TinyHAR, a 46k-parameter time-series model, reaches Macro F1 0.960 on 5-way gaze gesture recognition and 0.997 on user identification using ARKit data in a 4-person pilot.
Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Gaze behavior is an important non-verbal cue in social signal processing and human-computer interaction. In this paper, we tackle the problem of person- and head pose-independent 3D gaze estimation from remote cameras, using a multi-modal recurrent convolutional neural network (CNN). We propose to combine face, eyes region, and face landmarks as individual streams in a CNN to estimate gaze in still images. Then, we exploit the dynamic nature of gaze by feeding the learned features of all the frames in a sequence to a many-to-one recurrent module that predicts the 3D gaze vector of the last frame. Our multi-modal static solution is evaluated on a wide range of head poses and gaze directions, achieving a significant improvement of 14.6% over the state of the art on EYEDIAP dataset, further improved by 4% when the temporal modality is included.
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TinyGaze: Lightweight Gaze-Gesture Recognition on Commodity Mobile Devices
TinyHAR, a 46k-parameter time-series model, reaches Macro F1 0.960 on 5-way gaze gesture recognition and 0.997 on user identification using ARKit data in a 4-person pilot.