4 citations · 9 across the 6 of their papers we have counts for
6 papers
EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
Sangwon Kim, Dasom Ahn, Byoung Chul Ko +2
The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach…
Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
Hyeongjin Kim, Sangwon Kim, Dasom Ahn +2
Scene graph generation (SGG) is an important task in image understanding because it represents the relationships between objects in an image as a graph structure, making it possibl…
Semantic Scene Graph Generation Based on an Edge Dual Scene Graph and Message Passing Neural Network
Hyeongjin Kim, Sangwon Kim, Jong Taek Lee +1
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 stru…
Cross-Modal Learning with 3D Deformable Attention for Action Recognition
Sangwon Kim, Dasom Ahn, Byoung Chul Ko
An important challenge in vision-based action recognition is the embedding of spatiotemporal features with two or more heterogeneous modalities into a single feature. In this study…
STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition
Dasom Ahn, Sangwon Kim, Hyunsu Hong +1
In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature repr…
Interpretation and Simplification of Deep Forest
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. In deep RF, a large number of de…