4 papers
Appearance-Invariant Detection of Suggestive Motion via Laban Movement Descriptors
Jaehoon Ahn, Jeonghan Kong, Moon-Ryul Jung
Content moderation in online multiplayer 3D virtual environments is increasingly automated, yet detection has focused on images, video, and audio, leaving suggestive motion a blind…
The SMC Blind Spot: A Failure Mode Analysis of State-of-the-Art Beat Tracking
Jaehoon Ahn, Tae Gum Hwang, Moon-Ryul Jung
Over the past two decades, the task of musical beat tracking has transitioned from heuristic onset detection algorithms to highly capable deep neural networks (DNN). Although DNN-b…
AlignBeat: A Latent Variable Model for Multi-Class Beat Tracking from Partially Labeled Data
Jaehoon Ahn, Moon-Ryul Jung, Tae Gum Hwang
Recent neural beat trackers predict beats and downbeats with two independent frame-wise binary classification heads, a convention adopted because a single multi-class head cannot f…
ConTEXTure: Consistent Multiview Images to Texture
Jaehoon Ahn, Sumin Cho, Harim Jung +3
We introduce ConTEXTure, a generative network designed to create a texture map/atlas for a given 3D mesh using images from multiple viewpoints. The process begins with generating a…