Narciso Garcia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Narciso Garcia has a total of 317 co-authors. Here are the top co-authors by number of shared publications:
- Fernando Jaureguizar
Grupo de Tratamiento de Imgenes (GTI), Information Processing and Telecommunications Center, ETSI Telecomunicacin, Universidad Politcnica de Madrid, Madrid, Spain
90 shared publications - Julian Cabrera
Grupo de Tratamiento de Imagenes, Information Processing and Telecommunications Center, ETSI Telecomunicacion, Universidad Politecnica de Madrid, Madrid, Spain
62 shared publications - Carlos Roberto del Blanco
Grupo de Tratamiento de Imgenes (GTI), Information Processing and Telecommunications Center, ETSI Telecomunicacin, Universidad Politcnica de Madrid, Madrid, Spain
57 shared publications - Carlos Cuevas
Grupo de Tratamiento de Imgenes (GTI), Information Processing and Telecommunications Center (IPTC), ETSI Telecomunicacin, Universidad Politcnica de Madrid (UPM), Madrid, Spain
43 shared publications - Luis Salgado
Universidad Politécnica de Madrid
29 shared publications - Jesus Gutierrez
ETSI Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain
26 shared publications
Latest Publications
- 9 October 2026
- Published by Springer Nature
- p. 260-270
Adaptive Query-Conditional Fusion for Egocentric Natural Language Query Grounding
- 9 October 2026
- Published by Springer Nature
- p. 260-270
Adaptive Query-Conditional Fusion for Egocentric Natural Language Query Grounding
- Open Access
- 8 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 697-700
Immersive remote learning for individuals with intellectual disabilities
- 8 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 697-700
Open AccessImmersive remote learning for individuals with intellectual disabilities
- Open Access
- 23 March 2026
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 117
Viewpoint-invariant soccer pitch registration using geometric and learned features
- 23 March 2026
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 117
Open AccessViewpoint-invariant soccer pitch registration using geometric and learned features
- Open Access
- 12 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 210996-211009
Text-Guided Sports Highlights: A CLIP-Based Framework for Automatic Video Summarization
We present a text-guided framework for automatic sports video summarization that leverages Contrastive Language–Image Pretraining to classify frames as highlight or non-highlight from natural-language descriptions. The pipeline generates multiple highlight/non-highlight sentence pairs with a large language model, removes weak candidates via distribution- and area-based filters, averages the remaining framewise predictions, and refines events through lightweight post-processing. We further introduce Sport-CLIP, a multi-sport benchmark (diving, long jump, pole vault, tumbling) designed to probe robustness across distinct motion patterns and highlight durations. Comprehensive experiments on MATDAT (tricking) and SportCLIP showthat the method achieves consistent, high-quality summarization: an overall average F-score of 84.08% across sports using a single parameter set, with 91.05% and 87.98% on pole vault and long jump, respectively. Parameter sweeps indicate stable performance over a broad range of smoothing windows and filtering thresholds, underscoring resilience to moderate setting changes. Because the approach is training-free and prompt-driven, it integrates readily into consumer-electronics pipelines (e.g., cloud or mobile media platforms) and adapts to new sports and user intents by editing text prompts rather than retraining models. Code and data are publicly available at www.gti.ssr.upm.es/data.
- 12 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 210996-211009
Open AccessText-Guided Sports Highlights: A CLIP-Based Framework for Automatic Video Summarization
We present a text-guided framework for automatic sports video summarization that leverages Contrastive Language–Image Pretraining to classify frames as highlight or non-highlight from natural-language descriptions. The pipeline generates multiple highlight/non-highlight sentence pairs with a large language model, removes weak candidates via distribution- and area-based filters, averages the remaining framewise predictions, and refines events through lightweight post-processing. We further introduce Sport-CLIP, a multi-sport benchmark (diving, long jump, pole vault, tumbling) designed to probe robustness across distinct motion patterns and highlight durations. Comprehensive experiments on MATDAT (tricking) and SportCLIP showthat the method achieves consistent, high-quality summarization: an overall average F-score of 84.08% across sports using a single parameter set, with 91.05% and 87.98% on pole vault and long jump, respectively. Parameter sweeps indicate stable performance over a broad range of smoothing windows and filtering thresholds, underscoring resilience to moderate setting changes. Because the approach is training-free and prompt-driven, it integrates readily into consumer-electronics pipelines (e.g., cloud or mobile media platforms) and adapts to new sports and user intents by editing text prompts rather than retraining models. Code and data are publicly available at www.gti.ssr.upm.es/data.
- Open Access
- 31 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 346-349
Immersive Cognitive Training for Job Integration with people with Intellectual Disabilities
- 31 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 346-349
Open AccessImmersive Cognitive Training for Job Integration with people with Intellectual Disabilities
- Open Access
- 31 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 126-138
A Study on Immersive Behavioral Therapy for Individuals with Intellectual Disabilities with Fear of Stairs
- 31 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 126-138
Open AccessA Study on Immersive Behavioral Therapy for Individuals with Intellectual Disabilities with Fear of Stairs
- Open Access
- 31 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 175-186
The Impact of Segmentation Methods for Avatar representation on User Experience in a Task-Based XR experience
- 31 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 175-186
Open AccessThe Impact of Segmentation Methods for Avatar representation on User Experience in a Task-Based XR experience
- Open Access
- 12 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (9) , 13799-13810
TOP-Former: A Multi-Agent Transformer Approach for the Team Orienteering Problem
Route planning for a fleet of vehicles is an important task in applications such as package delivery, surveillance, or transportation, often integrated within larger Intelligent Transportation Systems (ITS). This problem is commonly formulated as a Vehicle Routing Problem (VRP) known as the Team Orienteering Problem (TOP). Existing solvers for this problem primarily rely on either linear programming, which provides accurate solutions but requires computation times that grow with the size of the problem, or heuristic methods, which typically find suboptimal solutions in a shorter time. In this paper, we introduce TOP-Former, a multi-agent route planning neural network designed to efficiently and accurately solve the Team Orienteering Problem. The proposed algorithm is based on a centralized Transformer neural network capable of learning to encode the scenario (modeled as a graph) and analyze the complete context of all agents to deliver fast, precise, and collaborative solutions. Unlike other neural network-based approaches that adopt a more local perspective, TOP-Former is trained to understand the global situation of the vehicle fleet and generate solutions that maximize long-term expected returns. Extensive experiments demonstrate that the presented system outperforms most state-of-the-art methods in terms of both accuracy and computation speed.
- 12 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (9) , 13799-13810
Open AccessTOP-Former: A Multi-Agent Transformer Approach for the Team Orienteering Problem
Route planning for a fleet of vehicles is an important task in applications such as package delivery, surveillance, or transportation, often integrated within larger Intelligent Transportation Systems (ITS). This problem is commonly formulated as a Vehicle Routing Problem (VRP) known as the Team Orienteering Problem (TOP). Existing solvers for this problem primarily rely on either linear programming, which provides accurate solutions but requires computation times that grow with the size of the problem, or heuristic methods, which typically find suboptimal solutions in a shorter time. In this paper, we introduce TOP-Former, a multi-agent route planning neural network designed to efficiently and accurately solve the Team Orienteering Problem. The proposed algorithm is based on a centralized Transformer neural network capable of learning to encode the scenario (modeled as a graph) and analyze the complete context of all agents to deliver fast, precise, and collaborative solutions. Unlike other neural network-based approaches that adopt a more local perspective, TOP-Former is trained to understand the global situation of the vehicle fleet and generate solutions that maximize long-term expected returns. Extensive experiments demonstrate that the presented system outperforms most state-of-the-art methods in terms of both accuracy and computation speed.
- Open Access
AnimalMotionCLIP: Embedding motion in CLIP for Animal Behavior Analysis
Recently, there has been a surge of interest in applying deep learning techniques to animal behavior recognition, particularly leveraging pre-trained visual language models, such as CLIP, due to their remarkable generalization capacity across various downstream tasks. However, adapting these models to the specific domain of animal behavior recognition presents two significant challenges: integrating motion information and devising an effective temporal modeling scheme. In this paper, we propose AnimalMotionCLIP to address these challenges by interleaving video frames and optical flow information in the CLIP framework. Additionally, several temporal modeling schemes using an aggregation of classifiers are proposed and compared: dense, semi dense, and sparse. As a result, fine temporal actions can be correctly recognized, which is of vital importance in animal behavior analysis. Experiments on the Animal Kingdom dataset demonstrate that AnimalMotionCLIP achieves superior performance compared to state-of-the-art approaches.
Open AccessAnimalMotionCLIP: Embedding motion in CLIP for Animal Behavior Analysis
Recently, there has been a surge of interest in applying deep learning techniques to animal behavior recognition, particularly leveraging pre-trained visual language models, such as CLIP, due to their remarkable generalization capacity across various downstream tasks. However, adapting these models to the specific domain of animal behavior recognition presents two significant challenges: integrating motion information and devising an effective temporal modeling scheme. In this paper, we propose AnimalMotionCLIP to address these challenges by interleaving video frames and optical flow information in the CLIP framework. Additionally, several temporal modeling schemes using an aggregation of classifiers are proposed and compared: dense, semi dense, and sparse. As a result, fine temporal actions can be correctly recognized, which is of vital importance in animal behavior analysis. Experiments on the Animal Kingdom dataset demonstrate that AnimalMotionCLIP achieves superior performance compared to state-of-the-art approaches.
- Open Access
- 6 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 44817-44835
Enhanced Nighttime Vehicle Detection for On-Board Processing
Nighttime vehicle detection poses significant challenges, particularly in scenarios with limited lighting, where visibility is often compromised. To address this problem, this paper proposes a novel nighttime vehicle detection system that dynamically adapts to extreme lighting conditions, ranging from bright daytime scenarios to challenging nighttime conditions where the vehicle’s appearance may be entirely lost. For this purpose, a multi-granularity detection approach is adopted, automatically combining bounding-box and point-based representations depending on the vehicle’s visibility. Bounding-box detections, reporting location and size information, are selected when the vehicle appearance is mostly visible, such as in daytime or urban nighttime scenarios with sufficient artificial street illumination. Point-based detections, indicating only location information, are used when the vehicle’s appearance is not discernible, such as in rural nighttime scenarios with little or no street illumination. The system is designed as a multi-head neural network built on a shared Hourglass backbone that accepts bounding-box and point-based annotations for training and can automatically predict, depending on the scenario, vehicle bounding boxes or point-based predictions. Extensive evaluations on a combined dataset of BDD100K and PVDN demonstrate that the proposed system achieves higher detection accuracy and robustness compared to existing methods, with mean Average Precision (mAP) scores of 0.7134 on BDD100K, 0.6621 on PVDN, and 0.6814 on the combined dataset. Additionally, a self-acquired dataset, FNTVD, further enhances the evaluation by providing real-world driving conditions. The system also achieves real-time performance at 45.45 FPS, making it suitable for practical applications.
- 6 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 44817-44835
Open AccessEnhanced Nighttime Vehicle Detection for On-Board Processing
Nighttime vehicle detection poses significant challenges, particularly in scenarios with limited lighting, where visibility is often compromised. To address this problem, this paper proposes a novel nighttime vehicle detection system that dynamically adapts to extreme lighting conditions, ranging from bright daytime scenarios to challenging nighttime conditions where the vehicle’s appearance may be entirely lost. For this purpose, a multi-granularity detection approach is adopted, automatically combining bounding-box and point-based representations depending on the vehicle’s visibility. Bounding-box detections, reporting location and size information, are selected when the vehicle appearance is mostly visible, such as in daytime or urban nighttime scenarios with sufficient artificial street illumination. Point-based detections, indicating only location information, are used when the vehicle’s appearance is not discernible, such as in rural nighttime scenarios with little or no street illumination. The system is designed as a multi-head neural network built on a shared Hourglass backbone that accepts bounding-box and point-based annotations for training and can automatically predict, depending on the scenario, vehicle bounding boxes or point-based predictions. Extensive evaluations on a combined dataset of BDD100K and PVDN demonstrate that the proposed system achieves higher detection accuracy and robustness compared to existing methods, with mean Average Precision (mAP) scores of 0.7134 on BDD100K, 0.6621 on PVDN, and 0.6814 on the combined dataset. Additionally, a self-acquired dataset, FNTVD, further enhances the evaluation by providing real-world driving conditions. The system also achieves real-time performance at 45.45 FPS, making it suitable for practical applications.