no code implementations • 2 Nov 2023 • Hyeongjin Kim, Sangwon Kim, Jong Taek Lee, Byoung Chul Ko
Along with generative AI, interest in scene graph generation (SGG), which comprehensively captures the relationships and interactions between objects in an image and creates a structured graph-based representation, has significantly increased in recent years.
no code implementations • ICCV 2023 • Sangwon Kim, Dasom Ahn, Byoung Chul Ko
The 3D deformable transformer consists of three attention modules: 3D deformability, local joint stride, and temporal stride attention.
Ranked #8 on Action Recognition on NTU RGB+D
no code implementations • WACV 2023 • Dasom Ahn, Sangwon Kim, Hyunsu Hong, Byoung Chul Ko
In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required.
Ranked #1 on Action Recognition on Penn Action
no code implementations • 14 Jan 2020 • Sangwon Kim, Mira Jeong, Byoung Chul Ko
This paper proposes a new method for interpreting and simplifying a black box model of a deep random forest (RF) using a proposed rule elimination.