no code implementations • 7 Nov 2020 • Seungyun Jeong, Keemin Sohn
An autoencoder was used to reduce the dimensions of input images, and reduced feature vectors were used to implement the online change-point algorithm.
no code implementations • 5 Oct 2020 • Byeonghyeop Yu, Johyun Shin, Gyeongjun Kim, Seungbin Roh, Keemin Sohn
As a result, the performance of the two models with bounding ellipses exceeded that of the reference models with bounding boxes.
no code implementations • 5 Aug 2020 • Gyeongjun Kim, Keemin Sohn
First, the action space exponentially explodes as the number of intersections to be jointly controlled increases.