Saved in:
Bibliographic Details
Main Authors: Ghosh, Partho, Hossain, Raisa Bentay, Zunaed, Mohammad, Hasan, Taufiq
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.12678
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915200460914688
author Ghosh, Partho
Hossain, Raisa Bentay
Zunaed, Mohammad
Hasan, Taufiq
author_facet Ghosh, Partho
Hossain, Raisa Bentay
Zunaed, Mohammad
Hasan, Taufiq
contents Automatic video activity recognition is crucial across numerous domains like surveillance, healthcare, and robotics. However, recognizing human activities from video data becomes challenging when training and test data stem from diverse domains. Domain generalization, adapting to unforeseen domains, is thus essential. This paper focuses on office activity recognition amidst environmental variability. We propose three pre-processing techniques applicable to any video encoder, enhancing robustness against environmental variations. Our study showcases the efficacy of MViT, a leading state-of-the-art video classification model, and other video encoders combined with our techniques, outperforming state-of-the-art domain adaptation methods. Our approach significantly boosts accuracy, precision, recall and F1 score on unseen domains, emphasizing its adaptability in real-world scenarios with diverse video data sources. This method lays a foundation for more reliable video activity recognition systems across heterogeneous data domains.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12678
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Domain Generalization for Improved Human Activity Recognition in Office Space Videos Using Adaptive Pre-processing
Ghosh, Partho
Hossain, Raisa Bentay
Zunaed, Mohammad
Hasan, Taufiq
Computer Vision and Pattern Recognition
Automatic video activity recognition is crucial across numerous domains like surveillance, healthcare, and robotics. However, recognizing human activities from video data becomes challenging when training and test data stem from diverse domains. Domain generalization, adapting to unforeseen domains, is thus essential. This paper focuses on office activity recognition amidst environmental variability. We propose three pre-processing techniques applicable to any video encoder, enhancing robustness against environmental variations. Our study showcases the efficacy of MViT, a leading state-of-the-art video classification model, and other video encoders combined with our techniques, outperforming state-of-the-art domain adaptation methods. Our approach significantly boosts accuracy, precision, recall and F1 score on unseen domains, emphasizing its adaptability in real-world scenarios with diverse video data sources. This method lays a foundation for more reliable video activity recognition systems across heterogeneous data domains.
title Domain Generalization for Improved Human Activity Recognition in Office Space Videos Using Adaptive Pre-processing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.12678