The wide range of algorithms for recognizing two-dimensional stroke gestures raises a crucial question: which recognizer should be selected depending on the gesture set and its context of use? Since the context of use expresses a category of users performing interactive tasks on a device in a physical environment, many contextual conditions are feasible. Recognizers have been tested in only a few of them, making them difficult to compare and select. A recognizer suitable for one context of use does not necessarily translate to another. Recognizer variables, such as the number of resampling points, the number of templates, and the number of users, vary from one recognizer to another, making them challenging to specify for practitioners and heterogeneous to compare for researchers. To address these issues, this article performs comparative tests of 16 recognizers (15 state-of-the-art recognizers and one for rotation invariance) in 11 gesture sets (9 reference sets and 2 for multi-device rotation invariance) against their accuracy, speed, and algorithmic complexity, in user-(in)dependent scenarios based on the variables mentioned above. In particular, the impact of two contextual dimensions, i.e., the visual impairments of end users and input devices, on accuracy is further studied. The comparative testing results in an empirically validated decision table for the researcher to select a recognizer depending on contextual conditions and a flow chart for the practitioner to be guided. We break down our design implications into two categories: gesture acquisition, recognition, and gesture set design. We also publicly release Gester , a JavaScript software for conducting comparative testing of recognizers under various contextual conditions, allowing the practitioner to test a recognizer in a project and the researcher to benchmark recognizers.

Browsing multimedia objects, such as photos, videos, documents, and maps represents a frequent activity in a context of use where an end-user interacts on a large vertical display close to bystanders, such as a meeting in a corporate environment or a family display at home. In these contexts, mid-air gesture interaction is suitable for a large variety of end-users, provided that gestures are consistently mapped to similar functions across media types. We present Lui (Large User Interface), a ready-to-deploy and to-use application for browsing multimedia objects by consistent mid-air gesture interaction on a large display that is customizable by mapping new gesture classes to functions in real-time. The method followed to design the gesture interaction and to develop the application consists of four stages: (1) a contextual gesture elicitation study (23 participants × 18 referents = 414 proposed gestures) is conducted with the various media types to determine a consensus set satisfying consistency, (2) the continuous integration of this consensus set with gesture recognizers into a pipeline software architecture, (3) a comparative testing of these recognizers on the consensus set to configure the pipeline with the most efficient ones, and (4) an evaluation of the interface regarding its global quality and specific to the implemented gestures.

The field of generative artificial intelligence has seen significant advancements in recent years with the advent of large language models, which have shown impressive results in software engineering tasks but not yet in engineering user interfaces. Thus, we raise a specific research question: would an LLM-based system be able to search for relevant GUI layouts? To address this question, we conducted a controlled study evaluating how Instigator, an LLM-based system for searching GUI layouts of web pages by generative pre-trained training, would return GUI layouts that are relevant to a given instruction and what would be the user experience of (N =34) practitioners interacting with Instigator. Our results identify a very high similarity and a moderate correlation between the rankings of the GUI layouts generated by Instigator and the rankings of the practitioners with respect to their relevance to a given design instruction. We highlight the results obtained through thirteen UEQ+ scales that characterize the user experience of the practitioner with Instigator, which we use to discuss perspectives for improving such future tools.

Radar sensing technologies offer several advantages over other gesture input modalities, such as the ability to reliably sense human movements, a reasonable deployment cost, insensitivity to ambient conditions such as light, temperature, and the ability to preserve anonymity. These advantages come at the price of high processing complexity mainly due to the spatio-temporal variations of gesture articulation performed by different people. Deep learning methods, such as CNN-LSTM and 3D CNN-LSTM, have a high potential to recognize radar-based gestures but usually require hundreds or thousands of labeled training samples and high processing power. Asking a lot of people to acquire a lot of gestures is particularly tedious and tiring to the point of being unrealistic. To overcome these challenges, we propose FORTE, a hand gesture recognition with few samples based on an optimized CNN architecture working on pre-processed raw data. Using a k=5-fold cross-validation, we define and compare three alternative CNNs for recognizing hand gestures acquired in a semi-mobile context of use with a portable radar attached to a smartphone. The best CNN reaches an accuracy of 94.96% with a precision of 95.92% and a recall of 96.03% for a dataset composed of solely 5 participants producing 2 samples for 20 classes covering 1 pointing, 2 pantomimic, 3 iconic, and 14 semaphoric gestures. We suggest some implications for designing radar-based gestures and we discuss the limitations of this approach.

Microwave radars bring many benefits to mid-air gesture sensing due to their large field of view and independence from environmental conditions, such as ambient light and occlusion. However, radar signals are highly dimensional and usually require complex deep learning approaches. To understand this landscape, we report results from a systematic literature review of ( N =118) scientific papers on radar sensing, unveiling a large variety of radar technology of different operating frequencies and bandwidths and antenna configurations but also various gesture recognition techniques. Although highly accurate, these techniques require a large amount of training data that depend on the type of radar. Therefore, the training results cannot be easily transferred to other radars. To address this aspect, we introduce a new gesture recognition pipeline that implements advanced full-wave electromagnetic modeling and inversion to retrieve physical characteristics of gestures that are radar independent, i.e., independent of the source, antennas, and radar-hand interactions. Inversion of radar signals further reduces the size of the dataset by several orders of magnitude, while preserving the essential information. This approach is compatible with conventional gesture recognizers, such as those based on template matching, which only need a few training examples to deliver high recognition accuracy rates. To evaluate our gesture recognition pipeline, we conducted user-dependent and user-independent evaluations on a dataset of 16 gesture types collected with the Walabot, a low-cost off-the-shelf array radar. We contrast these results with those obtained for the same gesture types collected with an ultra-wideband radar made of a vector network analyzer with a single horn antenna and with a computer vision sensor, respectively. Based on our findings, we suggest some design implications to support future development in radar-based gesture recognition.

We show how two recently introduced visual tools, RepliGES and GEStory, can be used conjointly to inform possible replications of Gesture Elicitation Studies (GES) with a case study centered on gestures that can be sensed with radars. Starting from a GES identified in GEStory, we employ the dimensions of the RepliGES space to enumerate eight possible ways to replicate that study towards gaining new insights into end user’s preferences for gesture-based interaction for applications that use radar sensors.

Microwave radar sensors in human-computer interactions have several advantages compared to wearable and image-based sensors, such as privacy preservation, high reliability regardless of the ambient and lighting conditions, and larger field of view. However, the raw signals produced by such radars are high-dimension and relatively complex to interpret. Advanced data processing, including machine learning techniques, is therefore necessary for gesture recognition. While these approaches can reach high gesture recognition accuracy, using artificial neural networks requires a significant amount of gesture templates for training and calibration is radar-specific. To address these challenges, we present a novel data processing pipeline for hand gesture recognition that combines advanced full-wave electromagnetic modelling and inversion with machine learning. In particular, the physical model accounts for the radar source, radar antennas, radar-target interactions and target itself, i.e.,, the hand in our case. To make this processing feasible, the hand is emulated by an equivalent infinite planar reflector, for which analytical Green’s functions exist. The apparent dielectric permittivity, which depends on the hand size, electric properties, and orientation, determines the wave reflection amplitude based on the distance from the hand to the radar. Through full-wave inversion of the radar data, the physical distance as well as this apparent permittivity are retrieved, thereby reducing by several orders of magnitude the dimension of the radar dataset, while keeping the essential information. Finally, the estimated distance and apparent permittivity as a function of gesture time are used to train the machine learning algorithm for gesture recognition. This physically-based dimension reduction enables the use of simple gesture recognition algorithms, such as template-matching recognizers, that can be trained in real time and provide competitive accuracy with only a few samples. We evaluate significant stages of our pipeline on a dataset of 16 gesture classes, with 5 templates per class, recorded with the Walabot, a lightweight, off-the-shelf array radar. We also compare these results with an ultra wideband radar made of a single horn antenna and lightweight vector network analyzer, and a Leap Motion Controller.

This paper presents SnappView, an open-source software development kit that facilitates end-user review of graphical user interfaces for mobile applications and streamlines their input into a continuous design life cycle. SnappView structures this user interface review process into four cumulative stages: (1) a developer creates a mobile application project with user interface code instrumented by only a few instructions governing SnappView and deploys the resulting application on an application store; (2) any tester, such as an end-user, a designer, a reviewer, while interacting with the instrumented user interface, shakes the mobile device to freeze and capture its screen and to provide insightful multimodal feedback such as textual comments, critics, suggestions, drawings by stroke gestures, voice or video records, with a level of importance; (3) the screenshot is captured with the application, browser, and status data and sent with the feedback to SnappView server; and (4) a designer then reviews collected and aggregated feedback data and passes them to the developer to address raised usability problems. Another cycle then initiates an iterative design. This paper presents the motivations and process for performing mobile application review based on SnappView. Based on this process, we deployed on the AppStore "WeTwo", a real-world mobile application to find various personal activities over a one-month period with 420 active users. This application served for a user experience evaluation conducted with N1=14 developers to reveal the advantages and shortcomings of the toolkit from a development point of view. The same application was also used in a usability evaluation conducted with N2=22 participants to reveal the advantages and shortcomings from an end-user viewpoint.

Despite the tremendous progress made for recognizing gestures acquired by various devices, such as the Leap Motion Controller, developing a gestural user interface based on such devices still induces a significant programming and software engineering effort before obtaining a running interactive application. To facilitate this development, we present QuantumLeap, a framework for engineering gestural user interfaces based on the Leap Motion Controller. Its pipeline software architecture can be parameterized to define a workflow among modules for acquiring gestures from the Leap Motion Controller, for segmenting them, recognizing them, and managing their mapping to functions of the application. To demonstrate its practical usage, we implement two gesture-based applications: an image viewer that allows healthcare workers to browse DICOM medical images of their patients without any hygiene issues commonly associated with touch user interfaces and a large-scale application for managing multimedia contents on wall screens. To evaluate the usability of QuantumLeap, seven participants took part in an experiment in which they used QuantumLeap to add a gestural interface to an existing application.

This paper presents theoretical and empirical results about user-defined gesture preferences for squeezable objects by focusing on a particular object: a deformable cushion. We start with a theoretical analysis of potential gestures for this squeezable object by defining a multi-dimension taxonomy of squeeze gestures composed of 82 gesture classes. We then empirically analyze the results of a gesture elicitation study resulting in a set of N=32 participants X 21 referents = 672 elicited gestures, further classified into 26 gesture classes. We also contribute to the practice of gesture elicitation studies by explaining why we started from a theoretical analysis (by systematically exploring a design space of potential squeeze gestures) to end up with an empirical analysis (by conducting a gesture elicitation study afterward): the intersection of the results from these sources confirm or disconfirm consensus gestures. Based on these findings, we extract from the taxonomy a subset of recommended gestures that give rise to design implications for gesture interaction with squeezable objects.

Intra-platform plasticity regularly assumes that the display of a computing platform remains fixed and rigid during interactions with the platform in contrast to reconfigurable displays, which can change form depending on the context of use. In this paper, we present a model-based approach for designing and deploying graphical user interfaces that support intra-platform plasticity for reconfigurable displays. We instantiate the model for E3Screen, a new device that expands a conventional laptop with two slidable, rotatable, and foldable lateral displays, enabling slidable user interfaces. Based on a UML class diagram as a domain model and a SCRUD list as a task model, we define an abstract user interface as interaction units with a corresponding master-detail design pattern. We then map the abstract user interface to a concrete user interface by applying rules for the reconfiguration, concrete interaction, unit allocation, and widget selection and implement it in JavaScript. In a first experiment, we determine display configurations most preferred by users, which we organize in the form of a state-transition diagram. In a second experiment, we address reconfiguration rules and widget selection rules. A third experiment provides insights into the impact of the lateral displays on a visual search task.

Abstract Adapting the user interface of a software system to the requirements of the context of use continues to be a major challenge, particularly when users become more demanding in terms of adaptation quality. A considerable number of methods have, over the past three decades, provided some form of modelling with which to support user interface adaptation. There is, however, a crucial issue as regards in analysing the concepts, the underlying knowledge, and the user experience afforded by these methods as regards comparing their benefits and shortcomings. These methods are so numerous that positioning a new method in the state of the art is challenging. This paper, therefore, defines a conceptual reference framework for intelligent user interface adaptation containing a set of conceptual adaptation properties that are useful for model-based user interface adaptation. The objective of this set of properties is to understand any method, to compare various methods and to generate new ideas for adaptation. We also analyse the opportunities that machine learning techniques could provide for data processing and analysis in this context, and identify some open challenges in order to guarantee an appropriate user experience for end-users. The relevant literature and our experience in research and industrial collaboration have been used as the basis on which to propose future directions in which these challenges can be addressed.

While end users can acquire full 3D gestures with many input devices, they often capture only 3D trajectories, which are 3D uni-path, uni-stroke single-point gestures performed in thin air. Such trajectories with their $(x,y,z)$ coordinates could be interpreted as three 2D stroke gestures projected on three planes,\ie, $XY$, $YZ$, and $ZX$, thus making them admissible for established 2D stroke gesture recognizers. To investigate whether 3D trajectories could be effectively and efficiently recognized, four 2D stroke gesture recognizers, \ie, \$P, \$P+, \$Q, and Rubine, are extended to the third dimension: $\$P^3$, $\$P+^3$, $\$Q^3$, and Rubine-Sheng, an extension of Rubine for 3D with more features. Two new variations are also introduced: $\F for flexible cloud matching and FreeHandUni for uni-path recognition. Rubine3D, another extension of Rubine for 3D which projects the 3D gesture on three orthogonal planes, is also included. These seven recognizers are compared against three challenging datasets containing 3D trajectories, \ie, SHREC2019 and 3DTCGS, in a user-independent scenario, and 3DMadLabSD with its four domains, in both user-dependent and user-independent scenarios, with varying number of templates and sampling. Individual recognition rates and execution times per dataset and aggregated ones on all datasets show a highly significant difference of $\$P+^3$ over its competitors. The potential effects of the dataset, the number of templates, and the sampling are also studied.