Metraipolis › archive › dc_66a8fe2ee41c

GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History — arXiv:2609.03868

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03868
License (as archived)
CC0-1.0
Archived
2026-10-17T01:12:08.054Z
SHA-256 of the archived text
3fa1487fe7ca33c2b28c054ea33a1c7d964cb2e1482f05b099f5b978bf1b8f9c
Stable URL of this page
https://metraipolis.com/documento/dc_66a8fe2ee41c

How to cite

GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History — arXiv:2609.03868 — arXiv (en), https://arxiv.org/abs/2609.03868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_66a8fe2ee41c (Metraipolis archive dc_66a8fe2ee41c, sha256 3fa1487fe7ca33c2b28c054ea33a1c7d964cb2e1482f05b099f5b978bf1b8f9c)
BibTeX
@misc{dc66a8fe2ee41c,
  title = {GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History — arXiv:2609.03868},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03868},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_66a8fe2ee41c; sha256 3fa1487fe7ca33c2b28c054ea33a1c7d964cb2e1482f05b099f5b978bf1b8f9c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Target-centered gaze interaction requires more than suppressing frame-to-frame fluctuations: target acquisition produces task-aligned changes in gaze-head dynamics, while a gaze trace may retain a persistent target-relative residual direction. We formulate gaze correction as online target-centered gaze-trajectory forecasting and stabilization and introduce GazeFS, which maps a variable-length gaze-head history to the next target-center direction and a short-horizon Search/Focus estimate without target information at inference. Across 7,960 acquisition episodes from 30 participants, Search-Focus differences remain stable under quality control, onset exclusion, and duration matching. History windows improve phase decoding over the current endpoint, but explicit task progress remains a strong control. Under the 30-participant, five-fold grouped out-of-fold protocol across three seeds, the reductions relative to raw hold in Focus episode bias, within-episode dispersion, and P90 target error are 0.182 degrees, 0.257 degrees, and 0.400 degrees, with participant-bootstrap 95% confidence intervals excluding zero. Endpoint-free replay from empty history preserves the Focus advantage and yields raw-network phase balanced accuracy/AUPRC of 0.925/0.993; coordinate controls further show that recent history contributes beyond explicit progress metadata. GazeFS therefore improves Focus target centering and empirical residual contraction while leaving temporal smoothness as a separate objective.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.03868 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T00:28:03.007Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).