{"ID":5675978,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-04T19:47:23.739882828Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01437","arxiv_id":"2607.01437","title":"How Much Future Helps? A Controlled Study of Future-Privileged Supervision for Causal Egocentric Gaze Estimation","abstract":"Egocentric gaze estimation is commonly studied using models that process the full video with access to future frames, while real-world applications require strictly causal, online prediction. This discrepancy raises key questions: Does future context inherently provide valuable signals for gaze estimation? If so, how much future look-ahead optimally supervises a causal model during training? To investigate, we propose a controlled framework featuring a future-aware branch that accesses a tunable look-ahead horizon during training but is discarded at inference. This design isolates the impact of future context while keeping the inference architecture fixed and strictly causal. Across EGTEA Gaze+ and Ego4D, we find that future-privileged supervision consistently improves causal gaze prediction, confirming its utility. However, performance gains do not increase monotonically with longer look-ahead, but rather peak within a bounded temporal regime. Specifically, optimal performance corresponds to roughly 1.7--3.3 seconds of future context ($H{\\in}[5, 10]$) on EGTEA Gaze+ and 2.7 seconds ($H{=}10$) on Ego4D. Our results demonstrate that lightweight causal models can effectively absorb future-aware signals, providing practical guidance for real-time egocentric gaze modeling.","short_abstract":"Egocentric gaze estimation is commonly studied using models that process the full video with access to future frames, while real-world applications require strictly causal, online prediction. This discrepancy raises key questions: Does future context inherently provide valuable signals for gaze estimation? If so, how m...","url_abs":"https://arxiv.org/abs/2607.01437","url_pdf":"https://arxiv.org/pdf/2607.01437v1","authors":"[\"Jia Li\",\"Wenjie Zhao\",\"Fnu Atisri\",\"Sanskriti Aripineni\",\"Shijian Deng\",\"Jon E. Froehlich\",\"Yuhang Zhao\",\"Yapeng Tian\"]","published":"2026-07-01T20:00:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}