Arbitrary Gestures Research Articles

User-Definable Dynamic Hand Gesture Recognition Based on Doppler Radar and Few-Shot Learning

In recent years, the radar-based dynamic hand gesture recognition (DHGR) system has been widely used in the non-contact interaction with smart electronic devices because of its advantages of safety, privacy security and robustness to different illumination environments. In order to achieve high-precision gesture recognition, Machine Learning algorithms, especially the deep learning algorithms are generally chosen by researchers. However, most deep learning models are trained based on large gesture dataset and only accept certain predefined specified gestures as input, i.e., user-defined gestures are not allowed. In this work, a neural network model trained with meta-learning method is proposed to deal with the few-shot classification task and realize the user-definable DHGR. Instead of learning a mapping between the unknown input gesture and the fixed predefined classes, the proposed model is trained to learn to compare the input gesture with arbitrary gestures entered by users, and then decide which class of gesture is the most probable one. Without retraining, the model can allow the user to enter the self-defined gestures for one or a few times and then recognize these gestures next time. To the best of our knowledge, this is the first work to apply the meta few-shot learning to the DHGR problem in the true sense. In this model, an embedding module is used in the network to extract the features of the input micro-Doppler spectrograms, and a comparison module is used to execute the feature-level comparison. Finally, a weighting module is proposed to weigh the comparison results and make the prediction. The evaluation result shows that with only one support sample for each class (i.e., for the one-shot tasks), the proposed model achieves an accuracy of 91% for 5 gesture classes and 90% for 10 gesture classes. When using 3 support samples (i.e., for the 3-shot tasks), the accuracies for 5 and 10 gestures are further improved to 96% and 92%, respectively.

Dynamic feature for an effective elbow-joint angle estimation based on electromyography signals

<a name="_Hlk561743"></a><span>Some physical parameters influence the electromyography signal (EMG). when the EMG signal is used to estimate the position of the elbow. An adaptable feature was important to reduce a variation on the parameters. The aim of this paper is to estimate the joint position of the elbow using EMG signal based on a dynamic function. The major contribution of this work is that the method proposed is capable of determining the elbow position using the non-pattern (NPR) recognition (PR) method. A Wilson amplitude (WAMP) which used a dynamic threshold was used to reduce the EMG signal. The dynamic threshold was generated from the root mean square (RMS) processor. With the dynamic threshold, the model could adapt to any variations on the independent variables. In order to confirm this opportunity, this work involved ten healthy male subjects to perform an experimental protocol. After a tuning and calibration process, the mean of RMS error and correlation coefficient are 9.83º±1.69º and 0.98±0.01 for a single cycle of motion, 10.39º±1.82º and 0.97±0.01 for a continuous cycle of motion and 15.19º±1.92º and 0.94±0.02 for the arbitrary gesture. For conclusion, the performance of the prediction did not significantly depend on the varying cycle of gesture (p-value>0.05). This study has confirmed that the success of the non-pattern recognition-based prediction of elbow position is adaptable to any different subjects, loads, and speed of motion</span><span>.</span>

Behavioral Foundations for Expression Meaning

According to a well-established tradition in the philosophy of language, we can understand what makes an arbitrary sound, gesture, or marking into a meaningful linguistic expression only by appealing to mental states, such as beliefs and intentions. In this paper, I explore the contrasting possibility of understanding the meaningfulness of linguistic expressions just in terms of observable linguistic behavior. Specifically, I explore the view that a type of sound (or other item) becomes a meaningful linguistic expression within a group in virtue of the production of that type of item becoming that group’s widespread, copied way of getting others to involve an object or relation in their activity. After discussing a preliminary version of the view, I develop it in response to some key concerns about whether it really does, as a matter of fact, eschew mental states, and about its adequacy as an account of linguistic meaning.

How many fingers am I holding up? The answer depends on children's language background.

Monolingual English-speaking preschool children tend to process number gestures as unanalyzed wholes rather than use the one-to-one (finger-to-quantity) correspondence. By school age, however, children can use the one-to-one correspondence. The purpose of the present studies was to test whether children learn one-to-one correspondence through exposure to a variety of finger configurations to convey a single quantity. In Study 1, we compared children with exposure to multiple one-to-one configurations, that is, French-English and German-English bilingual children, to English monolingual children who see consistent representations. As predicted, the bilingual children performed better in interpreting unconventional number gestures. In Study 2, we compared Chinese-English bilingual children who knew arbitrary one-handed Chinese numbers gestures for quantities 6-10 to Chinese-English bilingual children who did not know these gestures, as well as to monolingual English speakers. Chinese-English bilinguals who knew the arbitrary gestures were more likely to interpret unconventional gestures arbitrarily (i.e., influenced by the written and/or Chinese gesture forms). These children did not differ from English monolinguals in the interpretation of unconventional gestures. These results are consistent with the argument that children can become sensitive to the one-to-one correspondence in number gestures with exposure to multiple configurations for the same quantity.

Why Children have Rights: Children Rights in Janusz Korczak’s Education Philosophy

Children are a weak part of society. They suffer injustice, their voice is unheard, their property is not theirs and they depend on adults in all aspects of their life. Even today, children are victims of war crimes, street violence, sexual abuse, hard labour, lack of proper education and insufficient life conditions. Their rights remain an unfulfilled promise.We claim that children have rights, but what does it mean? Of course, we love our children, the challenge is not to define what we gracefully give but what children’s rights are, regardless of our own feelings? How can we substantiate the claim that children have rights? The legacy of Janusz Korczak, world-known children’s rights advocate (1878–1942), may help us in this task.Korczak’s education legacy portrays a cluster of inspiring ideas: children are not people-in-the-making, but human beings here-and-now, they deserve our respect and respect implies ultimate rights. Korczak was not only a theoretician, but also an educationalist in practice who structured his children’s houses as democratic communities, directed by a children’s parliament, court, newspaper and other community common spaces of discussion and learning.A major question remains: how we connect Korczak’s fragmented and isolated educational ideas and practices, each one inspiring and powerful on its own, into one integrated worldview? Can we connect all the dots into a meaningful picture that substantiates the claim that children have unconditional rights as human beings and not only as an arbitrary gesture of the adults? This study suggests that all of Korczak’s ideas and practices fit into the context of Greek philosophy and Korczak appears as a modern Stoic.His Stoicism gives ground to the idea of children’s dignity and children’s rights as an immediate outcome of this dignity. In the infinity of the cosmos, there is no hierarchy of being. In this context, children have rights like any other human being.

Comprehension of conventional gestures in typical children, children with autism spectrum disorders and children with language disorders

BackgroundConventional gestures (CG) contribute to communication and are a precursor of verbal language. The aim of our study was: (a) to analyse the developmental course of CG comprehension in typical children; (b) from a clinical perspective, to document how children with autism spectrum disorders (ASD) and language disorder (LD) can understand CG. MethodsComprehension of CG was evaluated through a video-based testing. The protocol consisted of 15 arbitrary gestures and 15 iconic gestures. We recruited 262 typical children aged from 3 to 10years old and 55 children with communication impairments aged from 4 to 8years old: 36 children with ASD and 19 with LD. ResultsCG comprehension increased during the early development of typical children and the improvement of iconic gestures comprehension occurred earlier than that of arbitrary ones. Children with ASD received lower CG scores than typical children and LD children. For each gesture taken separately, children with LD performed better than not only ASD children but typical children as well. Furthermore, when we performed the analysis with both arbitrary and iconic gesture, children with LD outperformed both children with ASD and TD children. ConclusionsOur results suggest a dissociation between oral language comprehension and language gesture comprehension in children with LD and a deficit in both oral language and language gesture comprehension in children with ASD.

Comprehension of iconic gestures by chimpanzees and human children

Iconic gestures—communicative acts using hand or body movements that resemble their referent—figure prominently in theories of language evolution and development. This study contrasted the abilities of chimpanzees (N=11) and 4-year-old human children (N=24) to comprehend novel iconic gestures. Participants learned to retrieve rewards from apparatuses in two distinct locations, each requiring a different action. In the test, a human adult informed the participant where to go by miming the action needed to obtain the reward. Children used the iconic gestures (more than arbitrary gestures) to locate the reward, whereas chimpanzees did not. Some children also used arbitrary gestures in the same way, but only after they had previously shown comprehension for iconic gestures. Over time, chimpanzees learned to associate iconic gestures with the appropriate location faster than arbitrary gestures, suggesting at least some recognition of the iconicity involved. These results demonstrate the importance of iconicity in referential communication.

The influence of iconic and arbitrary gestures on novel word learning in children with and without SLI

Two experiments were conducted to investigate the role of gestures on novel word learning in preschoolers. In Study 1, 20 children at the average age of 4;9 years were given novel words under 3 conditions: with support of iconic gestures; arbitrary gestures; no gestures, exemplifying a within-subject design. Results indicate scaffolding effects of both types of gestures in comparison to the control condition. No indication of gesture type effects could be observed even in children who were old enough to understand the iconicity of iconic gestures. Study 2 was implemented to further test the scaffolding effect of gestures vs. no gestures in children with SLI (n = 20) — but this time only iconic gestures were used. A between-subjects design was followed, using matched groups. Slow mapping was observed in addition to fast mapping within a 5-week-intervention period. Results confirm the scaffolding effect of iconic gestures on slow mapping in the clinical sample.

A Method of Lower Limb Joint Points Extraction Based on Pendulum Model under Arbitrary Gesture Walk

The position extraction of lower limb joint points is important for gait recognition because the feature data is always based on the position of lower limb joint points. Since the detection of motion information of human body can affect the gait recognition directly, we propose a position extraction method of lower limb joint points in this paper. Through the study on the human body centroid tracking, and positioning of human lower limb joint point, we can obtain the step cycle information. It has been demonstrated via plenty experiments that the proposed method is feasible and easy for implement, since it can achieve real-time tracking and improve positioning accuracy of the human body joints, and can provide feature data for human gait recognition.

Get by With a Little Help From a Word: Multimodal Input Facilitates 26-Month-Olds' Ability to Map and Generalize Arbitrary Gestural Labels

In the early stages of word learning, children demonstrate considerable flexibility in the type of symbols they will accept as object labels. However, around the 2nd year, as children continue to gain language experience, they become focused on more conventional symbols (e.g., words) as opposed to less conventional symbols (e.g., gestures). During this period of symbolic narrowing, the degree to which children are able to learn other types of labels, such as arbitrary gestures, remains a topic of debate. Thus, the purpose of the current set of experiments was to determine whether a multimodal label (word + gesture) could facilitate 26-month-olds' ability to learn an arbitrary gestural label. We hypothesized that the multimodal label would exploit children's focus on words thereby increasing their willingness to interpret the gestural label. To test this hypothesis, we conducted two experiments. In Experiment 1, 26-month-olds were trained with a multimodal label (word + gesture) and tested on their ability to map and generalize both the arbitrary gesture and the multimodal label to familiar and novel objects. In Experiment 2, 26-month-olds were trained and tested with only the gestural label. The findings revealed that 26-month-olds are able to map and generalize an arbitrary gesture when it is presented multimodally with a word, but not when it is presented in isolation. Furthermore, children's ability to learn the gestural labels was positively related to their reported productive vocabulary, providing additional evidence that children's focus on words actually helped, not hindered, their gesture learning.

Preschoolers’ interpretations of gesture: Label or action associate?

This study explores a common assumption made in the cognitive development literature that children will treat gestures as labels for objects. Without doubt, researchers in these experiments intend to use gestures symbolically as labels. The present studies examine whether children interpret these gestures as labels. In Study 1 two-, three-, and four-year olds tested in a training paradigm learned gesture–object pairs for both iconic and arbitrary gestures. Iconic gestures became more accurate with age, while arbitrary gestures did not. Study 2 tested the willingness of children aged 40–60 months to fast map novel nouns, iconic gestures and arbitrary gestures to novel objects. Children used fast mapping to choose objects for novel nouns, but treated gesture as an action associate, looking for an object that could perform the action depicted by the gesture. They were successful with iconic gestures but chose objects randomly for arbitrary gestures and did not fast map. Study 3 tested whether this effect was a result of the framing of the request and found that results did not change regardless of whether the request was framed with a deictic phrase (“this one 〈gesture〉”) or an article (“a 〈gesture〉”). Implications for preschool children’s understanding of iconicity, and for their default interpretations of gesture are discussed.

The Changing Role of Iconicity in Non-Verbal Symbol Learning: A U-Shaped Trajectory in the Acquisition of Arbitrary Gestures

This article reports 2 experiments examining the changing role of iconicity in symbol learning and its implications regarding the mechanisms supporting symbol-to-referent mapping. Experiment 1 compared 18- and 26-month-olds' mapping of iconic gestures (e.g., hopping gesture for a rabbit) vs. arbitrary gestures (e.g., dropping motion for a rabbit). Experiment 2 replicated this comparison with 4-year-olds. All ages successfully mapped iconic gestures. Eighteen-month-olds and 4-year-olds but not 26-month-olds mapped arbitrary gestures, revealing a U-shaped developmental function. These findings imply that (a) there is no advantage for iconicity in early symbol learning and (b) the range of symbols mapped becomes more restricted at 26 months, re-emerging more flexibly during the preschool years. We argue that the decline in arbitrary gesture learning is a function of developing appreciation of communicative conventions. We propose that the re-emergence of arbitrary gestures at 4 years is driven by a wider range of symbolic experiences, and enhanced sensitivity to others' communicative intent.

An Exploration Of Vibration During Interaction With Polarized Texture

As vibration signals take place when a finger or stick rubs over the material they can be recorded through a single piezoelectric transducer. Diverse textures produce different sound patterns depending on density and gradient of texture elements as well as on friction force and relative speed of motion between stick and surface. Vibration patterns of arbitrary gestures along a texture have the specific envelope. These signals and their combinations could be used for data input, user authentication or to add new functions in conventional input devices like a mouse or keyboard. We have explored the ribbed textures similar to the dieaction grid. The 'vertical' and 'horizontal' components of the vibration frequency had difference in two times when: the step between ribs was 0.06 mm, the slope angle of the ribbed texture concerning to the horizontal line of motion was 65 deg., the average speed of the pen motion was about 25 m d s . While the size of the end of the pen was commensurable to the ribs, sound patterns during input of handwriting characters were registered and had recognizable structure. The paper describes a new approach to designing surfaces with polarized texture for human-computer interaction.

Can Young Chimpanzees (Pan Troglodytes) Imitate Arbitrary Actions? Hayes & Hayes (1952) Revisited

Abstract Contrary to recent scepticism, systematic use of an experimental approach suggested by HAYES & HAYES (1952) shows that chimpanzees can imitate novel actions. Two chimpanzees imitated 13 and 17 novel arbitrary gestures, respectively. They were first taught to reproduce 15 gestures on the command, "Do this!", and then presented with 48 novel items. Using a rigourous coding system, two independent observers correctly identified a significant number of the chimpanzees' imitations (p < 0.0001). We conclude that after a period of tuition chimpanzees can go on to imitate arbitrary actions, providing evidence of a basic cognitive capacity for perspective-taking and cross-modal matching.

Effects of Induced Motor Gestures on Vocal Output

The communicative act is a complex phenomenon involving gestural and expressive, as well as vocal, components. In the present experiment, the relationship between gestural and vocal components was studied by imposing an arbitrary gesture on a speaker and examining its effect on his verbal output. Subjects either performed or viewed a circular or linear gesture, and were required to simultaneously produce either short stories or words in restricted categories. Analysis of the story protocols showed a significant effect of gesture type in both the observed and produced conditions. No such effect was found for word production. These results suggest that meaning was conveyed by the gestures, and that the gestural and vocal systems are not independent during the communicative act. Furthermore, the gesture is capable of constraining the content of vocal output at the ideational level of production (stories), but not at the level of production of individual words.