Content-based management of human motion data: survey and challenges

J Sedmidubsky, P Elias, P Budikova, P Zezula - IEEE Access, 2021 - ieeexplore.ieee.org
Digitization of human motion using skeleton representations offers exciting possibilities for a
large number of applications but, at the same time, requires innovative techniques for their …

LSTM-based real-time action detection and prediction in human motion streams

F Carrara, P Elias, J Sedmidubsky, P Zezula - Multimedia Tools and …, 2019 - Springer
Motion capture data digitally represent human movements by sequences of 3D skeleton
configurations. Such spatio-temporal data, often recorded in the stream-based nature, need …

Learned metric index—proposition of learned indexing for unstructured data

M Antol, J Ol'ha, T Slanináková, V Dohnal - Information Systems, 2021 - Elsevier
The main paradigm of similarity searching in metric spaces has remained mostly unchanged
for decades—data objects are organized into a hierarchical structure according to their …

Understanding the gap between 2D and 3D skeleton-based action recognition

P Elias, J Sedmidubsky, P Zezula - 2019 IEEE International …, 2019 - ieeexplore.ieee.org
Large volumes of RGB video data are recorded and processed every day. One of the
embedded data modality within these videos is the information about human motions. Up to …

DeepSegment: Segmentation of motion capture data using deep convolutional neural network

H Yasin, S Hayat - Image and Vision Computing, 2021 - Elsevier
In this paper, we propose a novel framework to segment 3D human motion capture data into
distinct behaviors. First, in preprocessing, we build a normalized pose space by eliminating …

Similarity search in 3D human motion data

J Sedmidubsky, P Zezula - Proceedings of the 2019 on International …, 2019 - dl.acm.org
Motion capture technologies can digitize human movements into a discrete sequence of 3D
skeletons. Such spatio-temporal data have a great application potential in many fields …

Understanding the Motion Adaption of Machine Using Long Short–Term Memory Networks for voiceless Virtual Assistant

S Roy, B Das - International Journal of Digital Technologies, 2023 - journal.nielit.edu.in
In recent years, the study of computer vision and pattern recognition has seen a significant
increase in the popularity of video-based human action recognition as a research topic …

Benchmarking search and annotation in continuous human skeleton sequences

J Sedmidubsky, P Elias, P Zezula - Proceedings of the 2019 on …, 2019 - dl.acm.org
Motion capture data are digital representations of human movements in form of 3D
trajectories of multiple body joints. To understand the captured motions, similarity-based …

Similarity-Based Processing of Motion Capture Data

J Sedmidubsky, P Zezula - Proceedings of the 26th ACM international …, 2018 - dl.acm.org
Motion capture technologies digitize human movements by tracking 3D positions of specific
skeleton joints in time. Such spatio-temporal data have an enormous application potential in …

[PDF][PDF] Advancing Management of Complex Data in Metric Spaces

RM ANTOL - is.muni.cz
Most of the data emerging in modern applications are complex in nature, which presents
specific challenges in their processing. To manage, retrieve and analyze complex data, the …