Customers' social ties have played a crucial role in influencing their consumption behaviors. Generally, users can influence others' consumption behaviors via word-of-mouth.But in some special industry such as telecom, some kinds of indirect influences also exist between users and some applications such as social recommendation have been researched on the basis of these influences. In order to explore such influences, this paper selects some attributes to outline the users' consumption behaviors and explores the relationship of the social ties and the behaviors via some analysis experiments.The results show that (1) the social tie attributes have strong correlations with users' consumption behaviors similarity; (2) as the strength of the telecom social ties improve, the similarity value of the users' value-added services using behaviors get greater but (3) the communication behaviors don't have a strong correlation with the strength of telecom social ties.
The success of the state-of-the-art video deblurring methods stems mainly from implicit or explicit estimation of alignment among the adjacent frames for latent video restoration. However, due to the influence of the blur effect, estimating the alignment information from the blurry adjacent frames is not a trivial task. Inaccurate estimations will interfere the following frame restoration. Instead of estimating alignment information, we propose a simple and effective deep Recurrent Neural Network with Multi-scale Bi-directional Propagation (RNN-MBP) to effectively propagate and gather the information from unaligned neighboring frames for better video deblurring. Specifically, we build a Multi-scale Bi-directional Propagation (MBP) module with two U-Net RNN cells which can directly exploit the inter-frame information from unaligned neighboring hidden states by integrating them in different scales. Moreover, to better evaluate the proposed algorithm and existing state-of-the-art methods on real-world blurry scenes, we also create a Real-World Blurry Video Dataset (RBVD) by a well-designed Digital Video Acquisition System (DVAS) and use it as the training and evaluation dataset. Extensive experimental results demonstrate that the proposed RBVD dataset effectively improve the performance of existing algorithms on real-world blurry videos, and the proposed algorithm performs favorably against the state-of-the-art methods on three typical benchmarks. The code is available at https://github.com/XJTU-CVLAB-LOWLEVEL/RNN-MBP.
The scarcity problem in user-product matrix has become severe, which is affecting the recommendation system efficiency in mobile services; it is also related to social networks and Internet of Things, where huge amount of data and complex relationships exist. This paper proposes a novel recommendation approach based on social relationships between users to handle the scarcity problem and facilitate recommendations in mobile services. We define a model of social relationships based on a set of call detail record factors of telecom users and design a vacancy-filling method to reduce the scarcity of the user-product matrix. An integrated similarity measure is provided to improve the filtering rules of neighbours of the target user. Then, we build a new recommendation system based on social relationships, with mobile services in the telecom industry as the application. Furthermore, we conductexperiments with the real-world data of voice calls, and experimental results show that the filling method proposed can effectively reduce the scarcity of the user-product matrix and our social relationships approach outperforms the collaborative filtering in terms of the call, precision and mean absolute error indicators.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.