EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Entropy-Gated Prediction Agreement for Two-View Video Action Recognition

Young-Jin Park, Hui-Sup Cho

Electronics · 2026-06-30 · 15 (13) · 2844

DOI: 10.3390/electronics15132844 ↗

At a glance

Journal article in Electronics, published online on 2026-06-30. Written by Young-Jin Park and 1 co-authors. 36 references. The full text is freely available (open access, CC BY 4.0). Funded by: DGIST R&D Program of the Ministry of Science and ICT of Korea.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Human action recognition (HAR) often struggles to capture important temporal cues distributed across an entire video when relying solely on a single sampled clip. To overcome this limitation, this study proposes a framework that constructs two temporal views from the same video and explicitly learns the prediction consistency between them. Specifically, the prediction-level agreement (AG) loss was introduced to align the class probability distributions of the two views. In addition, conditional gating was applied to adaptively control the contribution of AG loss according to the sample-wise prediction confidence, thereby reducing unstable alignment in temporally ambiguous or information-insufficient segments. The proposed framework was evaluated using both convolutional neural network (CNN)- and Transformer-based backbones on three representative action-recognition benchmark datasets, and it generally improved the performance over the single-view baseline across backbone–dataset combinations. Further empirical analyses, including training behavior, motion magnitude, temporal prediction stability, and qualitative case studies, were conducted to examine the effectiveness and behavior of the proposed two-view framework from multiple perspectives.

Funding

  • DGIST R&D Program of the Ministry of Science and ICT of Korea

Cite

APA

Park, Y., & Cho, H. (2026). Entropy-Gated Prediction Agreement for Two-View Video Action Recognition. Electronics, 15(13), 2844. https://doi.org/10.3390/electronics15132844

Vancouver

Park Y, Cho H. Entropy-Gated Prediction Agreement for Two-View Video Action Recognition. Electronics. 2026;15(13):2844. doi:10.3390/electronics15132844

BibTeX
@article{Park2026,
  author = {Park, Young-Jin and Cho, Hui-Sup},
  title = {Entropy-Gated Prediction Agreement for Two-View Video Action Recognition},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {13},
  pages = {2844},
  doi = {10.3390/electronics15132844}
}
Start for free →