Lévy Attention: Single-Pass Predictive Uncertainty for Continuous-Time Attention
该研究通过引入Lévy Attention方法，解决了不规则采样时间序列模型在任意连续时间戳查询时缺乏预测可信度的问题。
0 citationsRead paper
Selected work
Representative Papers
Gaze Prediction in Virtual Reality Without Eye Tracking Using Visual and Head Motion Cues
This work proposes a lightweight multimodal approach to accurately predict user gaze direction in virtual reality scenarios where eye-tracking hardware is unavailable or restricted by privacy constraints—a critical capability for techniques such as foveated rendering. The method uniquely integrates head-mounted display (HMD) motion signals with visual saliency cues from video frames by leveraging UniSal for visual feature extraction and combining TSMixer with LSTM to construct a temporal prediction module. Experiments on the EHTask dataset and commercial VR devices demonstrate that the proposed approach significantly outperforms baseline methods such as Center-of-HMD and Mean Gaze, achieving high prediction accuracy, low latency, and practical deployability without requiring eye-tracking data, thereby enhancing the naturalness and efficiency of VR interactions.
0 citationsRead paper
Recent publications
Latest Papers
Lévy Attention: Single-Pass Predictive Uncertainty for Continuous-Time Attention
该研究通过引入Lévy Attention方法，解决了不规则采样时间序列模型在任意连续时间戳查询时缺乏预测可信度的问题。
0 citationsRead paper
Gaze Prediction in Virtual Reality Without Eye Tracking Using Visual and Head Motion Cues
This work proposes a lightweight multimodal approach to accurately predict user gaze direction in virtual reality scenarios where eye-tracking hardware is unavailable or restricted by privacy constraints—a critical capability for techniques such as foveated rendering. The method uniquely integrates head-mounted display (HMD) motion signals with visual saliency cues from video frames by leveraging UniSal for visual feature extraction and combining TSMixer with LSTM to construct a temporal prediction module. Experiments on the EHTask dataset and commercial VR devices demonstrate that the proposed approach significantly outperforms baseline methods such as Center-of-HMD and Mean Gaze, achieving high prediction accuracy, low latency, and practical deployability without requiring eye-tracking data, thereby enhancing the naturalness and efficiency of VR interactions.
0 citationsRead paper