• A real-world dataset was collected from ultra-distance runners at different locations in 2020 and 2023, introducing realistic long-term Re-ID challenges like domain shift and appearance changes. • A two-stream Re-ID model combining gait and human action recognition (HAR) features through a cross-attention fusion, enriching gait-based identity cues with behavior context. • The method significantly improves over gait-only baselines, with up to 12 % mAP gain in cross-year evaluations and 11.6 % in same-year evaluations. • Cross-attention fusion allows the model to prioritize gait information while adaptively integrating activity cues from HAR, leading to faster convergence and higher Rank-1 accuracy. • Experimental results show that the fusion of motion and behavior signals outperforms traditional appearance-based Re-ID and standalone gait methods, especially in unconstrained outdoor environments. We propose a two-stream person re-identification (Re-ID) framework that integrates gait and human action recognition (HAR) through cross-attention fusion. The model processes gait sequences via a BiLSTM-based encoder to capture temporal motion dynamics. At the same time, HAR embeddings are extracted using pre-trained video backbones and distilled into compact behavioral features. These two modalities are fused using a cross-attention mechanism, enriching gait-based identity representations with context-aware activity cues. We evaluate our method on a newly curated long-term spatio-temporal dataset of ultra-distance runners captured in natural outdoor settings across multiple locations spanning three years (2020 to 2023). Experimental results demonstrate that integrating HAR significantly enhances gait-based Re-ID performance. Compared to gait-only models, our approach yields a 12 % improvement in mean Average Precision (mAP) in cross-year scenarios and up to an 11.6 % gain in same-year evaluations. The HAR-enhanced models also exhibit faster convergence and higher Rank-1 accuracy, establishing the effectiveness of multi-modal motion-based representations for long-term, real-world person Re-ID.

Facial expression recognition (FER) is a key research area in computer vision and human-computer interaction. Despite recent advances, challenges persist, especially in generalizing to new scenarios. In fact, zero-shot FER significantly reduces the performance of state-of-the-art FER models. The community has recently started to explore the integration of knowledge from Large Language Models for visual tasks. In this work, we evaluate a broad collection of Visual Language Models (VLMs), avoiding the lack of task-specific knowledge by adopting a Visual Question Answering strategy. We compare the proposed pipeline with state-of-the-art FER models, both integrating and excluding VLMs, evaluating well-known FER benchmarks: AffectNet, FERPlus, and RAF-DB. The results show state-of-the-art performance for some VLMs in zero-shot FER scenarios, suggesting a research line for further exploration to improve FER generalization.

Emotion classification through EEG signals plays a significant role in psychology, neuroscience, and human-computer interaction. This paper addresses the challenge of mapping human emotions using EEG data in the Mapping Human Emotions through EEG Signals FG24 competition. Subjects mimic the facial expressions of an avatar, displaying fear, joy, anger, sadness, disgust, and surprise in a VR setting. EEG data is captured using a multi-channel sensor system to discern brain activity patterns. We propose a novel two-stream neural network employing a Bi-Hemispheric approach for emotion inference, surpassing baseline methods and enhancing emotion recognition accuracy. Additionally, we conduct a temporal analysis revealing that specific signal intervals at the beginning and end of the emotion stimulus sequence contribute significantly to improve accuracy. Leveraging insights gained from this temporal analysis, our approach offers enhanced performance in capturing subtle variations in the states of emotions. Code is available at https://github.com/davidfreire/FG24-EmoNeuroDB/

Person re-identification has gained significant attention in recent years due to its numerous practical applications in video surveillance. However, while artificial intelligence and deep learning methods have enabled substantial progress in particular aspects of this domain, putting together those individual advances to generate practical systems remains a computer vision challenge. Existing methods are typically designed assuming the target person’s images are captured under uniform, stable conditions with similar lighting levels, but this assumption may not hold in real-world scenarios, such as outdoor monitoring over 24 h, as image quality can vary considerably throughout day and night. In this paper, we propose a framework that incorporates image enhancement techniques to improve the performance of a person re-identification model. The proposed approach achieves a significant improvement in a demanding re-identification dataset, raising the mAP from 9.0% using a zero-shot baseline to 65.8% through the combined use of low-light image enhancement methods and noise reduction.

Re-identifying participants in ultra-distance running competitions can be daunting due to the extensive distances and constantly changing terrain. To overcome these challenges, computer vision techniques have been developed to analyze runners’ faces, numbers on their bibs, and clothing. However, our study presents a novel gait-based approach for runners’ re-identification (re-ID) by leveraging various pre-trained human action recognition (HAR) models and loss functions. Our results show that this approach provides promising results for re-identifying runners in ultra-distance competitions. Furthermore, we investigate the significance of distinct human body movements when athletes are approaching their endurance limits and their potential impact on re-ID accuracy. Our study examines how the recognition of a runner’s gait is affected by a competition’s critical point (CP), defined as a moment of severe fatigue and the point where the finish line comes into view, just a few kilometers away from this location. We aim to determine how this CP can improve the accuracy of athlete re-ID. Our experimental results demonstrate that gait recognition can be significantly enhanced (up to a 9% increase in mAP) as athletes approach this point. This highlights the potential of utilizing gait recognition in real-world scenarios, such as ultra-distance competitions or long-duration surveillance tasks.

An article published on Medical News Today in June 2022 presented a \nfundamental question in its title: Can an earlobe crease predict heart attacks? \nThe author explained that end arteries supply the heart and ears. In other \nwords, if they lose blood supply, no other arteries can take over, resulting in \ntissue damage. Consequently, some earlobes have a diagonal crease, line, or \ndeep fold that resembles a wrinkle. In this paper, we take a step toward \ndetecting this specific marker, commonly known as DELC or Frank's Sign. For \nthis reason, we have made the first DELC dataset available to the public. In \naddition, we have investigated the performance of numerous cutting-edge \nbackbones on annotated photos. Experimentally, we demonstrate that it is \npossible to solve this challenge by combining pre-trained encoders with a \ncustomized classifier to achieve 97.7% accuracy. Moreover, we have analyzed the \nbackbone trade-off between performance and size, estimating MobileNet as the \nmost promising encoder.

Person re-identification (ReID) is a trending topic in computer vision. Significant developments have been achieved, but most rely on datasets with subjects captured statically within a short period of time in rather good lighting conditions. In the wild scenarios, such as long-distance races that involve widely varying lighting conditions, from full daylight to night, present a considerable challenge. This issue cannot be addressed by increasing the exposure time on the capture device, as the runners' motion will lead to blurred images, hampering any ReID attempts. In this paper, we survey some low-light image enhancement methods. Our results show that including an image processing step in a ReID pipeline before extracting the distinctive body appearance features from the subjects can provide significant performance improvements.

The scientific community and mass media have already reported the use of nonverbal behavior analysis in sports for athletes' performance. Their conclusions stated that certain emotional expressions are linked to athlete's performance, or even that psychological strategies serve to improve endurance performance. This paper examines the portrayal of well-known emotions and their relationship to the participants of an ultra-distance race in a high-stake environment. For this purpose, we analyzed almost 600 runners captured when they passed through a set of locations placed along the race track. We have observed a correlation between the runners' facial expressions and their performance along the track. Moreover, we have analyzed Action Unit activations and aligned our findings with the state-of-the-art psychological baseline.

Predicting an athlete’s performance based on short footage is highly challenging. Performance prediction requires high domain knowledge and enough evidence to infer an appropriate quality assessment. Sports pundits can often infer this kind of information in real-time. In this paper, we propose regressing an ultra-distance runner cumulative race time (CRT), i.e., the time the runner has been in action since the race start, by using only a few seconds of footage as input. We modified the I3D ConvNet backbone slightly and trained a newly added regressor for that purpose. We use appropriate pre-processing of the visual input to enable transfer learning from a specific runner. We show that the resulting neural network can provide a remarkable performance for short input footage: 18 minutes and a half mean absolute error in estimating the CRT for runners who have been in action from 8 to 20 hours. Our methodology has several favorable properties: it does not require a human expert to provide any insight, it can be used at any moment during the race by just observing a runner, and it can inform the race staff about a runner at any given time.

This paper extends the performance assessment of an underwater glider path planning approach recently proposed for constrained sub-mesoscale eddy border sampling conditions, for situations benefiting from extended mission planning time. The aim of addressing such situations is to improve the glider vehicle capabilities through improving its off-board controller, which computes an improved trajectory for the eddy sampling task, compared to the usual rather shorter planning time. The improvement in robustness for the controller for several scenarios in this global trajectory optimization is also analyzed, together with comparison to shorter planning time for this autonomous vehicle and environmental data sampling type. As shown through results, the approach is able to provide several useful and non-intuitive solutions, improving in helpful ways. The trajectories for sub-mesoscale eddy sampling are thereby improved, in a way that might be useful for possible machine controller pondering or auto-piloting at open sea, when piloting user feedback is not available or even amidst the consecutive interruptions of user-intensive planning instructions. Managing complexity under limited resources and designing vessel navigation schedule plan under uncertain conditions within such extended mission planning time, therefore improves the mission quality as well. By optimizing trajectories with differential evolution and then visualizing them, we provide human-machine interaction for rapid knowledge discovery, data mining, and presentation of possibly large space satellite captured data sets (Big Data) analysis and exploitation.

The automatic extraction of biometric descriptors of anonymous people is a challenging scenario in camera networks. This task is typically accomplished making use of visual information. Calibrated RGBD sensors make possible the extraction of point cloud information. We present a novel approach for people semantic description and re-identification using the individual point cloud information. The proposal combines the use of simple geometric features with point cloud features based on surface normals. To test the system validity, we have collected a new and challenging dataset using a RGBD sensor in a top view configuration containing up to 63 identities captured in different sessions in different days within a two weeks period. The results achieved outperform the previous literature based exclusively on geometric features for re-identification, providing additionally very promising results in people description related to gender and hair style.

Unmanned Underwater Vehicles (UUVs) are commonly used in Oceanography due to their relative low cost and wide range of capabilities. Gliders are a type of UUV particularly suitable for long-range missions because of their large autonomy. They change their buoyancy to dive and climb describing a vertical saw tooth pattern, which produces an effective but low horizontal speed. Consequently, gliders are strongly sensitive to ocean currents, so they might have to adapt the heading to the current field. In this article we outline a novel path planning algorithm for gliders using ocean currents. It bases on the A* family of algorithms and incorporates a probabilistic framework. Our approach intends to alleviate some of the drawbacks that A* has with the problem at hand. Instead of discretizing the search space, a set of bearing angles is sampled at each surfacing point and the glider trajectory is integrated. We propose an Adaptive Bearing Sampling (ABS) procedure which reduces the computational time with low impact on the results, as shown by the tests run with ocean currents of a Regional Ocean Model.

Underwater gliders constitute a technology in active development, which has proven very promising in Ocean Research because of its relative low cost and long mission range. Due to their low surge speed, however, gliders are strongly affected by ocean currents, making path planning a crucial tool for this type of vehicles. In this work, we present a novel path planning algorithm for gliders based on iterative optimization that shows promising results in realistic simulations. This method reflects accurately the vehicle operation pattern and exhibits a better performance when compared with alternative approaches that are compared in this paper.

The development and maintenance of software for robotic systems is a hard task due to the complexity inherent in these systems. Besides, the resulting applications have to deal with limited resources and variable execution conditions that must be considered in order to keep an acceptable system performance. To address both problems we have integrated a set of dynamic adaptation policies inside CoolBOT, a component oriented framework for programming robotic systems. CoolBOT contributes to reduce the programming effort, promoting robustness and code reuse, while the adaptation scheme provides a dynamic modulation of system performance to meet available computational resources at runtime. In this paper we also present two demonstrators that outline the benefits of using the proposed approach in the development of real robotic applications.

Developing software for controlling robotic systems is costly due to the complexity inherent in these systems. There is a need for tools that permit a reduction in the programming efforts, aiming at the generation of modular and robust applications, and promoting software reuse. The techniques which are of common use today in other areas are not adequate to deal with the complexity associated with these systems. In this work we present CoolBOT, a component oriented framework for programming robotic systems, based on the Port Automata model that fosters controllability and observability of software components. A simple demonstrator outlines the benefits of using the proposed approach in the development of a robotic application.

SVEX is a multilevel knowledge-based tool for developing applications in image segmentation. Both numerical and symbolic computations take place at each level, being the transition between these two domains defined by the computational structure itself. SVEX incorporates evidence combination and uncertainty control mechanisms. SVEX is programmed by means of a specific purpose declarative language based on a reduced set of objects. All the knowledge involved in the solution of a given segmentation problem is made explicit due to the declarative nature of the programming language. The results obtained by the application of SVEX in the segmentation of a set of outdoor images set are also shown.