EUVIMEDEUVIMED entdecken
Crossref

Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos

Shankhanil Mitra, Rajiv Soundararajan

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4251-4260

DOI: 10.1609/aaai.v38i5.28221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Shankhanil Mitra und 1 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Perceptual quality assessment of user generated content (UGC) videos is challenging due to the requirement of large scale human annotated videos for training. In this work, we address this challenge by first designing a self-supervised Spatio-Temporal Visual Quality Representation Learning (ST-VQRL) framework to generate robust quality aware features for videos. Then, we propose a dual-model based Semi Supervised Learning (SSL) method specifically designed for the Video Quality Assessment (SSL-VQA) task, through a novel knowledge transfer of quality predictions between the two models. Our SSL-VQA method uses the ST-VQRL backbone to produce robust performances across various VQA datasets including cross-database settings, despite being learned with limited human annotated videos. Our model improves the state-of-the-art performance when trained only with limited data by around 10%, and by around 15% when unlabelled data is also used in SSL. Source codes and checkpoints are available at https://github.com/Shankhanil006/SSL-VQA.

Zitieren

APA

Mitra, S., & Soundararajan, R. (2024). Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4251-4260. https://doi.org/10.1609/aaai.v38i5.28221

Vancouver

Mitra S, Soundararajan R. Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4251-4260. doi:10.1609/aaai.v38i5.28221

BibTeX
@article{Mitra2024,
  author = {Mitra, Shankhanil and Soundararajan, Rajiv},
  title = {Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {5},
  pages = {4251--4260},
  doi = {10.1609/aaai.v38i5.28221}
}
Kostenlos starten →