Learned disentangled latent representations for scalable image coding for humans and machines

E Özyılkan, M Ulhaq, H Choi… - 2023 Data Compression …, 2023 - ieeexplore.ieee.org
As an increasing amount of image and video content will be analyzed by machines, there is
demand for a new codec paradigm that is capable of compressing visual input primarily for …
被引用次数：7 相关文章
[PDF] researchgate.net

[PDF][PDF] Learned Disentangled Latent Representations for Scalable Image Coding for Humans and Machines

E Ozyılkan, M Ulhaq, H Choi… - arXiv preprint arXiv …, 2023 - researchgate.net
As an increasing amount of image and video content will be analyzed by machines, there is
demand for a new codec paradigm that is capable of compressing visual input primarily for …

Learned Disentangled Latent Representations for Scalable Image Coding for Humans and Machines

E Ozyilkan, M Ulhaq, H Choi, F Racape - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
As an increasing amount of image and video content will be analyzed by machines, there is
demand for a new codec paradigm that is capable of compressing visual input primarily for …

Learned Disentangled Latent Representations for Scalable Image Coding for Humans and Machines

E Ozyilkan, M Ulhaq, H Choi, F Racapé - ezgimez.github.io
Learned Disentangled Latent Representations for Scalable Image Coding for Humans and
Machines Page 1 Ezgi Ozyilkan , Mateen Ulhaq , Hyomin Choi , Fabien Racapé Learned …

Learned Disentangled Latent Representations for Scalable Image Coding for Humans and Machines

E Ozyilkan, M Ulhaq, H Choi, F Racapé - sfu.ca
● Various architecture configurations for the tuple.● Train on Vimeo-90K dataset with
“distortion” computed using mean-squared error (MSE).● Evaluate object detection on …

Learned Disentangled Latent Representations for Scalable Image Coding for Humans and Machines

E Ozyilkan, M Ulhaq, H Choi, F Racape - arXiv preprint arXiv:2301.04183, 2023 - arxiv.org
As an increasing amount of image and video content will be analyzed by machines, there is
demand for a new codec paradigm that is capable of compressing visual input primarily for …