Hand gesture recognition is becoming a more prevalent mode of human-computer interaction, especially as cameras proliferate across everyday devices. Despite continued progress in this field, gesture customization is often underexplored. Customization is crucial since it enables users to define and demonstrate gestures that are more natural, memorable, and accessible. However, customization requires efficient usage of user-provided data. We introduce a method that enables users to easily design bespoke gestures with a monocular camera from one demonstration. We employ transformers and meta-learning techniques to address few-shot learning challenges. Unlike prior work, our method supports any combination of one-handed, two-handed, static, and dynamic gestures, including different viewpoints, and the ability to handle irrelevant hand movements. We implement three real-world applications using our customization method, conduct a user study, and achieve up to 94% average recognition accuracy from one demonstration. Our work provides a viable path for vision-based gesture customization, laying the foundation for future advancements in this domain.

We present a framework for gesture customization requiring minimal examples from users, all without degrading the performance of existing gesture sets. To achieve this, we first deployed a large-scale study (N=500+) to collect data and train an accelerometer-gyroscope recognition model with a cross-user accuracy of 95.7% and a false-positive rate of 0.6 per hour when tested on everyday non-gesture data. Next, we design a few-shot learning framework which derives a lightweight model from our pre-trained model, enabling knowledge transfer without performance degradation. We validate our approach through a user study (N=20) examining on-device customization from 12 new gestures, resulting in an average accuracy of 55.3%, 83.1%, and 87.2% on using one, three, or five shots when adding a new gesture, while maintaining the same recognition accuracy and false-positive rate from the pre-existing gesture set. We further evaluate the usability of our real-time implementation with a user experience study (N=20). Our results highlight the effectiveness, learnability, and usability of our customization framework. Our approach paves the way for a future where users are no longer bound to pre-existing gestures, freeing them to creatively introduce new gestures tailored to their preferences and abilities.

In this paper, we present a method to integrate sensing capabilities into 3D printable metamaterial structures comprised of cells, which enables the creation of monolithic input devices for HCI. We accomplish this by converting select opposing cell walls within the metamaterial device into electrodes, thereby creating capacitive sensors. When a user interacts with the object and applies a force, the distance and overlapping area between opposing cell walls change, resulting in a measurable capacitance variation.

Zippers are common in a wide variety of objects that we use daily. This work investigates how we can take advantage of such common daily activities to support seamless interaction with technology. We look beyond simple zipper-sliding interactions explored previously to determine how to weave foreground and background interactions into a vocabulary of natural usage patterns. We begin by conducting two user studies to understand how people typically interact with zippers. The findings identify several opportunities for zipper input and sensing, which inform the design of Zippro, a self-contained prototype zipper slider, which we evaluate with a standard jacket zipper. We conclude by demonstrating several applications that make use of the identified foreground and background input methods.

We propose a new sensing technique for one-dimensional touch input workable on an interactive thread of less than 0.4 mm thick. Our technique locates up to two touches using impedance sensing with a spacing resolution unachievable by the existing methods. Our approach is also unique in that it locates a touch based on a mathematical model describing the change in thread impedance in relation to the touch locations. This allows the system to be easily calibrated by the user touching a known location(s) on the thread. The system can thus quickly adapt to various environmental settings and users. A system evaluation showed that our system could track the slide motion of a finger with an average error distance of 6.13 mm and 4.16 mm using one and five touches for calibration, respectively. The system could also distinguish between single touch and two concurrent touches with an accuracy of 99% and could track two concurrent touches with an average error distance of 8.55 mm. We demonstrate new interactions enabled by our sensing approach in several unique applications.

We present Fabriccio, a touchless gesture sensing technique developed for interactive fabrics using Doppler motion sensing. Our prototype was developed using a pair of loop antennas (one for transmitting and the other for receiving), made of conductive thread that was sewn onto a fabric substrate. The antenna type, configuration, transmission lines, and operating frequency were carefully chosen to balance the complexity of the fabrication process and the sensitivity of our system for touchless hand gestures, performed at a 10 cm distance. Through a ten-participant study, we evaluated the performance of our proposed sensing technique across 11 touchless gestures as well as 1 touch gesture. The study result yielded a 92.8% cross-validation accuracy and 85.2% leave-one-session-out accuracy. We conclude by presenting several applications to demonstrate the unique interactions enabled by our technique on soft objects.

We present a bimanual text input method on a miniature fingertip keyboard, that invisibly resides on the first segment of a user's index finger on both hands. Text entry can be carried out using the thumb-tip to tap the tip of the index finger. The design of our keyboard layout followed an iterative process, where we first conducted a study to understand the natural expectation of the handedness of the keys in a QWERTY layout for users. Among a choice of 67,108,864 design variations, we identified 1295 candidates offering a good satisfaction for user expectations. Based on these results, we computed an optimized bimanual keyboard layout, while considering the joint optimization problems of word ambiguity and movement time. Our user evaluation revealed that participants achieved an average text entry speed of 23.4 WPM.

In this paper, we present Acustico, a passive acoustic sensing approach that enables tap detection and 2D tap localization on uninstrumented surfaces using a wrist-worn device. Our technique uses a novel application of acoustic time differences of arrival (TDOA) analysis. We adopt a sensor fusion approach by taking both 'surface waves' (i.e., vibrations through surface) and 'sound waves' (i.e., vibrations through air) into analysis to improve sensing resolution. We carefully design a sensor configuration to meet the constraints of a wristband form factor. We built a wristband prototype with four acoustic sensors, two accelerometers and two microphones. Through a 20-participant study, we evaluated the performance of our proposed sensing technique for tap detection and localization. Results show that our system reliably detects taps with an F1-score of 0.9987 across different environmental noises and yields high localization accuracies with root-mean-square-errors of 7.6mm (X-axis) and 4.6mm (Y-axis) across different surfaces and tapping techniques.

The recent proliferation of fabrication and making activities has introduced a large number of users to a variety of tools and equipment. Monitored, reactive and adaptive fabrication spaces are needed to provide personalized information, feedback and assistance to users. This paper explores the sensorization of making and fabrication activities, where the environment, tools, and users were considered to be separate entities that could be instrumented for data collection. From this exploration, we present the design of a modular system that can capture data from the varied sensors and infer contextual information. Using this system, we collected data from fourteen participants with varying levels of expertise as they performed seven representative making tasks. From the collected data, we predict which activities are being performed, which users are performing the activities, and what expertise the users have. We present several use cases of this contextual information for future interactive fabrication spaces.

We propose autocomplete for the design and development of virtual breadboard circuits using software prototyping tools. With our system, a user inserts a component into the virtual breadboard, and it automatically provides a user with a list of suggested components. These suggestions complete or ex- tend the electronic functionality of the inserted component to save the user's time and reduce circuit error. To demon- strate the effectiveness of autocomplete, we implemented our system on Fritzing, a popular open source breadboard circuit prototyping software, used by novice makers. Our autocomplete suggestions were implemented based upon schematics from datasheets for standard components, as well as how components are used together from over 4000 circuit projects from the Fritzing community. We report the results of a controlled study with 16 participants, evaluating the effectiveness of autocomplete in the creation of virtual breadboard circuits, and conclude by sharing insights and directions for future research.

We propose a new type of haptic output for foreground interactions on an interactive chair, where input is carried out explicitly in the foreground of the user's consciousness. This type of force output restricts a user's motion by modulating the resistive force when rotating a seat, tilting the backrest, or rolling the chair. These interactions are useful for many applications in a ubiquitous computing environment, ranging from immersive VR games to rapid and private query of information for people who are occupied with other tasks (e.g. in a meeting). We carefully designed and implemented our proposed haptic force output on a standard office chair and determined the recognizability of five force profiles for rotating, tilting, and rolling the chair. We present the result of our studies, as well as a set of novel interaction techniques enabled by this new force output for chairs.

Instructors of hardware computing face many challenges including maintaining awareness of student progress, allocating their time adequately between lecturing and helping individual students, and keeping students engaged even while debugging problems. Based on formative interviews with 5 electronics instructors, we found that many circuit style behaviors could help novice users prevent or efficiently debug common problems. Drawing inspiration from the software engineering practice of coding style, these circuit style behaviors consist of best-practices and guidelines for implementing circuit prototypes that do not interfere with the functionality of the circuit, but help a circuit be more readable, less error-prone, and easier to debug. To examine if these circuit style behaviors could be peripherally enforced, aid an in-person instructor's ability to facilitate a workshop, and not monopolize instructor's attention, we developed CircuitStyle, a teaching aid for in-person hardware computing workshops. To evaluate the effectiveness of our tool, we deployed our system in an in-person maker-space workshop. The instructor appreciated CircuitStyle's ability to provide a broad understanding of the workshop's progress and the potential for our system to help instructors of various backgrounds better engage and understand the needs of their classroom.

We present Tessutivo, a contact-based inductive sensing technique for contextual interactions on interactive fabrics. Our technique recognizes conductive objects (mainly metallic) that are commonly found in households and workplaces, such as keys, coins, and electronic devices. We built a prototype containing six by six spiral-shaped coils made of conductive thread, sewn onto a four-layer fabric structure. We carefully designed the coil shape parameters to maximize the sensitivity based on a new inductance approximation formula. Through a ten-participant study, we evaluated the performance of our proposed sensing technique across 27 common objects. We yielded 93.9% real-time accuracy for object recognition. We conclude by presenting several applications to demonstrate the unique interactions enabled by our technique.

We propose blending the virtual and physical worlds for prototyping circuits using physical proxies. With physical proxies, real-world components (e.g. a motor, or light sensor) can be used with a virtual counterpart for a circuit designed in software. We demonstrate this concept in Proxino, and elucidate the new scenarios it enables for makers, such as remote collaboration with physically distributed electronics components. We compared our hybrid system and its output with designs of real circuits to determine the difference through a system evaluation and observed minimal differences. We then present the results of an informal study with 9 users, where we gathered feedback on the effectiveness of our system in different working conditions (with a desktop, using a mobile, and with a remote collaborator). We conclude by sharing our lessons learned from our system and discuss directions for future research that blend physical and virtual prototyping for electronic circuits.

In this paper, we propose and investigate a new text entry technique using micro thumb-tip gestures. Our technique features a miniature QWERTY keyboard residing invisibly on the first segment of the user's index finger. Text entry can be carried out using the thumb-tip to tap the tip of the index finger. The keyboard layout was optimized for eyes-free input by utilizing a spatial model reflecting the users' natural spatial awareness of key locations on the index finger. We present our approach of designing and optimizing the keyboard layout through a series of user studies and computer simulated text entry tests over 1,146,484 possibilities in the design space. The outcome is a 2×3 grid with the letters highly confining to the alphabetic and spatial arrangement of QWERTY. Our user evaluation showed that participants achieved an average text entry speed of 11.9 WPM and were able to type as fast as 13.3 WPM towards the end of the experiment.

Interacting with media and games is a challenging user experience on smartwatches due to their small screens. We propose using lateral force feedback to enhance these experiences. When virtual objects on the smartwatch display visually collide or push the edge of the screen, we add haptic feedback so that the user also feels the impact. This addition creates the illusion of a virtual object that is physically hitting or pushing the smartwatch, from within the device itself. Using this approach, we extend virtual space and scenes into a 2D physical space. To create realistic lateral force feedback, we first examined the minimum change in force magnitude that is detectable by users in different directions and weight levels, finding an average JND of 49% across all tested conditions, with no significant effect of weight and force direction. We then developed a proof-of-concept hardware prototype called Jetto and demonstrated its unique capabilities through a set of impact-enhanced videos and games. Our preliminary user evaluations indicated the concept was welcomed and is regarded as a worthwhile addition to smartwatch output and media experiences.

We present WrisText - a one-handed text entry technique for smartwatches using the joystick-like motion of the wrist. A user enters text by whirling the wrist of the watch hand, towards six directions which each represent a key in a circular keyboard, and where the letters are distributed in an alphabetical order. The design of WrisText was an iterative process, where we first conducted a study to investigate optimal key size, and found that keys needed to be 55º or wider to achieve over 90% striking accuracy. We then computed an optimal keyboard layout, considering a joint optimization problem of striking accuracy, striking comfort, word disambiguation. We evaluated the performance of WrisText through a five-day study with 10 participants in two text entry scenarios: hand-up and hand-down. On average, participants achieved a text entry speed of 9.9 WPM across all sessions, and were able to type as fast as 15.2 WPM by the end of the last day.

We present Indutivo, a contact-based inductive sensing technique for contextual interactions. Our technique recognizes conductive objects (metallic primarily) that are commonly found in households and daily environments, as well as their individual movements when placed against the sensor. These movements include sliding, hinging, and rotation. We describe our sensing principle and how we designed the size, shape, and layout of our sensor coils to optimize sensitivity, sensing range, recognition and tracking accuracy. Through several studies, we also demonstrated the performance of our proposed sensing technique in environments with varying levels of noise and interference conditions. We conclude by presenting demo applications on a smartwatch, as well as insights and lessons we learned from our experience.

In this paper, we propose using the auricle - the visible part of the ear - as a means of expressive output to extend body language to convey emotional states. With an initial exploratory study, we provide an initial set of dynamic and static auricular postures. Using these results, we examined the relationship between emotions and auricular postures, noting that dynamic postures involving stretching the top helix in fast (e.g., 2Hz) and slow speeds (1Hz) conveyed intense and mild pleasantness while static postures involving bending the side or top helix towards the center of the ear were associated with intense and mild unpleasantness. Based on the results, we developed a prototype (called Orrechio) with miniature motors, custom-made robotic arms and other electronic components. A preliminary user evaluation showed that participants feel more comfortable using expressive auricular postures with people they are familiar with, and that it is a welcome addition to the vocabulary of human body language.

We propose and explore actuating a smartwatch face to enable extended interactions. Five face movements are defined: rotation, hinging, translation, rising, and orbiting. These movements are incorporated into interaction techniques to address limitations of a fixed watch face. A 20-person study uses concept videos of a passive low fidelity prototype to confirm the usefulness of the actuated interaction techniques. A second 20-person study uses 3D rendered animations to access social acceptability and perceived comfort for different actuation dynamics and usage contexts. Finally, we present Cito, a high-fidelity proof-of-concept hardware prototype that investigates technical challenges.

Chronic disease is one of the most pressing health challenges facing the United States (and an increasing set of other countries). The onset or progression of diseases like obesity, diabetes, and metabolic disorder are strongly related to eating behavior, and scientists are still trying to fully understand the complex mixture of diet, exercise, genetics, sociocultural context, and physical environment that lead to these diseases. Health science, however, has no effective means for automatically measuring eating behavior in free-living conditions. The Auracle aims to be a wearable earpiece that detects eating behavior, to be fielded by health-science researchers in their efforts to study eating behavior and ultimately to develop interventions useful to individuals striving to address chronic disease related to eating.

We present Pyro, a micro thumb-tip gesture recognition technique based on thermal infrared signals radiating from the fingers. Pyro uses a compact, low-power passive sensor, making it suitable for wearable and mobile applications. To demonstrate the feasibility of Pyro, we developed a self-contained prototype consisting of the infrared pyroelectric sensor, a custom sensing circuit, and software for signal processing and machine learning. A ten-participant user study yielded a 93.9% cross-validation accuracy and 84.9% leave-one-session-out accuracy on six thumb-tip gestures. Subsequent lab studies demonstrated Pyro's robustness to varying light conditions, hand temperatures, and background motion. We conclude by discussing the insights we gained from this work and future research questions.

The small screen size of a smartwatch limits user experience when watching or interacting with media. We propose a supplementary tactile feedback system to enhance the user experience with a method unique to the smartwatch form factor. Our system has a deformable surface on the back of the watch face, allowing the visual scene on screen to extend into 2.5D physical space. This allows the user to watch and feel virtual objects, such as experiencing a ball bouncing against the wrist. We devised two controlled experiments to analyze the influence of tactile display resolution on the illusion of virtual object presence. Our first study revealed that on average, a taxel can render virtual objects between 70% and 138% of its own size without shattering the illusion. From the second study, we found visual and haptic feedback can be separated by 4.5mm to 16.2mm for the tested taxels. Based on the results, we developed a prototype (called RetroShape) with 4×4 10mm taxels using micro servo motors, and demonstrated its unique capability through a set of tactile-enhanced games and videos. A preliminary user evaluation showed that participants welcome RetroShape as a useful addition to existing smartwatch output.

We propose and study a new input modality, WristWhirl, that uses the wrist as an always-available joystick to perform one-handed continuous input on smartwatches. We explore the influence of the wrist's bio-mechanical properties for performing gestures to interact with a smartwatch, both while standing still and walking. Through a user study, we examine the impact of performing 8 distinct gestures (4 directional marks, and 4 free-form shapes) on the stability of the watch surface. Participants were able to perform directional marks using the wrist as a joystick at an average rate of half a second and free-form shapes at an average rate of approximately 1.5secs. The free-form shapes could be recognized by a $1 gesture recognizer with an accuracy of 93.8% and by three human inspectors with an accuracy of 85%. From these results, we designed and implemented a proof-of-concept device by augmenting the watchband using an array of proximity sensors, which can be used to draw gestures with high quality. Finally, we demonstrate a number of scenarios that benefit from one-handed continuous input on smartwatches using WristWhirl.