CV

Research interests

Person recognition under real-world conditions: face and gait at very low resolution, long range and cross-spectral (RGB/NIR) capture, often with limited training data.
Efficient architectures for edge devices: binarized networks, self-attention, hybrid CNN–Transformer designs, and distillation from large teacher architectures into compact student models.
Security of vision systems: presentation and digital injection attack detection that generalizes to unseen attacks, backdoor and adversarial robustness, and detection of generated media.
Privacy in Machine Learning applications: analyzing training sample leakage through membership inference and image inversion from ML models, and defenses on compact models and decentralized deployments.
Few-shot learning across architectures, from CNNs to Transformers, vision–language models and LLMs, with applications such as activity recognition and text-to-video search.
Controllable generative models for realistic degradations, ages and capture conditions, judged by whether they improve real-world recognition rather than by visual quality.

Academic and research experience

Universitat Autònoma de Barcelona (UAB) Barcelona, Spain	Assistant Professor, Department of Computer Science	August 2026 - Current
Teaching duties at the Department of Computer Science and research on Computer Vision & AI
Idiap Research Institute Valais, Switzerland	Postdoctoral Researcher, Biometrics Security & Privacy Group	June 2024 - July 2026
Research work for the InnoSuisse SENTINEL project on detection of presentation and digital injection attacks for age verification systems. Face and gait data collection on multiple modalities (RGB, NIR, long distance) and research on long distance face and gait recognition on the EU Horizon PopEye and CarMen projects.
Inria Rennes, France	Postdoctoral Researcher, WIDE team	May 2023 - May 2024
Collaborated on the European Union-funded SOTERIA project. Research work focused on Privacy on Decentralized Machine Learning and Trusted Execution Environments for data-centric scenarios.
Tecnológico de Monterrey State of Mexico, Mexico	Postdoctoral Researcher	Feb 2023 - July 2023
Research work focused on Computer Vision models for Smart Cities in applications such as surveillance, mobility, and health. Implemented models for real-time face recognition, face anti-spoofing, and crowd counting on PyTorch. Published one conference article.
Idiap Research Institute Valais, Switzerland	Research Intern, Biometrics Security & Privacy Group	Aug 2022 - Dec 2022
Authored code for training and evaluating state of the art and novel original method proposals for very low resolution face recognition on frameworks PyTorch and Bob using the internal computing infrastructure. Collaborated with fellow researchers at the group to achieve internal research objectives.

Industry experience

Dell Latin America Mexico City, Mexico	Sr. Analyst, Global Demand & Supply Chain Operations	May 2016 - Aug 2016
Successfully provided inventory visibility/availability to Sales & Support Teams, coordinated order entry support and production availability against inventory forecast to Sales.
Dell Latin America Mexico City, Mexico	Intern, Enterprise Merchandising Operations	Feb 2015 – May 2016
Positioned enterprise Servers, Storage and Networking products and generated demand in their respective road to market. Launched successful promotions for Enterprise solutions.

Teaching experience

Assistant Professor at Universitat Autònoma de Barcelona (2026-present)

Undergraduate & Graduate courses, UAB Campus Bellaterra, Computer Science Department, 2026

Created class contents, lecturing, grading, and tutoring students at the Computer Science Department at UAB for undergraduate and graduate programs.

Computer Science Teaching Assistant at Tecnológico de Monterrey (2020-2022)

Undergraduate & Graduate courses, Tecnológico de Monterrey, Campus State of Mexico, Computer Science Department, 2022

Created class contents, such as presentations and assignments, for the courses of Cognitive Computing, Deep Learning, Analysis and Design of Advanced Algorithms, Neural Systems, and Research Methods; at undergraduate and graduate levels. Assisted with lecturing, grading, and tutoring students.

Research supervision

Undergraduate research mentoring - Google Explore Computer Science Research (CSR) LATAM Undergraduate Research Program, organized with LatinX in AI (LXAI) - Jan 2024 - 2024
- Project: Improving Model Privacy on Decentralized Computer Vision Applications (differential privacy, secure aggregation, and federated learning for computer vision)
- Co-mentored with Prof. Miguel González Mendoza (Tecnológico de Monterrey)
- Mentee: Lauren Lissette Llauradó Reyes, B.Sc. student at Tecnológico de Monterrey, Mexico

Education

Tecnológico de Monterrey State of Mexico, Mexico	Ph.D. in Computer Science	Jan 2019 - Dec 2022
Research focused on Face Recognition (Computer Vision). Thesis: Closing the Gap on Affordable Real-Time Very Low Resolution Face Recognition for Automated Video Surveillance. Advisors: Dr. Leonardo Chang Fernández and Dr. Miguel González Mendoza. Published 3 journal articles and 3 conference articles
Stevens Institute of Technology New Jersey, USA	M.Sc. in Computer Science	Aug. 2016 - May 2018
Focus on Computer Vision and Machine Learning. Grade Point Average: 3.7/4.0
Tecnológico de Monterrey State of Mexico, Mexico	B.Sc. Computer Science and Technology	Aug 2011 - Dec 2015
Cumulative average: 92.5/100

Research projects

CarMen - Non-stop Biometric Border Control for Secure and Efficient Crossing (EU Horizon Europe) - Idiap, 2024 - 2026
- Face data collection (RGB, NIR, through-glass, on-the-move) and research on cross-spectral face recognition for vehicular border control.
PopEye - On-the-move biometric identification at EU external borders (EU Horizon Europe) - Idiap, 2024 - 2026
- Long-distance face and gait data collection and research on long-range face and gait recognition.
AIM-GATE (Frontex Research Grants) - Idiap, 2025 - 2026
- Data collection of challenging border-crossing scenarios, carried out together with PopEye and CarMen.
SENTINEL-UK - Securing Age Estimation and Digital IDs against Presentation and Injection Threats (Innosuisse) - Idiap, 2024 - 2025
- Detection of presentation and digital injection attacks for age verification systems.
SOTERIA - User-centric privacy and decentralized personal data vault (EU H2020) - Inria, 2023 - 2024
- Privacy on decentralized machine learning and Trusted Execution Environments for data-centric scenarios.

Released datasets and code

Datasets
- GaitFace - Multimodal long-range face and gait dataset (70 subjects, up to 100 m, ground-level and elevated views) - IJCB 2026
- DriveFace - Cross-spectral (RGB/NIR) through-glass in-vehicle face dataset with a presentation attack subset - IJCB 2026
- AgeSynth - Synthetic identity-preserving aged and de-aged face dataset - IJCB 2025
Code
- Synthetic data generation for low-resolution face recognition - IJCB 2026
- DriveFace benchmark - IJCB 2026
- AgeSynth: identity-preserving face aging in the StyleGAN latent space - IJCB 2025
- SwiftFaceFormer - ICPR 2024
- Efficient face anti-spoofing against physical and digital attacks - CVPR 2024 Workshops
- Custom lightweight face anti-spoofing
- BinaryFaceNet: binarized networks for low-resolution face recognition (InsightFace + Larq, Keras)

Publication list

Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gap

Luis S. Luevano, Ünsal Öztürk, Hatef Otroshi Shahreza, Anjith George, Sébastien Marcel. "Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gap". IEEE International Joint Conference on Biometrics (IJCB) 2026, Focus Session on Generative AI for Fair and Secure Biometrics under Limited Data.

GaitFace: A Multimodal Dataset for Long-Range Person Identification

Alain Komaty, Luis S. Luevano, Vidit Vidit, Anjith George, Zeina Al Amine, Sébastien Marcel. "GaitFace: A Multimodal Dataset for Long-Range Person Identification". IEEE International Joint Conference on Biometrics (IJCB) 2026.

DriveFace: A Cross-Spectral Through-Glass Face Dataset for On-the-Move Vehicular Border Control

Anjith George, Luis S. Luevano, Alain Komaty, Zeina Al Amine, Vidit Vidit, Sébastien Marcel. "DriveFace: A Cross-Spectral Through-Glass Face Dataset for On-the-Move Vehicular Border Control". IEEE International Joint Conference on Biometrics (IJCB) 2026.

Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space

Luis S. Luevano, Pavel Korshunov, Sébastien Marcel. "Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space". IEEE International Joint Conference on Biometrics (IJCB) 2025.

SwiftFaceFormer: An Efficient and Lightweight Hybrid Architecture for Accurate Face Recognition Applications

Luis S. Luevano, Yoanna Martínez-Díaz, Heydi Méndez-Vázquez, Miguel Gonzalez-Mendoza, Davide Frey. "SwiftFaceFormer: An Efficient and Lightweight Hybrid Architecture for Accurate Face Recognition Applications". 2024 27th International Conference on Pattern Recognition (ICPR).

Assessing the Performance of Efficient Face Anti-Spoofing Detection Against Physical and Digital Presentation Attacks

Luis S. Luevano, Yoanna Martínez-Díaz, Heydi Méndez-Vázquez, Miguel Gonzalez-Mendoza, Davide Frey. "Assessing the Performance of Efficient Face Anti-Spoofing Detection Against Physical and Digital Presentation Attacks". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.

Effectiveness of Blind Face Restoration to Boost Face Recognition Performance at Low-Resolution Images

Yoanna Martínez-Díaz, Luis S. Luevano, Heydi Méndez-Vázquez. "Effectiveness of Blind Face Restoration to Boost Face Recognition Performance at Low-Resolution Images". Progress in Artificial Intelligence and Pattern Recognition. IWAIPR 2023. Lecture Notes in Computer Science, vol 14335. Springer, Cham. https://doi.org/10.1007/978-3-031-49552-6_39

Exploring the Effectiveness of Lightweight Architectures for Face Anti-Spoofing

Yoanna Martínez-Díaz, Heydi Méndez-Vázquez, Luis S. Luevano, Miguel Gonzalez-Mendoza. "Exploring the Effectiveness of Lightweight Architectures for Face Anti-Spoofing". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 6391-6401

Utilizing CNNs for Cryptanalysis of Selective Biometric Face Sample Encryption

H. Hofbauer, Y. Martínez-Díaz, L. S. Luevano, H. Méndez-Vázquez and A. Uhl, "Utilizing CNNs for Cryptanalysis of Selective Biometric Face Sample Encryption," 2022 26th International Conference on Pattern Recognition (ICPR), Montreal, QC, Canada, 2022, pp. 892-899, doi: 10.1109/ICPR56361.2022.9956664.

Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation

Y. Martínez-Díaz, H. Méndez-Vázquez, L. S. Luevano, M. Nicolás-Díaz, L. Chang and M. González-Mendoza, "Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation," in IEEE Access, vol. 10, pp. 7341-7353, 2022, doi: 10.1109/ACCESS.2021.3135255.

A Study on the Performance of Unconstrained Very Low Resolution Face Recognition: Analyzing Current Trends and New Research Directions

L. S. Luevano, L. Chang, H. Méndez-Vázquez, Y. Martínez-Díaz and M. González-Mendoza, "A Study on the Performance of Unconstrained Very Low Resolution Face Recognition: Analyzing Current Trends and New Research Directions," in IEEE Access, vol. 9, pp. 75470-75493, 2021, doi: 10.1109/ACCESS.2021.3080712.

Benchmarking lightweight face architectures on specific face recognition scenarios

Martínez-Díaz, Y., Nicolás-Díaz, M., Méndez-Vázquez, H., Luevano, L.S. et al. Benchmarking lightweight face architectures on specific face recognition scenarios. Artif Intell Rev 54, 6201–6244 (2021). https://doi.org/10.1007/s10462-021-09974-2

Lightweight Low-Resolution Face Recognition for Surveillance Applications

Y. Martínez-Díaz, H. Méndez-Vázquez, L. S. Luevano, L. Chang and M. Gonzalez-Mendoza, "Lightweight Low-Resolution Face Recognition for Surveillance Applications," 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, 2021, pp. 5421-5428, doi: 10.1109/ICPR48806.2021.9412280.

ShuffleFaceNet: A Lightweight Face Architecture for Efficient and Highly-Accurate Face Recognition

Y. Martínez-Díaz, L. S. Luevano, H. Mendez-Vazquez, M. Nicolas-Diaz, L. Chang and M. Gonzalez-Mendoza, "ShuffleFaceNet: A Lightweight Face Architecture for Efficient and Highly-Accurate Face Recognition," 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea (South), 2019, pp. 2721-2728, doi: 10.1109/ICCVW.2019.00333.

Peer-reviewed extended abstracts

Luis S. Luevano, Miguel González-Mendoza, Yoanna Martínez-Díaz, Heydi Méndez-Vázquez. “Exploring the Potential for Real-Time Vision Transformer-Level Precision on Face Recognition Scenarios through Binarization on Embedded Systems”. LatinX in AI Workshop at ICCV 2023 - IEEE/CVF International Conference on Computer Vision Workshops, Paris, France, October 2023. Extended abstract, Poster

Project deliverables

Luis S. Luevano, Davide Frey, Marc Sel, Dave Singelee. “SOTERIA D5.4 Hardware-Based Privacy”. EU H2020 SOTERIA project, 2024. Official document, hal-04393670

Skills

Computer Vision
- Experience working on filtering, keypoint matching, depth map extraction, 3D point cloud extraction, space carving, image segmentation, convolutional neural networks, image recognition, face anti-spoofing, face recognition, low-resolution and cross-spectral face recognition, gait recognition, face image generation and editing (GANs), and biometric dataset collection.
Natural Language Processing
- Transformers, BERT, LSTMs, and wav2vec in PyTorch.
Machine Learning:
- Experience working on regression, maximum likelihood & Bayesian estimation, support vector machines, decision trees, random forests, neural networks.
Programming languages:
- Proficiency in C/C++, Java, Python, JavaScript, Matlab.
- Competent in R, SQL and PL/SQL.
Libraries and frameworks:
- OpenCV, PyTorch, Bob (Idiap biometrics toolkit), TensorFlow, Keras, MxNet, Trax, Pandas, Sklearn, SciPy, NumPy.
Tools and infrastructure:
- Git, Linux, Docker, HPC clusters and job schedulers (SGE, Slurm), Jupyter, LaTeX.
Languages:
- Spanish (native), English (proficient, TOEFL iBT score: 101/120 points), French (fluent), Japanese (fluent), German (basic), Catalan (basic)

Exploring the Potential for Real-Time Vision Transformer-Level Precision on Face Recognition Scenarios through Binarization on Embedded Systems

October 2023

Poster at LatinX in AI (LXAI) Workshop at ICCV 2023, Paris, France

Cerrando la brecha en el reconocimiento facial (Closing the gap in face recognition)

March 2022

Doctoral consortium presentation at CIDTEC Doctoral Consortium, Tecnológico de Monterrey (virtual edition), Online

Awards

2nd place of José Negrete Martínez Award for Best Doctoral Thesis - November 2023
- Awarded by the Mexican Society for Artificial Intelligence (SMIA)

Academic service

Journal reviewer (verified peer review record on ORCID)
- IEEE Access (6 reviews)
- Computing, Springer (2 reviews)
- Health Information Science and Systems, Springer (1 review)
Conference reviewer
- International Conference on Pattern Recognition (ICPR)
- IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC)
- Mexican International Conference on Artificial Intelligence (MICAI)
- Congreso Mexicano de Inteligencia Artificial (COMIA)

Memberships

IEEE Student Member (active)
European Association for Biometrics (EAB) - member while at Idiap (2024 - 2026)

Outreach and media

Conecta Tec: “La Sociedad Mexicana de Inteligencia Artificial otorgó el reconocimiento al egresado Tec” - December 2023
Interview at Tec Sounds radio - January 2024
Conecta Tec: “Centro de investigación suizo invita a egresado Tec a colaborar” - August 2022
Tec Research video: “Cerrando la brecha en el reconocimiento facial” - March 2022

Luis S. Luévano, PhD

CV