Action-Region Mixing: A Video Augmentation Approach for Reducing Scene Bias in Action Recognition
Applied Sciences · 04.11.2026 · 16 (21) · 10920
DOI: 10.3390/app162110920 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 04.11.2026. Verfasst von Aslı Çelik und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific and Technological Research Council of Türkiye.
Abstract (Originalsprache)
Video action recognition models can rely heavily on recurring scene context rather than action-relevant cues, limiting their generalization to background changes. foreground–background mixing has therefore emerged as a useful augmentation strategy for reducing such scene dependence. However, existing semantic mixing approaches typically rely on off-the-shelf object detectors and associated preprocessing and postprocessing pipelines to localize action-related regions, while bounding-box-based representations may introduce unrelated background content into the mixed samples. To address these limitations, we propose ActionRegionMix, a prompt-guided, action-aware video augmentation framework that leverages a mask-generating Multimodal Large Language Model (MLLM) to extract action-related regions at the pixel level in an open-vocabulary manner. The extracted action regions are transferred across videos and composited with backgrounds from other training samples, introducing contextual variation while preserving action-relevant content. Experiments on UCF101 and HMDB51 show that ActionRegionMix consistently improves recognition performance over the no-augmentation baseline and the compared bounding-box-based semantic augmentation methods. These results demonstrate the effectiveness of pixel-level action-region mixing as a video augmentation strategy, offering a promising approach to enhance background diversity and mitigate reliance on scene-specific cues.
Förderung
- Scientific and Technological Research Council of Türkiye
Zitieren
APA
Çelik, A., Yıldırım, T., & Urhan, O. (2026). Action-Region Mixing: A Video Augmentation Approach for Reducing Scene Bias in Action Recognition. Applied Sciences, 16(21), 10920. https://doi.org/10.3390/app162110920
Vancouver
Çelik A, Yıldırım T, Urhan O. Action-Region Mixing: A Video Augmentation Approach for Reducing Scene Bias in Action Recognition. Applied Sciences. 2026;16(21):10920. doi:10.3390/app162110920
BibTeX
@article{elik2026,
author = {Çelik, Aslı and Yıldırım, Türkay and Urhan, Oğuzhan},
title = {Action-Region Mixing: A Video Augmentation Approach for Reducing Scene Bias in Action Recognition},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {21},
pages = {10920},
doi = {10.3390/app162110920}
}
EUVIMED