Adversarial complementary learning for just noticeable difference estimation

Recently, many unsupervised learning-based models have emerged for Just Noticeable Difference (JND) estimation, demonstrating remarkable improvements in accuracy. However, these models suffer from a significant drawback is that their heavy reliance on handcrafted priors for guidance. This restricts...

Täydet tiedot

Bibliografiset tiedot
Päätekijät: Yu, Dong, Jin, Jian, Meng, Lili, Chen, Zhipeng, Zhang, Huaxiang
Muut tekijät: School of Computer Science and Engineering
Aineistotyyppi: Journal Article
Kieli:English
Julkaistu: 2024
Aiheet:
Linkit:https://hdl.handle.net/10356/178981