Purdue University Graduate School

Hyung-gun Chi


  • InfoGCN: Representation Learning for Human Skeleton-based Action Recognition
  • A Large-Scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks
  • Object Synthesis by Learning Part Geometry with Surface and Volumetric Representations
  • An evaluation methodology for 3D deep neural networks using visualization in 3D data classification
  • Latent transformations neural network for object view synthesis
  • Egocentric view hand action recognition by leveraging hand surface and hand grasp type
  • First-Person View Hand Segmentation of Multi-Modal Hand Activity Video Dataset
  • Simplification of 3D CAD Model in Voxel Form for Mechanical Parts Using Generative Adversarial Networks
  • Pose Relation Transformer Refine Occlusions for Human Pose Estimation
  • AdamsFormer for Spatial Action Localization in the Future
  • InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition
  • Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction
  • Interacting Objects: A Dataset of Object-Object Interactions for Richer Dynamic Scene Representations
  • Deep Learning‐Assisted Design of Bilayer Nanowire Gratings for High‐Performance MWIR Polarizers

Hyung-gun Chi's public data