FAIR - Fundamental and Applied Information Technology 

VISLab member presents a contribution on "Performance Evaluation of Mediapipe and Openpose for Skeleton Data Extraction"

In this study, our focus lies in evaluating two approaches for extracting skeletal data based on OpenPose and Mediapipe frameworks across the KTH and UTD-MHAD datasets. The skeletal data extracted from both methods serves as input for the AcTv2 model, an enhanced version of the AcT model. Through training and evaluating on the AcTv2 model, we ascertain the effectiveness of both skeletal data extraction methods on specific datasets. The experimental results of this research contribute to a better understanding of the efficacy of these skeletal data extraction methods in providing informative data for the AcTv2 model to recognize human actions across different datasets.

ACIIDS 2016 is an international scientific conference for research in the field of intelligent information and database systems, to be held during 14-16 March, 2016 in Da Nang, Vietnam.

The aim of the conference is to provide an internationally respected forum for scientific research in the technologies and applications of intelligent information and database systems.

The conference is hosted by Vietnam-Korea Friendship Information Technology College (Viethanit), Vietnam and jointly organized by Wrocław University of Technology, Poland in cooperation with IEEE SMC Technical Committee on Computational Collective Intelligence, Bina Nusantara University, Indonesia, Ton DucThang University, Vietnam, and QuangBinh University, Vietnam.

Participant from ISLab is Dr. Van-Dung Hoang with the contributions: "Accelerative Object Classification Using Cascade Structure for Vision Based Security Monitoring Systems" and "Multiscale Car Detection Using Oriented Gradient Feature and Boosting Machine"

Over all, everything is well organized.