We present an integrated prefetching and caching proxy, termed iPac, for HTTP-based adaptive video streaming services like Netflix and YouTube. The challenge we address is maximizing the byte-hit ratio for proxies through prefetching in the context of the limited bandwidth between proxies and content servers. The problem is NP-hard, and the best approximation ratio that any optimal offline algorithm can achieve is 1-e--1 ≈ 0.63. Considering that offline algorithms cannot be applied to real-time applications with stringent time constraints, we propose a novel 0.5-competitive online prefetching algorithm which, to the best of our knowledge, has the best lower bound so far. We evaluate the performance of iPac by deploying it over the Amazon EC2 cloud accepting user requests from the video clients deployed on the PlanetLab based on a real trace of user requests for YouTube videos. Our experimental results demonstrate that iPac can significantly improve the performance in terms of byte-hit ratio (up to 84%) and video rates (up to 34%), compared with the state-of-the-art approaches. The proposed iPac is compatible with existing HTTP-based adaptive streaming implementations without requiring any modification to existing content servers and video clients.

It is of great importance in a WiFi network to achieve a good user experience and fair allocation of the limited bandwidth resource. In this paper we propose the design of a cross-layer AP (Access Point) centric streaming scheduler for DASH (Dynamic Adaptive Streaming over HTTP) in multirate 802.11 wireless networks. Residing at the AP, the scheduler achieves proportional fairness at the packet level by implementing weighted fair queuing. At the request level, the scheduler uses URL redirection to modify the client's request when necessary to reduce playback freezes and fluctuations. Extensive simulations in ns2 show that our scheduler improves the clients' playback experiences and achieves a fairer bandwidth allocation while fully utilizing the available bandwidth resource.

Mobile video streaming sometimes suffers from playback interruptions which are typically due to considerable network bandwidth variations that a user may experience when s/he travels along a route. Segmented adaptive HTTP streaming that switches between video streams encoded at different bitrates -- and hence different quality levels -- can be used to alleviate the issues of variable bandwidth. An important issue with respect to users' perceived experience is how the system schedules the quality levels to match the end-to-end network bandwidth capacity. It is very beneficial if the application can estimate the future network conditions in advance, and therefore perform quality control and buffer control wisely.

Due to technological advances and the popularity of camera sensors, it is now straightforward for users to capture and share videos. A large number of geo-tagged photos and videos have been accumulating continuously on the web, posing a challenging problem for mining this type of media data. In one application scenario, users might desire to know what the Points of Interest (POI) are which contain important objects or places in a video. Existing solutions attempt to examine the content of the videos and recognize objects and events. This is typically time-consuming and computationally expensive and the results can be uneven. Therefore these methods face challenges when applied to large video repositories. We propose a novel technique that leverages sensor-generated meta-data (camera locations and viewing directions) which are automatically acquired as continuous streams together with the video frames. Existing smartphones can easily accommodate such integrated recording tasks. By considering a collective set of videos and leveraging the acquired auxiliary meta-data, our approach is able to detect interesting regions and objects (POIs) and their distances from the camera positions in a fully automated way. Because of its computational efficiency, the proposed method scales well and our experiments show very promising results.

To present user-generated videos that relate to geographic areas for easy access and browsing it is often natural to use maps as interfaces. A common approach is to place thumbnail images of video keyframes in appropriate locations. Here we consider the challenge of determining which keyframes to select and where to place them on the map. Our proposed technique leverages sensor-collected meta-data which are automatically acquired as a continuous stream together with the video. Our approach is able to detect interesting regions and objects (hotspots) and their distances from the camera in a fully automated way. Meaningful keyframes are adaptively selected based on the popularity of the hotspots. Our experiments show very promising results and demonstrate excellent utility for the users.

Result presentations from searches into video repositories is still a challenging problem. Current systems usually display a ranked list that shows the first frame of each video. Users then explore the videos one-by-one. In our recent work we have investigated the fusion of captured video with a continuous stream of sensor meta-data. These so-called sensor-rich videos can conveniently be captured with today's smartphones. Importantly, the recorded sensor-data streams enable processing and result resentation in novel and useful ways.

Mobile devices are increasingly popular for the versatile capture and delivery of video content. However, the acquisition and transmission of large amounts of video data on mobile devices face fundamental challenges such as power and wireless bandwidth constraints. To support diverse mobile video applications, it is critical to overcome these challenges. We present a design framework that brings together several key ideas to enable energy-efficient mobile video management applications. First, we leverage off-the-shelf smartphones as mobile video sensors. Second, concurrently with video recordings we acquire geospatial sensor meta-data to describe the videos. Third, we immediately upload the meta-data to a server to enable low latency video search. This last step allows for very energy-efficient transmissions, as the sensor data sets are small and the bulky video data can be uploaded on demand, if and when needed. We present the design, a simulation study, and a preliminary prototype of the proposed system. Experimental results show that our approach substantially prolongs the battery life of mobile devices while only slightly increasing the search