Search Results (12)

Sport Vision is a speciality of multidisciplinary interest aimed at improving the performance of the visual system to achieve benefits in practiced sports, as well as in daily life and in preventive care. The type of training practiced by the athlete, his or her physical condition, cognitive level, and level of fatigue condition affects the speed of the reaction time and, consequently, the speed of motor response. Specific orthoptic exercises, the use of technological devices, the recovery of static and dynamic postural stability by using unstable platforms and the dual-task paradigm can help to achieve the expected results. The aim of this systematic review of Sport Vision was to assess the overall existing literature on Sport Vision, paying particular attention to the effects of visual training and its application in different sports and in rehabilitation and preventive settings. We analysed published English language studies about the role of sport vision in athletic performance from 1950 to 2023. We searched through the Medline database. The PRISMA 2020 checklist was used to assess the transparency and reproducibility of this review. The enrolled papers were evaluated with the Jadad Scale, Amstar 2 Scale and Newcastle–Ottawa Scale. 25 (16 studies, 5 reviews, 2 comments, 1 editorial, 1 descriptive paper) out of 476 studies met the inclusion criteria. Due to the variability in the age of the samples, the different techniques, the treatments among the participants in the studies and the finding of non-evaluable articles, a meta-analysis was not conducted. The limitations of this review are the single database research, the studies analyzed contain a non-statistically representative sample size and the lack of a control group. There is no standardized test to measure performance. It was shown that the development of visual skills can benefit athletes in injury prevention, and can lead to improved sports performance and motor function at any age, acquiring adaptive motor behaviour even when the visual system is impaired, due to task repetition and familiarity of the gesture. We intended to identify a multidisciplinary approach and a manual treatment scheme to optimize the circuitry involved in sport vision in order to increase the results that are achieved, but further studies will be needed to this end. Full article

The generation of co-speech gestures for digital humans is an emerging area in the field of virtual human creation. Prior research has progressed by using acoustic and semantic information as input and adopting a classification method to identify the person’s ID and emotion for driving co-speech gesture generation. However, this endeavor still faces significant challenges. These challenges go beyond the intricate interplay among co-speech gestures, speech acoustic, and semantics; they also encompass the complexities associated with personality, emotion, and other obscure but important factors. This paper introduces “DiT-Gestures”, a speech-conditional diffusion-based and non-autoregressive transformer-based generative model with the WavLM pre-trained model and a dynamic mask attention network (DMAN). It can produce individual and stylized full-body co-speech gestures by only using raw speech audio, eliminating the need for complex multimodal processing and manual annotation. Firstly, considering that speech audio contains acoustic and semantic features and conveys personality traits, emotions, and more subtle information related to accompanying gestures, we pioneer the adaptation of WavLM, a large-scale pre-trained model, to extract the style from raw audio information. Secondly, we replace the causal mask by introducing a learnable dynamic mask for better local modeling in the neighborhood of the target frames. Extensive subjective evaluation experiments are conducted on the Trinity, ZEGGS, and BEAT datasets to confirm WavLM’s and the model’s ability to synthesize natural co-speech gestures with various styles. Full article

The use of back propagation through the time learning rule enabled the supervised training of deep spiking neural networks to process temporal neuromorphic data. However, their performance is still below non-spiking neural networks. Previous work pointed out that one of the main causes is the limited number of neuromorphic data currently available, which are also difficult to generate. With the goal of overcoming this problem, we explore the usage of auxiliary learning as a means of helping spiking neural networks to identify more general features. Tests are performed on neuromorphic DVS-CIFAR10 and DVS128-Gesture datasets. The results indicate that training with auxiliary learning tasks improves their accuracy, albeit slightly. Different scenarios, including manual and automatic combination losses using implicit differentiation, are explored to analyze the usage of auxiliary tasks. Full article

A student’s engagement in a real classroom environment usually varies with respect to time. Moreover, both genders may also engage differently during lecture procession. Previous research measures students’ engagement either from the assessment outcome or by observing their gestures in online or real but controlled classroom environments with limited students. However, most works either manually assess the engagement level in online class environments or use limited features for automatic computation. Moreover, the demographic impact on students’ engagement in the real classroom environment is limited and needs further exploration. This work is intended to compute student engagement in a real but least controlled classroom environment with 45 students. More precisely, the main contributions of this work are twofold. First, we proposed an efficient transfer-learning-based VGG16 model with extended layer, and fine-tuned hyperparameters to compute the students’ engagement level in a real classroom environment. Overall, 90% accuracy and 0.5 N seconds computational time were achieved in terms of computation for engaged and non-engaged students. Subsequently, we incorporated inferential statistics to measure the impact of time while performing 14 experiments. We performed six experiments for gender impact on students’ engagement. Overall, inferential analysis reveals the positive impact of time and gender on students’ engagement levels in a real classroom environment. The comparisons were also performed by various transfer learning algorithms. The proposed work may help to improve the quality of educational content delivery and decision making for educational institutions. Full article

Sign language is the main channel for hearing-impaired people to communicate with others. It is a visual language that conveys highly structured components of manual and non-manual parameters such that it needs a lot of effort to master by hearing people. Sign language recognition aims to facilitate this mastering difficulty and bridge the communication gap between hearing-impaired people and others. This study presents an efficient architecture for sign language recognition based on a convolutional graph neural network (GCN). The presented architecture consists of a few separable 3DGCN layers, which are enhanced by a spatial attention mechanism. The limited number of layers in the proposed architecture enables it to avoid the common over-smoothing problem in deep graph neural networks. Furthermore, the attention mechanism enhances the spatial context representation of the gestures. The proposed architecture is evaluated on different datasets and shows outstanding results. Full article

At a language’s inception, what determines which elements are taken up to build a grammar? How is the initial raw material reshaped through intergenerational language learning? We approached this question by focusing on the emergence of non-manual wh-question markers in Nicaraguan Sign Language (LSN), a young sign language. We asked whether the seeds of non-manual markers originate in the facial gestures of the hearing Nicaraguan community, and we explored the iterated process by which a form becomes selected and then systematized through generational transmission. We identified six non-manual facial and body movements produced with questions by 34 deaf LSN signers, representing three sequential age cohorts of learners, and compared them to those produced by 16 non-signing Spanish speakers. We examined the frequency and duration of each non-manual, and its temporal overlap with a question word. One non-manual, the brow furrow, was overwhelmingly represented among LSN signers, despite appearing rarely among non-signers and not being initially favored in duration or temporal overlap. With the second and third cohorts, the brow furrow emerges as a frequent and systematic marker. With each cycle of child learners, variable input was transformed into a more constrained set of grammatical forms. Full article

Typological comparisons have revealed that signers can use manual elements and/or a non-manual marker to express standard negation, but little is known about how such systematic marking emerges from its gestural counterparts as a new sign language arises. We analyzed 1.73 h of spontaneous language data, featuring six deaf native signers from generations III-V of the sign language isolate Kata Kolok (Bali). These data show that Kata Kolok cannot be classified as a manual dominant or non-manual dominant sign language since both the manual negative sign and a side-to-side headshake are used extensively. Moreover, the intergenerational comparisons indicate a considerable increase in the use of headshake spreading for generation V which is unlikely to have resulted from contact with Indonesian Sign Language varieties. We also attest a specialized negative existential marker, namely, tongue protrusion, which does not appear in co-speech gesture in the surrounding community. We conclude that Kata Kolok is uniquely placed in the typological landscape of sign language negation, and that grammaticalization theory is essential to a deeper understanding of the emergence of grammatical structure from gesture. Full article

Catarrhine primates gesture preferentially with their right hands, which led to the hypothesis of a gestural origin of human left-hemispheric specialization for language. However, the factors influencing this gestural laterality remain understudied in non-hominoid species, particularly in intraspecific contexts, although it may bring valuable insights into the proximate and ultimate causes of language lateralization. We present here a preliminary investigation of intraspecific gestural laterality in catarrhine monkeys, red-capped mangabeys (Cercocebus torquatus). We described the spontaneous production of brachio-manual intentional gestures in twenty-five captive subjects. Although we did not evidence any significant gestural lateralization neither at the individual- nor population-level, we found that mangabeys preferentially use their right hands to gesture in negative social contexts, such as aggressions, suggesting an effect of emotional lateralization, and that they adapt to the position of their receiver by preferentially using their ipsilateral hand to communicate. These results corroborate previous findings from ape studies. By contrast, factors related to gesture form and socio-demographic characteristics of signaler and receiver did not affect gestural laterality. To understand better the relationships between gestural laterality and brain lateralization from an evolutionary perspective, we suggest that the gestural communication of other monkey species should be examined with a multifactorial approach. Full article

Sign languages are the main visual communication medium between hard-hearing people and their societies. Similar to spoken languages, they are not universal and vary from region to region, but they are relatively under-resourced. Arabic sign language (ArSL) is one of these languages that has attracted increasing attention in the research community. However, most of the existing and available works on sign language recognition systems focus on manual gestures, ignoring other non-manual information needed for other language signals such as facial expressions. One of the main challenges of not considering these modalities is the lack of suitable datasets. In this paper, we propose a new multi-modality ArSL dataset that integrates various types of modalities. It consists of 6748 video samples of fifty signs performed by four signers and collected using Kinect V2 sensors. This dataset will be freely available for researchers to develop and benchmark their techniques for further advancement of the field. In addition, we evaluated the fusion of spatial and temporal features of different modalities, manual and non-manual, for sign language recognition using the state-of-the-art deep learning techniques. This fusion boosted the accuracy of the recognition system at the signer-independent mode by 3.6% compared with manual gestures. Full article

Distracted driving has become a major cause of road traffic accidents. There are generally four different types of distractions: manual, visual, auditory, and cognitive. Manual distractions are the most common. Previous studies have used physiological indicators, vehicle behavior parameters, or machine-visual features to support research. However, these technologies are not suitable for an in-vehicle environment. To address this need, this study examined a non-intrusive method for detecting in-transit manual distractions. Wrist kinematics data from 20 drivers were collected using wearable inertial measurement units (IMU) to detect four common gestures made while driving: dialing a hand-held cellular phone, adjusting the audio or climate controls, reaching for an object in the back seat, and maneuvering the steering wheel to stay in the lane. The study proposed a progressive classification model for gesture recognition, including two major time-based sequencing components and a Hidden Markov Model (HMM). Results show that the accuracy for detecting disturbances was 95.52%. The accuracy associated with recognizing manual distractions reached 96.63%, using the proposed model. The overall model has the advantages of being sensitive to perceptions of motion, effectively solving the problem of a fall-off in recognition performance due to excessive disturbances in motion samples. Full article

The integration of greater functionalities into vehicles increases the complexity of car-controlling. Many research efforts are dedicated to designing car-controlling systems that allow users to instruct the car just to show it what it should do; however, for non-expert users, controlling the car with a remote or a switch is complicated. So, keeping this in mind, this paper presents an Arduino based car-controlling system that no longer requires manual control of the cars. Two main contributions are presented in this work. Firstly, we show that the car can be controlled with hand-gestures, according to the movement and position of the hand. The hand-gesture system works with an Arduino Nano, accelerometer, and radio-frequency (RF) transmitter. The accelerometer (attached with the hand-glove) senses the acceleration forces that are produced by the hand movement, and it will transfer the data to the Arduino Nano that is placed on hand glove. After receiving the data, Arduino Nano will convert it into different angle values in ranges of 0–450° and send the data to the RF receiver of the Arduino Uno, which is placed on the car through the RF transmitter. Secondly, the proposed car system is to be controlled by an android based mobile-application with different modes (e.g., touch buttons mode, voice recognition mode). The mobile-application system is the extension of the hand-gesture system with the addition of Bluetooth module. In this case, whenever the user presses any of the touch buttons in the application, and/or gives voice commands, the corresponding signal is sent to the Arduino Uno. After receiving the signal, Arduino will check this against its predefined instructions for moving forward, backward, left, right, and brake; then it will send the command to the motor module to move the car in the corresponding direction. In addition, an automatic obstacle detection system is introduced to improve the safety measurements to avoid any hazards with the help of sensors placed at the front of the car. The proposed systems are designed as a lab-scale prototype to experimentally validate the efficiency, accuracy, and affordability of the systems. The experimental results prove that the proposed work has all in one capability (hand-gesture, touch buttons and voice-recognition with mobile-application, obstacle detection), is very easy to use, and can be easily assembled in a simple hardware circuit. We remark that the proposed systems can be implemented under real conditions at large-scale in the future, which will be useful in automobiles and robotics applications. Full article

Every year, a significant number of people lose a body part in an accident, through sickness or in high-risk manual jobs. Several studies and research works have tried to reduce the constraints and risks in their lives through the use of technology. This work proposes a learning-based approach that performs gesture recognition using a surface electromyography-based device, the Myo Armband released by Thalmic Labs, which is a commercial device and has eight non-intrusive low-cost sensors. With 35 able-bodied subjects, and using the Myo Armband device, which is able to record data at about 200 MHz, we collected a dataset that includes six dissimilar hand gestures. We used a gated recurrent unit network to train a system that, as input, takes raw signals extracted from the surface electromyography sensors. The proposed approach obtained a 99.90% training accuracy and 99.75% validation accuracy. We also evaluated the proposed system on a test set (new subjects) obtaining an accuracy of 77.85%. In addition, we showed the test prediction results for each gesture separately and analyzed which gestures for the Myo armband with our suggested network can be difficult to distinguish accurately. Moreover, we studied for first time the gated recurrent unit network capability in gesture recognition approaches. Finally, we integrated our method in a system that is able to classify live hand gestures. Full article