A lightweight video violence detection method based on multi-scale temporal pyramid networks
Fundamental Scientific Reports in Multidisciplinary Areas · 28.06.2026 · 2 (01) · 277-287
DOI: 10.66238/fsrma94 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fundamental Scientific Reports in Multidisciplinary Areas, online erschienen am 28.06.2026. Verfasst von Liu Pan und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Video violence detection plays a critical role in public safety surveillance and online content moderation. This paper proposes a Multi-Scale Temporal Pyramid Network that employs three parallel temporal pyramid branches with strides of 1, 2, and 4 to explicitly model fine-grained, intermediate, and coarse temporal dynamics. The model adopts a lightweight MobileNetV3-Large backbone for spatial feature extraction, followed by spatial-to-temporal projection to generate compact token sequences. Three temporal depth-wise separable residual blocks independently process each temporal scale, while a temporal scale attention fusion module adaptively integrates multi-scale representations. Learnable temporal attention pooling then compresses variable-length sequences into a compact video-level descriptor for classification. Systematic experiments on three public benchmark datasets: RWF-2000, Hockey Fights, and Real Life Violence Situations, demonstrate that MPPN achieves competitive detection performance, validating the effectiveness of explicit multi-scale temporal modeling for practical video violence detection.
Zitieren
APA
Pan, L., Guangbin, L., & Nyamasvisva, T. E. (2026). A lightweight video violence detection method based on multi-scale temporal pyramid networks. Fundamental Scientific Reports in Multidisciplinary Areas, 2(01), 277-287. https://doi.org/10.66238/fsrma94
Vancouver
Pan L, Guangbin L, Nyamasvisva TE. A lightweight video violence detection method based on multi-scale temporal pyramid networks. Fundamental Scientific Reports in Multidisciplinary Areas. 2026;2(01):277-287. doi:10.66238/fsrma94
BibTeX
@article{Pan2026,
author = {Pan, Liu and Guangbin, Liu and Nyamasvisva, Tadiwa Elisha},
title = {A lightweight video violence detection method based on multi-scale temporal pyramid networks},
journal = {Fundamental Scientific Reports in Multidisciplinary Areas},
year = {2026},
volume = {2},
number = {01},
pages = {277--287},
doi = {10.66238/fsrma94}
}
EUVIMED