Watch video in high-quality
even when network becomes congested.

NAS is a new Internet video delivery framework that integrates deep neural network based quality enhancement.
In current video delivery (adaptive streaming), video quality directly degrades when newtork becomes congested.

NAS outperforms the current state of the art, enhancing the average QoE by 43.08% using the same bandwidth budget or saving 17.13% of bandwidth while providing the same user QoE.

Demo Video

All video clips used in the demo videos are from popular channels on Youtube.
No intent to infringe on copyright. All rights belong to their respective owners.

How It Works?

Highlight

Paper


Hyunho Yeo, Youngmok Jung, Jaehong Kim, Jinwoo Shin, and Dongsu Han. “Neural Adaptive Content-aware Internet Video Delivery” In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’18), pp. 645–661. USENIX Association, 2018.

Paper PDF
Usenix Webpage

Slide




NAS was presented at 13th USENIX Symposium on Operating Systems Design and Implementation. The talk was given on October 10, 2018.

Slide PDF
Slide PPT

Authors

Hyunho Yeo

Ph.D Candidate

KAIST

Youngmok Jung

Master's

KAIST

Jaehong Kim

Master's

KAIST

Jinwoo Shin

Associate Professor

KAIST

Dongsu Han

Associate Professor

KAIST

Press