no code implementations • 15 Jan 2019 • Sang-ho Lee, Simyung Chang, Nojun Kwak
There are methods to reduce the cost by compressing networks or varying its computational path dynamically according to the input image.
no code implementations • CVPR 2018 • Sang-ho Lee, Jinyoung Sung, Youngjae Yu, Gunhee Kim
Second, we evaluate the temporal summarization with a newly collected 360° video dataset.
no code implementations • CVPR 2018 • Jaeyoung Yoo, Sang-ho Lee, Nojun Kwak
In this paper, we propose a method to solve the image restoration problem, which tries to restore the details of a corrupted image, especially due to the loss caused by JPEG compression.
no code implementations • CVPR 2018 • Sang-ho Lee, Jinyoung Sung, Youngjae Yu, Gunhee Kim
Second, we evaluate the temporal summarization with a newly collected 360{\deg} video dataset.
no code implementations • 31 Jan 2018 • Youngjae Yu, Sang-ho Lee, Joonil Na, Jaeyun Kang, Gunhee Kim
We address the problem of highlight detection from a 360 degree video by summarizing it both spatially and temporally.
1 code implementation • ICCV 2017 • Seil Na, Sang-ho Lee, Ji-Sung Kim, Gunhee Kim
We propose a novel memory network model named Read-Write Memory Network (RWMN) to perform question and answering tasks for large-scale, multimodal movie story understanding.
Ranked #3 on Video Story QA on MovieQA
1 code implementation • 24 Jun 2017 • Seil Na, Youngjae Yu, Sang-ho Lee, Ji-Sung Kim, Gunhee Kim
YouTube-8M is the largest video dataset for multi-label video classification.