Search

YouTube is arguably the most popular online videos sharing site nowadays. To further augment its service with better revenue, it has started working with content owners (known as YouTube partners) whose copyrighted videos and channels have pulled massive audience. By uploading high-quality premium videos, the partners have essentially changed the user-generated content feature of YouTube and further increased YouTube's popularity. Understanding the latest YouTube access pattern is thus crucial to both YouTube and its partners, as well as to other providers of relevant services. In this paper, we for the first time analyze a large-scale YouTube dataset from a partner's view. We make effective use of Insight, a new analytics service of YouTube that offers inside statistics for partners about their content accesses and audience behaviours. From the raw Insight data that are confined to simple scalars and charts, we reveal the inherent relationship among the various metrics that affect the popularity of the videos. Our findings facilitate YouTube partners to adapt their content deployment and user engagement strategies, having great potentials for them to collaborate with YouTube to generate more views and subsequently increasing their revenues.

Video streaming has become one of the most popular networked applications and, with the increased bandwidth and computation power of mobile devices, anywhere and anytime streaming has become a reality. Unfortunately, it remains a challenging task to compress high-quality video in real-time in such devices given the excessive computation and energy demands of compression. On the other hand, transmitting the raw video is simply unaffordable from both energy and bandwidth perspective.In this paper, we propose CAME, a novel cloud-assisted video compression method for mobile devices. CAME leverages the abundant cloud server resources for motion estimation, which is known to be the most computation-intensive step in video compression, accounting for over 90% of the computation time. With CAME, a mobile device selects and uploads only the key information of each picture frame to cloud servers for mesh-based motion estimation, eliminating most of the local computation operations. We develop smart algorithms to identify the key mesh nodes, resulting in minimum distortion and data volume for uploading. Our simulation results demonstrate that CAME saves almost 30% energy for video compression and transmission.

The problem of streaming packetized media has been intensively studied for a long time. In this paper, we revisit this problem in the high-speed railway context, where passengers encode and upload videos through increasingly powerful smartphones. The challenge is highlighted by the fast changing channel conditions in high-speed trains and the limited battery of cell phones. Inspired by the unique spatial-temporal characteristics of wireless signals along high-speed railways, we propose a novel energy-efficient and rate-distortion optimized approach for video streaming. Our solution effectively predicts the signal strength through its spatial-temporal periodicity in this new application scenario. It then smartly adjusts the GOF budget, schedules the video transmission to achieve graceful rate-distortion performance and yet conserves the energy consumption. Performance evaluation based on simulated railway scenarios and H.264 video traces demonstrates the effectiveness of our solution and its superiority as compared to existing solutions.