Metraipolis › archive › dc_74ba8034247a
GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction — arXiv:2609.38519
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38519
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:47:14.994Z
- SHA-256 of the archived text
f53307bf153b307a01c84074429c943b14bf5dd42e2e23cde0a0be195e699cbb- Stable URL of this page
https://metraipolis.com/documento/dc_74ba8034247a
How to cite
GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction — arXiv:2609.38519 — arXiv (en), https://arxiv.org/abs/2609.38519 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_74ba8034247a (Metraipolis archive dc_74ba8034247a, sha256 f53307bf153b307a01c84074429c943b14bf5dd42e2e23cde0a0be195e699cbb)
BibTeX
@misc{dc74ba8034247a,
title = {GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction — arXiv:2609.38519},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38519},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_74ba8034247a; sha256 f53307bf153b307a01c84074429c943b14bf5dd42e2e23cde0a0be195e699cbb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38519. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Egocentric gaze prediction enables many downstream applications but remains challenging, as human gaze is inherently stochastic. This stochasticity is constrained by structured temporal dynamics alternating between fixations and saccades, top-down influences from tasks, and bottom-up visual saliency. Based on this observation, we introduce GazeFlow, a framework that directly models gaze as a joint distribution of temporal gaze positions conditioned upon both top-down and bottom-up information. In particular, GazeFlow uses conditional flow matching (CFM): a learned velocity field iteratively transports a Gaussian noise sample into a plausible gaze trajectory drawn from this joint distribution. The velocity field is conditioned on bottom-up visual features extracted by a video encoder and on top-down task information obtained by globally querying these features. On standard datasets, GazeFlow achieves state-of-the-art performance on per-frame metrics, and the generated trajectories align better with human gaze temporal dynamics. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.38519 — 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 2026-10-07T13:18:10.572Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).