YOLO-Act: Unified Spatiotemporal Detection of Human Actions Across Multi-Frame Sequences
Sensors · 10.05.2025 · 25 (10) · 3013
DOI: 10.3390/s25103013 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.05.2025. Verfasst von Nada Alzahrani und 2 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh 11451, Saudi Arabia. Hauptthemen laut MEDLINE: Video Recording, Pattern Recognition, Automated, Human Activities. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Automated action recognition has become essential in the surveillance, healthcare, and multimedia retrieval industries owing to the rapid proliferation of video data. This paper introduces YOLO-Act, a novel spatiotemporal action detection model that enhances the object detection capabilities of YOLOv8 to efficiently manage complex action dynamics within video sequences. YOLO-Act achieves precise and efficient action recognition by integrating keyframe extraction, action tracking, and class fusion. The model depicts essential temporal dynamics without the computational overhead of continuous frame processing by leveraging the adaptive selection of three keyframes representing the beginning, middle, and end of the actions. Compared with state-of-the-art approaches such as the Lagrangian Action Recognition Transformer (LART), YOLO-Act exhibits superior performance with a mean average precision (mAP) of 73.28 in experiments conducted on the AVA dataset, resulting in a gain of +28.18 mAP. Furthermore, YOLO-Act achieves this higher accuracy with significantly lower FLOPs, demonstrating its efficiency in computational resource utilization. The results highlight the advantages of incorporating precise tracking, effective spatial detection, and temporal consistency to address the challenges associated with video-based action detection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh 11451, Saudi Arabia.
- Computer Science Department, College of Computer Engineering and Science, Prince Sattam Bin Abdulaziz University, Al-Kharj 16278, Saudi Arabia.
ORCID-Profile: Ouiem Bchir
Zitieren
APA
Alzahrani, N., Bchir, O., & Ismail, M. M. B. (2025). YOLO-Act: Unified Spatiotemporal Detection of Human Actions Across Multi-Frame Sequences. Sensors, 25(10), 3013. https://doi.org/10.3390/s25103013
Vancouver
Alzahrani N, Bchir O, Ismail MMB. YOLO-Act: Unified Spatiotemporal Detection of Human Actions Across Multi-Frame Sequences. Sensors. 2025;25(10):3013. doi:10.3390/s25103013
BibTeX
@article{Alzahrani2025,
author = {Alzahrani, Nada and Bchir, Ouiem and Ismail, Mohamed Maher Ben},
title = {YOLO-Act: Unified Spatiotemporal Detection of Human Actions Across Multi-Frame Sequences},
journal = {Sensors},
year = {2025},
volume = {25},
number = {10},
pages = {3013},
doi = {10.3390/s25103013}
}
EUVIMED