Luis Felipe Gomez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Luis Felipe Gomez has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Aythami Morales
Universidad Autónoma de Madrid (UAM)
8 shared publications - Julian Fierrez
Universidad Autónoma de Madrid (UAM)
8 shared publications - Ruben Tolosana
Universidad Autónoma de Madrid
7 shared publications - Roberto Daza
Universidad Autónoma de Madrid
4 shared publications Javier Ortega-Garcia
Universidad Autónoma de Madrid
3 shared publications- Enrique Navarro
Sport Biomechanics Laboratory, Department of Health and Human Performance, Faculty of Physical Activity and Sports Sciences INEF, Universidad Politécnica de Madrid, 28040 Madrid, Spain
2 shared publications
Latest Publications
- Open Access
- 6 September 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
Leveraging avatar fingerprinting: A multi-generator photorealistic talking-head public database and benchmark
- 6 September 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
Open AccessLeveraging avatar fingerprinting: A multi-generator photorealistic talking-head public database and benchmark
- 30 April 2025
- Published by Springer Nature
- p. 398-412
VideoRun2D: Cost-Effective Markerless Motion Capture for Sprint Biomechanics
- 30 April 2025
- Published by Springer Nature
- p. 398-412
VideoRun2D: Cost-Effective Markerless Motion Capture for Sprint Biomechanics
- Open Access
VideoRun2D: Cost-Effective Markerless Motion Capture for Sprint Biomechanics
Sprinting is a determinant ability, especially in team sports. The kinematics of the sprint have been studied in the past using different methods specially developed considering human biomechanics and, among those methods, markerless systems stand out as very cost-effective. On the other hand, we have now multiple general methods for pixel and body tracking based on recent machine learning breakthroughs with excellent performance in body tracking, but these excellent trackers do not generally consider realistic human biomechanics. This investigation first adapts two of these general trackers (MoveNet and CoTracker) for realistic biomechanical analysis and then evaluate them in comparison to manual tracking (with key points manually marked using the software Kinovea). Our best resulting markerless body tracker particularly adapted for sprint biomechanics is termed VideoRun2D. The experimental development and assessment of VideoRun2D is reported on forty sprints recorded with a video camera from 5 different subjects, focusing our analysis in 3 key angles in sprint biomechanics: inclination of the trunk, flex extension of the hip and the knee. The CoTracker method showed huge differences compared to the manual labeling approach. However, the angle curves were correctly estimated by the MoveNet method, finding errors between 3.2° and 5.5°. In conclusion, our proposed VideoRun2D based on MoveNet core seems to be a helpful tool for evaluating sprint kinematics in some scenarios. On the other hand, the observed precision of this first version of VideoRun2D as a markerless sprint analysis system may not be yet enough for highly demanding applications. Future research lines towards that purpose are also discussed at the end: better tracking post-processing and user- and time-dependent adaptation.
Open AccessVideoRun2D: Cost-Effective Markerless Motion Capture for Sprint Biomechanics
Sprinting is a determinant ability, especially in team sports. The kinematics of the sprint have been studied in the past using different methods specially developed considering human biomechanics and, among those methods, markerless systems stand out as very cost-effective. On the other hand, we have now multiple general methods for pixel and body tracking based on recent machine learning breakthroughs with excellent performance in body tracking, but these excellent trackers do not generally consider realistic human biomechanics. This investigation first adapts two of these general trackers (MoveNet and CoTracker) for realistic biomechanical analysis and then evaluate them in comparison to manual tracking (with key points manually marked using the software Kinovea). Our best resulting markerless body tracker particularly adapted for sprint biomechanics is termed VideoRun2D. The experimental development and assessment of VideoRun2D is reported on forty sprints recorded with a video camera from 5 different subjects, focusing our analysis in 3 key angles in sprint biomechanics: inclination of the trunk, flex extension of the hip and the knee. The CoTracker method showed huge differences compared to the manual labeling approach. However, the angle curves were correctly estimated by the MoveNet method, finding errors between 3.2° and 5.5°. In conclusion, our proposed VideoRun2D based on MoveNet core seems to be a helpful tool for evaluating sprint kinematics in some scenarios. On the other hand, the observed precision of this first version of VideoRun2D as a markerless sprint analysis system may not be yet enough for highly demanding applications. Future research lines towards that purpose are also discussed at the end: better tracking post-processing and user- and time-dependent adaptation.
- Open Access
PAD-Phys: Exploiting Physiology for Presentation Attack Detection in Face Biometrics
Presentation Attack Detection (PAD) is a crucial stage in facial recognition systems to avoid leakage of personal information or spoofing of identity to entities. Recently, pulse detection based on remote photoplethysmography (rPPG) has been shown to be effective in face presentation attack detection. This work presents three different approaches to the presentation attack detection based on rPPG: (i) The physiological domain, a domain using rPPG-based models, (ii) the Deepfakes domain, a domain where models were retrained from the physiological domain to specific Deepfakes detection tasks; and (iii) a new Presentation Attack domain was trained by applying transfer learning from the two previous domains to improve the capability to differentiate between bona-fides and attacks. The results show the efficiency of the rPPG-based models for presentation attack detection, evidencing a 21.70% decrease in average classification error rate (ACER) (from 41.03% to 19.32%) when the presentation attack domain is compared to the physiological and Deepfakes domains. Our experiments highlight the efficiency of transfer learning in rPPG-based models and perform well in presentation attack detection in instruments that do not allow copying of this physiological feature.
Open AccessPAD-Phys: Exploiting Physiology for Presentation Attack Detection in Face Biometrics
Presentation Attack Detection (PAD) is a crucial stage in facial recognition systems to avoid leakage of personal information or spoofing of identity to entities. Recently, pulse detection based on remote photoplethysmography (rPPG) has been shown to be effective in face presentation attack detection. This work presents three different approaches to the presentation attack detection based on rPPG: (i) The physiological domain, a domain using rPPG-based models, (ii) the Deepfakes domain, a domain where models were retrained from the physiological domain to specific Deepfakes detection tasks; and (iii) a new Presentation Attack domain was trained by applying transfer learning from the two previous domains to improve the capability to differentiate between bona-fides and attacks. The results show the efficiency of the rPPG-based models for presentation attack detection, evidencing a 21.70% decrease in average classification error rate (ACER) (from 41.03% to 19.32%) when the presentation attack domain is compared to the physiological and Deepfakes domains. Our experiments highlight the efficiency of transfer learning in rPPG-based models and perform well in presentation attack detection in instruments that do not allow copying of this physiological feature.
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (13) , 16422-16424
edBB-Demo: Biometrics and Behavior Analysis for Online Educational Platforms
We present edBB-Demo, a demonstrator of an AI-powered research platform for student monitoring in remote education. The edBB platform aims to study the challenges associated to user recognition and behavior understanding in digital platforms. This platform has been developed for data collection, acquiring signals from a variety of sensors including keyboard, mouse, webcam, microphone, smartwatch, and an Electroencephalography band. The information captured from the sensors during the student sessions is modelled in a multimodal learning framework. The demonstrator includes: i) Biometric user authentication in an unsupervised environment; ii) Human action recognition based on remote video analysis; iii) Heart rate estimation from webcam video; and iv) Attention level estimation from facial expression analysis.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (13) , 16422-16424
Open AccessedBB-Demo: Biometrics and Behavior Analysis for Online Educational Platforms
We present edBB-Demo, a demonstrator of an AI-powered research platform for student monitoring in remote education. The edBB platform aims to study the challenges associated to user recognition and behavior understanding in digital platforms. This platform has been developed for data collection, acquiring signals from a variety of sensors including keyboard, mouse, webcam, microphone, smartwatch, and an Electroencephalography band. The information captured from the sensors during the student sessions is modelled in a multimodal learning framework. The demonstrator includes: i) Biometric user authentication in an unsupervised environment; ii) Human action recognition based on remote video analysis; iii) Heart rate estimation from webcam video; and iv) Attention level estimation from facial expression analysis.
- Open Access
Toward Face Biometric De-identification using Adversarial Examples
The remarkable success of face recognition (FR) has endangered the privacy of internet users particularly in social media. Recently, researchers turned to use adversarial examples as a countermeasure. In this paper, we assess the effectiveness of using two widely known adversarial methods (BIM and ILLC) for de-identifying personal images. We discovered, unlike previous claims in the literature, that it is not easy to get a high protection success rate (suppressing identification rate) with imperceptible adversarial perturbation to the human visual system. Finally, we found out that the transferability of adversarial examples is highly affected by the training parameters of the network with which they are generated.
Open AccessToward Face Biometric De-identification using Adversarial Examples
The remarkable success of face recognition (FR) has endangered the privacy of internet users particularly in social media. Recently, researchers turned to use adversarial examples as a countermeasure. In this paper, we assess the effectiveness of using two widely known adversarial methods (BIM and ILLC) for de-identifying personal images. We discovered, unlike previous claims in the literature, that it is not easy to get a high protection success rate (suppressing identification rate) with imperceptible adversarial perturbation to the human visual system. Finally, we found out that the transferability of adversarial examples is highly affected by the training parameters of the network with which they are generated.
- Open Access
- 2 February 2023
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 18 (2) , e0281248
Exploring facial expressions and action unit domains for Parkinson detection
Background and objective: Patients suffering from Parkinson’s disease (PD) present a reduction in facial movements called hypomimia. In this work, we propose to use machine learning facial expression analysis from face images based on action unit domains to improve PD detection. We propose different domain adaptation techniques to exploit the latest advances in automatic face analysis and face action unit detection. Methods: Three different approaches are explored to model facial expressions of PD patients: (i) face analysis using single frame images and also using sequences of images, (ii) transfer learning from face analysis to action units recognition, and (iii) triplet-loss functions to improve the automatic classification between patients and healthy subjects. Results: Real face images from PD patients show that it is possible to properly model elicited facial expressions using image sequences (neutral, onset-transition, apex, offset-transition, and neutral) with accuracy improvements of up to 5.5% (from 72.9% to 78.4%) with respect to single-image PD detection. We also show that our proposed action unit domain adaptation provides improvements of up to 8.9% (from 78.4% to 87.3%) with respect to face analysis. Finally, we also show that triplet-loss functions provide improvements of up to 3.6% (from 78.8% to 82.4%) with respect to action unit domain adaptation applied upon models created from scratch. The code of the experiments is available at https://github.com/luisf-gomez/Explorer-FE-AU-in-PD. Conclusions: Domain adaptation via transfer learning methods seem to be a promising strategy to model hypomimia in PD patients. Considering the good results and also the fact that only up to five images per participant are considered in each sequence, we believe that this work is a step forward in the development of inexpensive computational systems suitable to model and quantify problems of PD patients in their facial expressions.
- 2 February 2023
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 18 (2) , e0281248
Open AccessExploring facial expressions and action unit domains for Parkinson detection
Background and objective: Patients suffering from Parkinson’s disease (PD) present a reduction in facial movements called hypomimia. In this work, we propose to use machine learning facial expression analysis from face images based on action unit domains to improve PD detection. We propose different domain adaptation techniques to exploit the latest advances in automatic face analysis and face action unit detection. Methods: Three different approaches are explored to model facial expressions of PD patients: (i) face analysis using single frame images and also using sequences of images, (ii) transfer learning from face analysis to action units recognition, and (iii) triplet-loss functions to improve the automatic classification between patients and healthy subjects. Results: Real face images from PD patients show that it is possible to properly model elicited facial expressions using image sequences (neutral, onset-transition, apex, offset-transition, and neutral) with accuracy improvements of up to 5.5% (from 72.9% to 78.4%) with respect to single-image PD detection. We also show that our proposed action unit domain adaptation provides improvements of up to 8.9% (from 78.4% to 87.3%) with respect to face analysis. Finally, we also show that triplet-loss functions provide improvements of up to 3.6% (from 78.8% to 82.4%) with respect to action unit domain adaptation applied upon models created from scratch. The code of the experiments is available at https://github.com/luisf-gomez/Explorer-FE-AU-in-PD. Conclusions: Domain adaptation via transfer learning methods seem to be a promising strategy to model hypomimia in PD patients. Considering the good results and also the fact that only up to five images per participant are considered in each sequence, we believe that this work is a step forward in the development of inexpensive computational systems suitable to model and quantify problems of PD patients in their facial expressions.
- Open Access
MATT: Multimodal Attention Level Estimation for e-learning Platforms
This work presents a new multimodal system for remote attention level estimation based on multimodal face analysis. Our multimodal approach uses different parameters and signals obtained from the behavior and physiological processes that have been related to modeling cognitive load such as faces gestures (e.g., blink rate, facial actions units) and user actions (e.g., head pose, distance to the camera). The multimodal system uses the following modules based on Convolutional Neural Networks (CNNs): Eye blink detection, head pose estimation, facial landmark detection, and facial expression features. First, we individually evaluate the proposed modules in the task of estimating the student's attention level captured during online e-learning sessions. For that we trained binary classifiers (high or low attention) based on Support Vector Machines (SVM) for each module. Secondly, we find out to what extent multimodal score level fusion improves the attention level estimation. The mEBAL database is used in the experimental framework, a public multi-modal database for attention level estimation obtained in an e-learning environment that contains data from 38 users while conducting several e-learning tasks of variable difficulty (creating changes in student cognitive loads).
Open AccessMATT: Multimodal Attention Level Estimation for e-learning Platforms
This work presents a new multimodal system for remote attention level estimation based on multimodal face analysis. Our multimodal approach uses different parameters and signals obtained from the behavior and physiological processes that have been related to modeling cognitive load such as faces gestures (e.g., blink rate, facial actions units) and user actions (e.g., head pose, distance to the camera). The multimodal system uses the following modules based on Convolutional Neural Networks (CNNs): Eye blink detection, head pose estimation, facial landmark detection, and facial expression features. First, we individually evaluate the proposed modules in the task of estimating the student's attention level captured during online e-learning sessions. For that we trained binary classifiers (high or low attention) based on Support Vector Machines (SVM) for each module. Secondly, we find out to what extent multimodal score level fusion improves the attention level estimation. The mEBAL database is used in the experimental framework, a public multi-modal database for attention level estimation obtained in an e-learning environment that contains data from 38 users while conducting several e-learning tasks of variable difficulty (creating changes in student cognitive loads).
- Open Access
edBB-Demo: Biometrics and Behavior Analysis for Online Educational Platforms
We present edBB-Demo, a demonstrator of an AI-powered research platform for student monitoring in remote education. The edBB platform aims to study the challenges associated to user recognition and behavior understanding in digital platforms. This platform has been developed for data collection, acquiring signals from a variety of sensors including keyboard, mouse, webcam, microphone, smartwatch, and an Electroencephalography band. The information captured from the sensors during the student sessions is modelled in a multimodal learning framework. The demonstrator includes: i) Biometric user authentication in an unsupervised environment; ii) Human action recognition based on remote video analysis; iii) Heart rate estimation from webcam video; and iv) Attention level estimation from facial expression analysis.
Open AccessedBB-Demo: Biometrics and Behavior Analysis for Online Educational Platforms
We present edBB-Demo, a demonstrator of an AI-powered research platform for student monitoring in remote education. The edBB platform aims to study the challenges associated to user recognition and behavior understanding in digital platforms. This platform has been developed for data collection, acquiring signals from a variety of sensors including keyboard, mouse, webcam, microphone, smartwatch, and an Electroencephalography band. The information captured from the sensors during the student sessions is modelled in a multimodal learning framework. The demonstrator includes: i) Biometric user authentication in an unsupervised environment; ii) Human action recognition based on remote video analysis; iii) Heart rate estimation from webcam video; and iv) Attention level estimation from facial expression analysis.
- Open Access
- 29 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (21) , 3533
Classical FE Analysis to Classify Parkinson’s Disease Patients
Parkinson’s disease (PD) is a neurodegenerative condition that affects the correct functioning of the motor system in the human body. Patients exhibit a reduced capability to produce facial expressions (FEs) among different symptoms, namely hypomimia. Being a disease so hard to be detected in its early stages, automatic systems can be created to help physicians in assessing and screening patients using basic bio-markers. In this paper, we present several experiments where features are extracted from images of FEs produced by PD patients and healthy controls. Classical machine learning methods such as local binary patterns and histograms of oriented gradients are used to model the images. Similarly, a well-known classification method, namely support vector machine is used for the discrimination between PD patients and healthy subjects. The most informative regions of the faces are found with a principal component analysis algorithm. Three different FEs were modeled: angry, happy, and surprise. Good results were obtained in most of the cases; however, happiness was the one that yielded better results, with accuracies of up to 80.4%. The methods used in this paper are classical and well-known by the research community; however, their main advantage is that they provide clear interpretability, which is valuable for many researchers and especially for clinicians. This work can be considered as a good baseline such that motivates other researchers to propose new methodologies that yield better results while keep the characteristic of providing interpretability.
- 29 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (21) , 3533
Open AccessClassical FE Analysis to Classify Parkinson’s Disease Patients
Parkinson’s disease (PD) is a neurodegenerative condition that affects the correct functioning of the motor system in the human body. Patients exhibit a reduced capability to produce facial expressions (FEs) among different symptoms, namely hypomimia. Being a disease so hard to be detected in its early stages, automatic systems can be created to help physicians in assessing and screening patients using basic bio-markers. In this paper, we present several experiments where features are extracted from images of FEs produced by PD patients and healthy controls. Classical machine learning methods such as local binary patterns and histograms of oriented gradients are used to model the images. Similarly, a well-known classification method, namely support vector machine is used for the discrimination between PD patients and healthy subjects. The most informative regions of the faces are found with a principal component analysis algorithm. Three different FEs were modeled: angry, happy, and surprise. Good results were obtained in most of the cases; however, happiness was the one that yielded better results, with accuracies of up to 80.4%. The methods used in this paper are classical and well-known by the research community; however, their main advantage is that they provide clear interpretability, which is valuable for many researchers and especially for clinicians. This work can be considered as a good baseline such that motivates other researchers to propose new methodologies that yield better results while keep the characteristic of providing interpretability.