Search Keywords

Results Restricted To:

https://www.temple.edu

Total Results: 98

Boosting Chamfer Matching by Learning Chamfer Distance Normalization

https://cis.temple.edu/~latecki/Papers/ChamferECCVFinal.pdf

2 Related work There is a large number of applications of chamfer matching in computer vision and in medical image analysis. Chamfer distance was first introduced by Barrow et al. [2] in 1977 with a goal of matching two collections of contour fragments. Until today chamfer matching is widely used in object detection and classifica-tion task due to its tolerance to misalignment in position ...

IEEE MASS 2023 - Temple University

https://cis.temple.edu/ieeemass2023/

The 20th IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS 2023) September 25 - 27, 2023 Toronto, Canada

Computer and Information Science PhD - Temple University

https://www.temple.edu/academics/degree-programs/computer-information-science-phd-st-cis-phd

Prepare to undertake independent research leading to science and engineering advances in computer and information sciences.

Dr. Jie Wu - 2024 Publications

https://cis.temple.edu/~jiewu/research/publications/Publications_2024.html

W. Tang, T. Ai, and J. Wu, " Tiresias: Optimizing NUMA Performance with CXL Memory and Locality-Aware Process Scheduling," Proc. of the ACM Turing Award Celebration Conference (ACM TURC), Jun 5-7, 2024.

stoj-1.qxd - Temple University

https://cis.temple.edu/~wu/teaching/Spring%202013/handoff.pdf

1.1 INTRODUCTION Mobility is the most important feature of a wireless cellular communication system. Usu-ally, continuous service is achieved by supporting handoff (or handover) from one cell to another. Handoff is the process of changing the channel (frequency, time slot, spreading code, or combination of them) associated with the current connection while a call is in progress. It is often ...

The OpenNARS implementation of the Non-Axiomatic Reasoning System

https://cis.temple.edu/~pwang/Publication/OpenNARS.pdf

NARS utilises the Non-Axiomatic Logic (NAL) [9] for inference and the Nars-ese language for representing statements. The language and the logic are outside the scope of this document. The aim of this paper is to describe the current implementation of NARS in detail. The following aspects of the implementa-tion are focused on: memory management with concept centric processing, non-deterministic ...

Building Classification Models: ID3 and C4.5 - Temple University

https://cis.temple.edu/~ingargio/cis587/readings/id3-c45.html

Introduction ID3 and C4.5 are algorithms introduced by Quinlan for inducing Classification Models, also called Decision Trees, from data.

TileSR: Accelerate On-Device Super-Resolution with Parallel Offloading ...

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 ...