Mohammad Karimiabdolmaleki

Mohammad Karimiabdolmaleki
University of Alberta | UAlberta · Department of Computing Science

Master of Science

About

2
Publications
1,480
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
0
Citations
Citations since 2017
2 Research Items
0 Citations
20172018201920202021202220230.00.20.40.60.81.0
20172018201920202021202220230.00.20.40.60.81.0
20172018201920202021202220230.00.20.40.60.81.0
20172018201920202021202220230.00.20.40.60.81.0
Introduction
In our most recent project, we have used a mixture of four datasets: “HMDB51”, “CHARADES EGO”, “The Twenty Billion Something Something” and "UCF-101". With spending a lot of time selecting the best videos from more than 220000 video files, our collection is surprisingly considerable for those who need an indoor human activities dataset for Neural Network Model purposes.

Publications

Publications (2)
Thesis
Full-text available
Robots are trying to be an integral part of human life soon. With the development of societies and increasing the expectations of people, it is now desirable to make the future more convenient. We are now pleased to tell that we have gathered a collection of high-quality indoor activities from the latest and hottest datasets around the web. Althoug...
Technical Report
Full-text available
Nowadays service robots are very useful and become a part of our life. These robots can help us in daily activities in an easy interactive way. In this article we present how a Service Human Robot (SHR) can be programmed to do several tasks in a home-like environment i.e. navigating to a given loca-tion, recognizing, grasping and bringing objects e...

Network

Projects

Project (1)
Project
In our most recent project, we have used a mixture of four datasets: “HMDB51”, “CHARADES EGO”, “The Twenty Billion Something Something” and "UCF-101". With spending a lot of time selecting the best videos from more than 220000 video files, our collection is surprisingly considerable for those who need an indoor human activities dataset for Neural Network Model purposes. We are using the dataset for our Human Action Recognition platform that tries to give some knowledge about the human actions to the Robot. This is a benefit for both human and the robot since a better understanding of human needs and desires will be acheivable by the robot. At the end, we try to attach this ability to the Human Support Robot.