochastic Gradient Optimization Techniques (8 papers), Model Reduction and Neural Networks (7 papers) and Generative Adversarial Networks and Image Synthesis (6 papers). Aurélien Lucchi is often cited by papers focused on Stochastic Gradient Optimization Techniques (8 papers), Model Reduction and Neural Networks (7 papers) and Generative Adversarial Networks and Image Synthesis (6 papers). Aurélien Lucchi collaborates with scholars based in Switzerland, United States and France. Aurélien Lucchi's co-authors include Pascal Fua, Kevin Smith, Radhakrishna Achanta, Anil Shaji, Sabine Süsstrunk, Christa Zoufal, Stefan Woerner, Thomas Hofmann, Jan Dirk Wegner and Graham Knott and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Applied Energy and IEEE Transactions on Medical Imaging.

In The Last Decade

Aurélien Lucchi

49 papers receiving 7.8k citations

Hit Papers

SLIC Superpixels Compared to State-of-the-Art Superpixel ... 2012 2026 2016 2021 2012 2019 2.0k 4.0k 6.0k

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Aurélien Lucchi Switzerland 20 4.7k 2.1k 1.6k 651 518 52 8.1k
Anil Shaji United States 19 4.3k 0.9× 2.0k 0.9× 2.7k 1.7× 634 1.0× 466 0.9× 54 8.5k
Radhakrishna Achanta Switzerland 17 8.2k 1.7× 2.7k 1.3× 988 0.6× 968 1.5× 570 1.1× 33 11.0k
Kevin Smith United States 33 5.1k 1.1× 2.2k 1.0× 1.9k 1.2× 698 1.1× 1.2k 2.4× 98 10.1k
Paul Fieguth Canada 33 4.0k 0.9× 991 0.5× 1.6k 1.0× 523 0.8× 576 1.1× 225 8.7k
Qingshan Liu China 47 5.2k 1.1× 2.2k 1.1× 1.7k 1.1× 415 0.6× 379 0.7× 273 8.5k
Linda G. Shapiro United States 38 6.7k 1.4× 1.3k 0.6× 2.0k 1.3× 1.2k 1.9× 931 1.8× 272 11.1k
Hanzi Mao United States 5 3.8k 0.8× 869 0.4× 1.9k 1.2× 606 0.9× 866 1.7× 8 7.8k
Jinchang Ren United Kingdom 46 3.6k 0.8× 3.6k 1.7× 1.7k 1.1× 621 1.0× 612 1.2× 306 9.0k
R.M. Haralick United States 25 4.0k 0.9× 1.1k 0.5× 1.0k 0.7× 750 1.2× 647 1.2× 138 6.6k
Josiane Zerubia France 41 3.0k 0.6× 2.0k 0.9× 748 0.5× 985 1.5× 347 0.7× 280 6.5k

Countries citing papers authored by Aurélien Lucchi

Since Specialization
Citations

This map shows the geographic impact of Aurélien Lucchi'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 Aurélien Lucchi with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Aurélien Lucchi more than expected).

Fields of papers citing papers by Aurélien Lucchi

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Aurélien Lucchi. 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 Aurélien Lucchi. The network helps show where Aurélien Lucchi may publish in the future.

Co-authorship network of co-authors of Aurélien Lucchi

This figure shows the co-authorship network connecting the top 25 collaborators of Aurélien Lucchi. A scholar is included among the top collaborators of Aurélien Lucchi 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 Aurélien Lucchi. Aurélien Lucchi 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.
Proske, Frank, et al.. (2023). Mean first exit times of Ornstein–Uhlenbeck processes in high-dimensional spaces. Journal of Physics A Mathematical and Theoretical. 56(21). 215003–215003. 5 indexed citations
3.
Bécigneul, Gary, et al.. (2021). Momentum Improves Optimization on Riemannian Manifolds. International Conference on Artificial Intelligence and Statistics. 1351–1359. 1 indexed citations
4.
Sutter, David, et al.. (2021). The power of quantum neural networks. Nature Computational Science. 1(6). 403–409. 6 indexed citations
5.
Lauber, Annika, et al.. (2020). A convolutional neural network for classifying cloud particles recorded by imaging probes. Atmospheric measurement techniques. 13(5). 2219–2239. 34 indexed citations
6.
Pavllo, Dario, et al.. (2020). Convolutional Generation of Textured 3D Meshes. Lirias (KU Leuven). 33. 870–882. 1 indexed citations
7.
Bécigneul, Gary, et al.. (2020). Practical Accelerated Optimization on Riemannian Manifolds. arXiv (Cornell University). 5 indexed citations
8.
Bécigneul, Gary, et al.. (2020). A Continuous-time Perspective for Modeling Acceleration in Riemannian Optimization.. International Conference on Artificial Intelligence and Statistics. 1297–1307. 4 indexed citations
9.
Daneshmand, Hadi, Jonas Köhler, Francis Bach, Thomas Hofmann, & Aurélien Lucchi. (2020). Batch normalization provably avoids ranks collapse for randomly initialised deep networks. Neural Information Processing Systems. 33. 18387–18398. 8 indexed citations
10.
Köhler, Jonas, et al.. (2019). Ellipsoidal Trust Region Methods and the Marginal Value of Hessian Information for Neural Network Training.. arXiv (Cornell University). 2 indexed citations
11.
Daneshmand, Hadi, Jonas Köhler, Aurélien Lucchi, & Thomas Hofmann. (2018). Escaping Saddles with Stochastic Gradients. International Conference on Machine Learning. 1155–1164. 6 indexed citations
12.
Wegner, Jan Dirk, et al.. (2018). PolyMapper: Extracting City Maps using Polygons.. arXiv (Cornell University). 7 indexed citations
13.
Fluri, Janis, T. Kacprzak, Alexandre Réfrégier, et al.. (2018). Cosmological constraints from noisy convergence maps through deep learning. Physical review. D. 98(12). 53 indexed citations
14.
Kacprzak, Tomasz, Aurélien Lucchi, A. Amara, et al.. (2018). Fast cosmic web simulations with generative adversarial networks. Repository for Publications and Research Data (ETH Zurich). 59 indexed citations
15.
Levy, Kfir Y., Aurélien Lucchi, Nathanaël Perraudin, et al.. (2018). A domain agnostic measure for monitoring and evaluating GANs. arXiv (Cornell University). 32. 12092–12102. 5 indexed citations
16.
Chen, Wenhu, Aurélien Lucchi, & Thomas Hofmann. (2016). Bootstrap, Review, Decode: Using Out-of-Domain Textual Data to Improve Image Captioning.. arXiv (Cornell University). 1 indexed citations
17.
Daneshmand, Hadi, Aurélien Lucchi, & Thomas Hofmann. (2016). Starting Small -- Learning with Adaptive Sample Sizes. arXiv (Cornell University). 1463–1471. 7 indexed citations
18.
Hofmann, Thomas, Aurélien Lucchi, & Brian McWilliams. (2015). Neighborhood Watch: Stochastic Gradient Descent with Neighbors. arXiv (Cornell University). 1 indexed citations
19.
Sznitman, Raphael, Aurélien Lucchi, Peter I. Frazier, Bruno Jedynak, & Pascal Fua. (2013). An Optimal Policy for Target Localization with Application to Electron Microscopy. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 28(1). 1–9. 16 indexed citations
20.
Zufferey, Guillaume, Patrick Jermann, Aurélien Lucchi, & Pierre Dillenbourg. (2009). TinkerSheets. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 377–384. 36 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