https://cis.temple.edu/~jiewu/research/publications/Publication_files/DiVE.pdf
Abstract—Ensuring stable and high-quality real-time video an-alytics for computationally constrained mobile agents is essential. However, limited computing resources and network bandwidth present significant challenges in meeting the objective of low response time and high inference accuracy. In this paper, we present DiVE, an edge-assisted video analytics system that utilizes motion vectors ...
https://www.fox.temple.edu/sites/fox/files/documents/Cummins%20Conference%202022/RILA_Moenig_JRI_final.pdf
Registered index-linked annuities (RILAs) are increasingly popular equity-based re-tirement savings products o ered by U.S. life insurance companies. They combine features of xed-index annuities and traditional variable annuities (TVAs), o ering in-vestors equity exposure with downside protection in a tax-deferred setting. This article introduces RILAs to the academic literature by describing ...
https://www.fox.temple.edu/sites/fox/files/Frontiers-Machines-versus-Humans-The-Impact-of-Artificial-Intelligence-Chatbot-Disclosure-on-Customer-Purchases.pdf
Abstract. Empowered by artificial intelligence (AI), chatbots are surging as new technol-ogies with both business potential and customer pushback. This study exploits field ex-periment data on more than 6,200 customers who are randomized to receive highly structured outbound sales calls from chatbots or human workers. Results suggest that undisclosed chatbots are as effective as pro ficient ...
https://cis.temple.edu/~latecki/Papers/Quan_DRBANET_ICIP_2022.pdf
ABSTRACT Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years. However, most of them ignore the benefit of boundary information. This paper introduces a lightweight dual-resolution network, called DRBANet, aim-ing to refine semantic segmentation results with the aid of boundary information. DRBANet also ...
https://sites.temple.edu/ticlj/files/2017/02/23.2.Hughes-TICLJ.pdf
ABSTRACT The goal of this Comment is to highlight the disconnect between the theoretical law and economics debate over the merits of insider trading regulations and the empirical body of work regarding the effect of these regulations on stock market efficiency. This Comment first summarizes the theories of insider trading which have heretofore consumed and defined this law and economics debate ...
https://cis.temple.edu/~wu/teaching/Spring2020_CIS5644_Distributed_Computing/distributed-computing-2020-notes-1.pdf
A distributed system is collection of independent computers that appear to the users of the system as single computer.
https://cis.temple.edu/~latecki/Papers/DSP_PAMI2014.pdf
Abstract—In this paper, we present a novel partition framework, called dense subgraph partition (DSP), to automatically, precisely and efficiently decompose a positive hypergraph into dense subgraphs. A positive hypergraph is a graph or hypergraph whose edges, except self-loops, have positive weights. We first define the concepts of core subgraph, conditional core subgraph, and disjoint ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/WENJUNJIANG2021TWeb.pdf
In online systems, including e-commerce platforms, many users resort to the reviews or comments generated by previous consumers for decision making, while their time is limited to deal with many reviews. Therefore, a review summary, which contains all important features in user-generated reviews, is expected. In this paper, we study “how to generate a comprehensive review summary from a ...
https://cis.temple.edu/~wu/research/publications/Publication_files/J-CT-2024-Balancing%20Privacy%20and%20Accuracy%20using%20Siginificant%20Gradient%20Protection%20in%20Federated%20Learning.pdf
Abstract—Previous state-of-the-art studies have demonstrated that adversaries can access sensitive user data by membership inference attacks (MIAs) in Federated Learning (FL). Intro-ducing differential privacy (DP) into the FL framework is an effective way to enhance the privacy of FL. Nevertheless, in differentially private federated learning (DP-FL), local gradients become excessively ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/m37113-chen%20final.pdf
Abstract—Recent years have witnessed the unprecedented performance of convolutional networks in image super-resolution (SR). SR involves upscaling a single low-resolution image to meet application-specific image quality demands, making it vital for mobile devices. However, the excessive computational and memory requirements of SR tasks pose a challenge in mapping SR networks on a single ...