Traditional authentication methods, such as biometrics and passwords, cannot guarantee security once the authenticated user changes after login. Periodic re-authentication at short intervals could preserve security but would severely degrade usability. To balance security and usability, we propose an implicit and continuous identification method based on eye-tracking data. Our approach compares a saliency map personalized for the legitimate user with the gaze heatmap of the current user, and identifies the current user as legitimate if the two maps are similar. To demonstrate our approach, we first develop and verify that a personalized saliency map well expresses a legitimate user’s gaze behavior. With one example result of the user study, we then illustrated the potential application of our identification as a second-factor authentication and as an unobtrusive re-authentication suggestion.

We release an eye-tracking dataset recorded with a Tobii Pro Fusion eye tracker (120 Hz) across six tasks: (1) repeated free viewing of 100 images over three sessions (300 presentations per participant), (2) gaze-pattern authentication, (3) numeric password entry, and (4-6) three 10-minute naturalistic screen activities (shopping, news browsing, and video viewing). Our key design choice is to present the same 100 images three times to obtain stable, participant-level average gaze behavior; the image order is deterministically randomized with a fixed seed such that all participants view the same sequence. Due to copyright restrictions, we provide only the 80 copyright-free natural images collected from the internet as stimuli. The dataset is released under the CC BY 4.0 license. We do not include baseline models or benchmark evaluations, allowing researchers to apply their own post-processing and modeling approaches to the unconstrained, raw tabular data.

We propose an approach to detect finger hover inputs on a smartphone screen using corneal reflection images captured by the device’s built-in front camera. This method requires no external sensors or hardware, enabling hover input detection in the near-screen space that is not directly visible to the camera. By leveraging a convolutional neural network (CNN), we estimate the two-dimensional position of a hovering finger and classify it into a predefined screen grid. Experimental results show that our model achieves approximately 95% accuracy for coarse grids and maintains over 88% accuracy for finer divisions. Furthermore, our system demonstrates real-time processing capability with an end-to-end latency of approximately 22 ms on a standard smartphone. These findings highlight the practical feasibility of camera-only hover sensing and suggest a wide range of touchless interaction applications, enabling touchless interaction when touch is undesirable, pre-touch UI adaptation, and accessibility support on commodity mobile devices.

This study shows a method for estimating users’ emotions in Virtual Reality (VR) spaces through the collection of eye behaviors. In our method, we use eye-related information available from the Head Mounted Display (HMD), including the direction vector of the gaze, coordination of the pupil, pupil diameter, and the eyelid opening width, to estimate whether the user is having fun or feeling others emotions. Using the LightGBM algorithm, the estimation accuracy resulted in an AUC of 0.84 and an accuracy of 0.78.

Studies on gaze-based interactions have utilized natural eye-related information to detect user intent. Most use a machine learning-based approach to minimize the cost of choosing appropriate eye-related information. While those studies demonstrated the effectiveness of an intent detection system, understanding which eye-related information is useful for interactions is important. In this paper, we reanalyze how eye-related information affected the detection performance of a previous study to develop better intent detection systems in the future. Specifically, we analyzed two aspects of dimensionality reduction and adaptation to different tasks. The results showed that saccade and fixation are not always useful, and the direction of gaze movement could potentially cause overfitting.

In this paper, we first position the current dwell selection among gaze-based interactions and its advantages against head-gaze selection, which is the mainstream interface for HMDs. Next, we show how dwell selection and head-gaze selection are used in an actual interaction situation. By comparing these two selection methods, we describe the potential of dwell selection as an essential AR/VR interaction.

We investigated the relationship between dwell-time and the model human processor (MHP). First, we devised an equation that can represent the time taken for recognizing an image based on MHP. Then, we evaluated whether the equation can represent the time and wheter the time estimated by the equation matches the user’s preferred dwell-time. The experiment consisted of two tasks: image selection with a button (button-task) and image selection with a dwell (dwell-task). From the results of the button-task, we found that the equation derived by MHP can estimate the time; the time taken for button selection was 662 ms on average, and the time estimated by the equation was 660 ms on average. Also, we showed that the estimated time represented the user’s preferred dwell-time; all participants in the experiment answered that 500 ms and 600 ms were their preferred dwell-times.

We demonstrate a gaze-based command activation technique that is robust against unintentional command activations using a series of dwelling on a target and performing a specific gesture (dwell-thengesture manipulation). The gesture adopted is a simple two-level stroke, which consists of a sequence of two orthogonal strokes. To achieve robustness against unintentional command activations, we designed and fine-tuned a gesture detection system based on how users move their gaze, as revealed through three experiments. Although our technique seems to simply combine well-known dwelland gesture-based manipulations, implying a low rate of success, our technique is actually the first technique that consists of a short time dwelling for target selection and a simple gesture for command activation. In addition, our technique will be the first technique adopting a marking menu, which is a traditional menu for command activation used in mouseor pen-based interactions to gaze-based interactions.

We present a dwell time reduction technique for gaze-based target acquisition. We adopt Fitts' Law to achieve the dwell time reduction. Our technique uses both the eye movement time for target acquisition estimated using Fitts' Law (Te) and the actual eye movement time (Ta) for target acquisition; a target is acquired when the difference between Te and Ta is small. First, we investigated the relation between the eye movement for target acquisition and Fitts' Law; the result indicated a correlation of 0.90 after error correction. Then we designed and implemented our technique. Finally, we conducted a user study to investigate the performance of our technique; an average dwell time of 86.7 ms was achieved, with a 10.0% Midas-touch rate.