Adaptive dimensionality reduction for efficient deep learning on temporal video datasets

Abstract In the domain of computer vision and its related research fields, especially in temporal data handling, the analysis and processing of high dimensional data is a huge problem. Challenges in deep learning-based high dimension data processing often arise from their variable length sequences and their complex data patterns. As the use of high dimensional data continues to grow, the demand for dimension reduction of complex data is growing rapidly. Dimensionality reduction is the process of reducing a high-dimensional matrix of a dataset into a lower dimension. Standard approaches based on principal component analysis, independent component analysis and others, including simple padding and truncation, can lead to data loss or unwanted computational overhead. To address this issue, we introduce a VidSqeOpt method for dimensionality reduction based on feature extraction which exploits statistical approaches with reduced dimension and optimal length finding. Our method is validated on several benchmark datasets that are based on temporal data with complex dimensionality. Cross comparison with the baseline methods shows that our proposed approach adapts to diverse tasks, achieving up to 2.0% higher accuracy while reducing per-frame processing time by at least 23.7%, down to ≤0.45 seconds.

Authors

Institutions

Publication Details

Journal
Knowledge and Information Systems
Published
2026-11-14
DOI
https://doi.org/10.1007/s10115-026-02926-8
Citations
1
Primary Topic
Face and Expression Recognition
Type
article
Field-Weighted Citation Impact
1.46

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Adaptive dimensionality reduction for efficient deep learning on temporal video datasets

Yaseen Yaseen, Oh‐Jin Kwon, Jaeho Kim
1 citations
Knowledge and Information Systems
Face and Expression Recognition
1.46
article

Adaptive dimensionality reduction for efficient deep learning on temporal video datasets

Yaseen Yaseen, Oh‐Jin Kwon, Jaeho Kim
article en
1 citations

Abstract

Abstract In the domain of computer vision and its related research fields, especially in temporal data handling, the analysis and processing of high dimensional data is a huge problem. Challenges in deep learning-based high dimension data processing often arise from their variable length sequences and their complex data patterns. As the use of high dimensional data continues to grow, the demand for dimension reduction of complex data is growing rapidly. Dimensionality reduction is the process of reducing a high-dimensional matrix of a dataset into a lower dimension. Standard approaches based on principal component analysis, independent component analysis and others, including simple padding and truncation, can lead to data loss or unwanted computational overhead. To address this issue, we introduce a VidSqeOpt method for dimensionality reduction based on feature extraction which exploits statistical approaches with reduced dimension and optimal length finding. Our method is validated on several benchmark datasets that are based on temporal data with complex dimensionality. Cross comparison with the baseline methods shows that our proposed approach adapts to diverse tasks, achieving up to 2.0% higher accuracy while reducing per-frame processing time by at least 23.7%, down to ≤0.45 seconds.

Knowledge and Information SystemsVol. 68(1)
Sejong University (KR)
National Research Foundation, National Research Foundation of Korea, Iran Telecommunication Research Center, Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion
Openalex Percentile: Top 22%
Face and Expression Recognition
1.46
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon