https://cis.temple.edu/~latecki/Papers/JoPanECAI2024.pdf
This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0).
https://cis.temple.edu/~latecki/Papers/ACM_MM2023.pdf
ABSTRACT Image stitching aims to align a pair of images in the same view. Generating precise alignment with natural structures is challeng-ing for image stitching, as there is no wider field-of-view image as a reference, especially in non-coplanar practical scenarios. In this paper, we propose an unsupervised image stitching frame-work, breaking through the coplanar constraints in homography ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/Paper%206190%20Camera%20Ready%20Version.pdf
a major challenge for federated learning in diverse settings. Personalized Federated Learning (PFL), [Tan et al., 2022a] addresses these issues by allowing client-specific models that leverage global insights to enhance local outcomes. The main challenge in PFL lies in balancing global knowledge sharing with preserving client-specific information, making the trade- off an important research ...
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://cis.temple.edu/~yu/research/HearBP-info24.pdf
Abstract—Continuous blood pressure (BP) monitoring using wearable devices has received increasing attention due to its importance in diagnosing diseases. However, existing methods mainly measure BP intermittently, involve some form of user effort, and suffer from insuficient accuracy due to sensor properties. In order to overcome these limitations, we study the BP measurement technology ...
https://cis.temple.edu/tagit/presentations/Hopfield%20Networks%20is%20all%20you%20need.pdf
Classical Binary Hopfield Networks More complicated, patterns like (binary) images can be learned.
https://commencement.temple.edu/sites/commencement/files/TU-Comm-Program-05-07-2021.pdf
I couldn’t be more proud of the diverse and driven students who are graduating this spring. Congratulations to all of you, to your families and to our dedicated faculty and academic advisors who had the pleasure of educating and championing you. If Temple’s founder Russell Conwell were alive to see your collective achievements today, he’d be thrilled and amazed. In 1884, he planted the ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/Paper%206750%20Camera%20Ready%20Version.pdf
FedHAN: A Cache-Based Semi-Asynchronous Federated Learning Framework Defending Against Poisoning Attacks in Heterogeneous Clients Xiaoding Wang1 , Bin Ye1 , Li Xu1 , Sun-Yuan Hsieh2 , Jie Wu3;4 and Limei Lin1 1College of Computer and Cyber Security, Fujian Provincial Key Laboratory of Network Security and Cryptology, Fujian Normal University, Fuzhou 350117, China 2Department of Computer ...
https://cis.temple.edu/tagit/presentations/Sparks%20of%20AGI%20Early%20Experiments%20with%20GPT4.pdf
Paper Review: 'Sparks of Artificial General Intelligence: Early experiments with GPT-4' Authors: Sebastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, Yi Zhang
https://cis.temple.edu/~jiewu/research/publications/Publication_files/jiang_www_2020.pdf
ABSTRACT Serendipity recommendation has attracted more and more atten-tion in recent years; it is committed to providing recommendations which could not only cater to users’ demands but also broaden their horizons. However, existing approaches usually measure user-item relevance with a scalar instead of a vector, ignoring user preference direction, which increases the risk of unrelated ...