TinyGaze: Lightweight Gaze-Gesture Recognition on Commodity Mobile Devices
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913022134452224 |
|---|---|
| author | Lei, Yaxiong Cho, Hyochan Buchanan, Fergus He, Shijing Gong, Xinya Wang, Yuheng Ye, Juan |
| author_facet | Lei, Yaxiong Cho, Hyochan Buchanan, Fergus He, Shijing Gong, Xinya Wang, Yuheng Ye, Juan |
| contents | Gaze gestures can provide hands free input on mobile devices, but practical use requires (i) gestures users can learn and recall and (ii) recognition models that are efficient enough for on-device deployment. We present an end-to-end pipeline using commodity ARKit head/eye transforms and a scaffolded guidance-to-recall protocol grounded in learning theory. In a pilot feasibility study (N=4 participants; 240 trials; controlled single-session setting), we benchmark a compact time-series model (TinyHAR) against deeper baselines (DeepConvLSTM, SA-HAR) on 5-way gesture recognition and 4-way user identification. TinyHAR achieves strong performance in this pilot benchmark (Macro F1 = 0.960 for gesture recognition; Macro F1 = 0.997 for user identification) while using only 46k parameters. A modality analysis further indicates that head pose dynamics are highly informative for mobile gaze gestures, highlighting embodied head--eye coordination as a key design consideration. Although the small sample size and controlled setting limit generalizability, these results indicate a potential direction for further investigation into on-device gaze gesture recognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09658 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TinyGaze: Lightweight Gaze-Gesture Recognition on Commodity Mobile Devices Lei, Yaxiong Cho, Hyochan Buchanan, Fergus He, Shijing Gong, Xinya Wang, Yuheng Ye, Juan Human-Computer Interaction Computer Vision and Pattern Recognition H.5 Gaze gestures can provide hands free input on mobile devices, but practical use requires (i) gestures users can learn and recall and (ii) recognition models that are efficient enough for on-device deployment. We present an end-to-end pipeline using commodity ARKit head/eye transforms and a scaffolded guidance-to-recall protocol grounded in learning theory. In a pilot feasibility study (N=4 participants; 240 trials; controlled single-session setting), we benchmark a compact time-series model (TinyHAR) against deeper baselines (DeepConvLSTM, SA-HAR) on 5-way gesture recognition and 4-way user identification. TinyHAR achieves strong performance in this pilot benchmark (Macro F1 = 0.960 for gesture recognition; Macro F1 = 0.997 for user identification) while using only 46k parameters. A modality analysis further indicates that head pose dynamics are highly informative for mobile gaze gestures, highlighting embodied head--eye coordination as a key design consideration. Although the small sample size and controlled setting limit generalizability, these results indicate a potential direction for further investigation into on-device gaze gesture recognition. |
| title | TinyGaze: Lightweight Gaze-Gesture Recognition on Commodity Mobile Devices |
| topic | Human-Computer Interaction Computer Vision and Pattern Recognition H.5 |
| url | https://arxiv.org/abs/2604.09658 |