Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cheng, Shihao, Zhang, Jinlu, Liu, Yue, Tu, Zhigang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2503.23266
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916666188759040
author Cheng, Shihao
Zhang, Jinlu
Liu, Yue
Tu, Zhigang
author_facet Cheng, Shihao
Zhang, Jinlu
Liu, Yue
Tu, Zhigang
contents Human action recognition in low-light environments is crucial for various real-world applications. However, the existing approaches overlook the full utilization of brightness information throughout the training phase, leading to suboptimal performance. To address this limitation, we propose OwlSight, a biomimetic-inspired framework with whole-stage illumination enhancement to interact with action classification for accurate dark video human action recognition. Specifically, OwlSight incorporates a Time-Consistency Module (TCM) to capture shallow spatiotemporal features meanwhile maintaining temporal coherence, which are then processed by a Luminance Adaptation Module (LAM) to dynamically adjust the brightness based on the input luminance distribution. Furthermore, a Reflect Augmentation Module (RAM) is presented to maximize illumination utilization and simultaneously enhance action recognition via two interactive paths. Additionally, we build Dark-101, a large-scale dataset comprising 18,310 dark videos across 101 action categories, significantly surpassing existing datasets (e.g., ARID1.5 and Dark-48) in scale and diversity. Extensive experiments demonstrate that the proposed OwlSight achieves state-of-the-art performance across four low-light action recognition benchmarks. Notably, it outperforms previous best approaches by 5.36% on ARID1.5 and 1.72% on Dark-101, highlighting its effectiveness in challenging dark environments.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23266
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition
Cheng, Shihao
Zhang, Jinlu
Liu, Yue
Tu, Zhigang
Computer Vision and Pattern Recognition
Human action recognition in low-light environments is crucial for various real-world applications. However, the existing approaches overlook the full utilization of brightness information throughout the training phase, leading to suboptimal performance. To address this limitation, we propose OwlSight, a biomimetic-inspired framework with whole-stage illumination enhancement to interact with action classification for accurate dark video human action recognition. Specifically, OwlSight incorporates a Time-Consistency Module (TCM) to capture shallow spatiotemporal features meanwhile maintaining temporal coherence, which are then processed by a Luminance Adaptation Module (LAM) to dynamically adjust the brightness based on the input luminance distribution. Furthermore, a Reflect Augmentation Module (RAM) is presented to maximize illumination utilization and simultaneously enhance action recognition via two interactive paths. Additionally, we build Dark-101, a large-scale dataset comprising 18,310 dark videos across 101 action categories, significantly surpassing existing datasets (e.g., ARID1.5 and Dark-48) in scale and diversity. Extensive experiments demonstrate that the proposed OwlSight achieves state-of-the-art performance across four low-light action recognition benchmarks. Notably, it outperforms previous best approaches by 5.36% on ARID1.5 and 1.72% on Dark-101, highlighting its effectiveness in challenging dark environments.
title OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.23266