Improving Stability of Gaze Target Detection in Videos

Obtaining accurate and stable results in gaze target detection is vital for the subsequent analysis of gaze meaning. However, existing image-based methods, which focus solely on enhancing accuracy, demonstrate poor stability when directly applied on videos. Especially when the video frame rate is low, even though the actual gaze target positions do not differ significantly between adjacent frames, the detected positions vary considerably. This inconsistency, stemming from the lack of temporal information, makes dynamic detection challenging and can lead to jarring outcomes. To reduce the jitter in gaze target detection in videos, we introduce an approach that integrates spatial and temporal modules to combine spatial with temporal information. Additionally, we propose a Jitter loss function to capture significant jitter and impose a strong penalty during training, which empowers our model with increased stability for dynamic detection. Based on a self-collected dataset, experiments demonstrate that our approach exhibits superior stability without compromising accuracy.