This paper aims to simultaneously consider two inseparable issues for privacy setting recommendation: (1) sensitiveness of visual content of the images being shared; and (2) trustworthiness of users being granted. Fir...
详细信息
This paper aims to simultaneously consider two inseparable issues for privacy setting recommendation: (1) sensitiveness of visual content of the images being shared; and (2) trustworthiness of users being granted. First, an object-based approach is developed for image content sensitiveness (privacy) representation. Secondly, the users on a social network are clustered into a set of representative social groups to generate a discriminative dictionary for user trustworthiness characterization. Finally, a tree classifier is trained hierarchically to recommend appropriate privacy settings for image sharing.
Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images an...
详细信息
Current cloud data centers are fully virtualized for service consolidations and power/energy reduction. Although virtualization could reduce real time power and overall energy consumption, the energy characteristics o...
详细信息
Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both visual content of images and textual content of questions. To support the VQA task, we need to find good solution...
详细信息
The existing method of task mapping between process models is mostly based on the similarity of labels to get the similarity between tasks, which is affected by a single factor and easy to cause errors. This paper pro...
详细信息
In Mobile Opportunistic Networks, there are special cases of multicast in which destinations (except the total number) are not predetermined. E.g., a person tries to find another three players to play poker without kn...
详细信息
ISBN:
(纸本)9781467398152
In Mobile Opportunistic Networks, there are special cases of multicast in which destinations (except the total number) are not predetermined. E.g., a person tries to find another three players to play poker without knowing them. Achieving efficient data routing in this scenario (target any k destinations among m of them) can be very challenge due to (1) no predetermined destinations, (2) extra delay cost by the destinations collision, and (3) difficulty of the receiver quantity control. We define this as a K-Anycast problem, the goal is to route copies of the message to any k destinations with the shortest average delay. In this paper, we first propose a matching method to solve the problem in a centralized way. We then bring forward a layered hierarchical structure where nodes are organized according to their degree of activities. Based on the structure, two routing algorithms are proposed where K-Cast initializes exactly k copies of the message without replication in the middle, K-Epidemic performs epidemic routing only in a controlled range. Both algorithms will first forward copies upwards along the structure and then downwards to the destinations. Experiments on real data trace show that the proposed algorithms achieve much better delay, delivery ratio and lower forwarding numbers.
Automatic prediction of photo aesthetic quality is useful for many practical purposes. Current computational approaches typically solved this problem by assigning a categorical label (good or bad) to a photo. However,...
详细信息
ISBN:
(纸本)9781509018987
Automatic prediction of photo aesthetic quality is useful for many practical purposes. Current computational approaches typically solved this problem by assigning a categorical label (good or bad) to a photo. However, due to the subjectivity and complexity of humans aesthetic judgments, only a categorical label is insufficient to represent humans perceived aesthetic quality of a photo. This paper focuses on an interesting problem: is it possible to predict the crowed opinions about the aesthetic quality of a photo? The crowed opinion here is expressed by the distribution of scores given by a number of subjects. For each given photo, a deep convolutional neural network (DCNN) is utilized to calculate its feature representation. Afterwards, the crowed opinion prediction problem is formulated as one of label distribution learning (LDL). Experiments show that the proposed method is highly effective and outperforms state-of-the-art algorithms.
Bicycle sharing system has emerged as a new mode of transportation in many big cities over the past *** the large number of bicycle stations distribute widely in the city,it is difficult to identify their unique attri...
详细信息
Bicycle sharing system has emerged as a new mode of transportation in many big cities over the past *** the large number of bicycle stations distribute widely in the city,it is difficult to identify their unique attributes and characteristics *** to the real bicycle hire dataset in Hangzhou,China,the clustering analysis for the bicycle stations based on the temporal flow data was carried out ***,based on the spatial distribution and temporal attributes of calculated clusters,visual diagram and map were used to vividly analyze the bicycle hire behavior related to station category and study the travel rules of *** experimental results demonstrate the relation between human mobility,the time of day,day of week and the station location.
Public bicycle sharing services are becoming popular over the past decade. The behavior of using public bicycle system(PBS) produces numerous hire records involving citizens' movement. This paper presents a visual...
详细信息
Public bicycle sharing services are becoming popular over the past decade. The behavior of using public bicycle system(PBS) produces numerous hire records involving citizens' movement. This paper presents a visual analytics system-Touching PBSData, to help both traffic administrators and ordinary citizens visually explore and understand PBS data on multi-touch devices. Tasks and design principles are put forward firstly. Four views are designed to show different aspects of the dataset, including the geographical distribution, the spatio-temporal pattern and personal relevant information. In order to enhance the flexibility and usability of system, the organization mode of views and rich user interaction suitable for multi-touch device are further studied. By adopting real PBS dataset, the results of case studies certify that our method is able to help analyzers to find stations' main function and citizens' travel habits. Moreover, the feedback from the participants with various backgrounds is very affirmative through the user study.
A new generation memory, Non-Volatile Memory (NVM), such as Phase-Change Memory (PCM), has been adopted together with DRAM in the main memory to form the hybrid main memory for low energy consumption and high capacity...
详细信息
暂无评论