How Much Future Helps? A Controlled Study of Future-Privileged Supervision for Causal Egocentric Gaze Estimation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Gaze EstimationSimilar Papers 제목 키워드 기반
Revealing the unseen: Benchmarking video action recognition under occlusion
In this work, we study the effect of occlusion on video action recognition. To facilitate this study, we propose three benchmark datasets and experiment with seven different video action recognition models. These dataset…
Continual Learning via Neural Pruning
We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the i…
Continual LearningDiagnosticLifelong learningFiltering Noisy Parallel Corpus using Transformers with Proxy Task Learning
This paper illustrates Huawei’s submission to the WMT20 low-resource parallel corpus filtering shared task. Our approach focuses on developing a proxy task learner on top of a transformer-based multilingual pre-trained l…
Language ModelingLanguage ModellingMachine TranslationTranslationDisentangling Visuo-Tactile Foresight: Oracle-Guided Interface Discovery for World Action Models
Contact-rich manipulation remains challenging because successful control depends on physical interaction cues that are often weakly observable from vision alone. Recent tactile world action models jointly model future vi…
TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering
AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measurements. We introduce TadA-Bench, a milli…