Effect Of Personalized Calibration On Gaze Estimation Using Deep-Learning
This work addresses a domain-specific problem for human-computer interaction applications by providing insights into calibration effects, but it is incremental as it builds on existing methods without introducing major innovations.
The study tackled the challenge of appearance-based gaze estimation for unknown individuals in real-world scenarios by simulating a personalized calibration mechanism using the MPIIGaze dataset, resulting in improved performance of a deep learning model with calibration compared to without it.
With the increase in computation power and the development of new state-of-the-art deep learning algorithms, appearance-based gaze estimation is becoming more and more popular. It is believed to work well with curated laboratory data sets, however it faces several challenges when deployed in real world scenario. One such challenge is to estimate the gaze of a person about which the Deep Learning model trained for gaze estimation has no knowledge about. To analyse the performance in such scenarios we have tried to simulate a calibration mechanism. In this work we use the MPIIGaze data set. We trained a multi modal convolutional neural network and analysed its performance with and without calibration and this evaluation provides clear insights on how calibration improved the performance of the Deep Learning model in estimating gaze in the wild.