High-accuracy, low-latency gaze tracking is becoming one of the indispensable features in augmented reality (AR) head-mounted devices (HMDs). Researchers have proposed different approaches to predict gaze positions from eye images. However, since only the eye modality is focused, these appearance-based algorithms are still struggle to trade off the accuracy and running speed in HMDs. In this paper, we propose a lightweight multi-modal network (HE-Tracker) to regress gaze positions. By fusing head-movement features with eye features, HE-Tracker achieves comparable accuracy (3.655° in all subjects) and $27 \times$ speedup (48 fps in the specialized AR HMD) compared to the state-of-the-art gaze tracking algorithm. We further demonstrate that when applying our head-eye coordination strategy to other baseline models, all these models achieve at least 6.36% performance improvement without a pronounced effect on running speed. Moreover, we construct HE-Gaze, the first multi-modal dataset with eye images and head-movement data for near-eye gaze tracking. This dataset is currently made of 757,360 frames and 15 persons, providing an opportunity to foster research in multi-modal gaze tracking approaches. Our dataset is available at DOWNLOAD LINK1.

Due to the explosive growth of Internet traffic, network operators must be able to monitor the whole network situations and manage their network resources in an efficient way. Traditional network analysis method that works on a single machine are no longer suitable for this huge traffic data due to its poor processing ability. Some big data frameworks, such as Hadoop and Spark, can handle such analysis job even for large network traffic, but they are inherently designed for offline data analysis. In this paper, we treat the online network analysis as a stream analysis problem and use Spark Streaming to cope with the high-speed Internet traffic data in real time. The system consists of two parts, collector and stream processor. Firstly, several collectors capture network traffic data from switches through mirrored ports and send the packet information to a central stream processor which is a cluster running Spark Streaming. Then, the stream processor analyzes the input data streams and calculates Internet performance metrics. We take TCP performance monitoring as an example to show how network measurement can be done using the stream processing platform. Finally, we conducted typical experiments in a cluster of 3 computers with the standalone mode, showing that our system performs well in huge Internet traffic measurement and monitoring.