3 citations · 8 across the 8 of their papers we have counts for
8 papers · 1 filter
Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object Detection
Yecheol Kim, Junho Lee, Changsoo Park +4
3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgr…
Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detection
Konyul Park, Yecheol Kim, Junho Koh +2
Developing high-performance, real-time architectures for LiDAR-based 3D object detectors is essential for the successful commercialization of autonomous vehicles. Pillar-based meth…
PillarGen: Enhancing Radar Point Cloud Density and Quality via Pillar-based Point Generation Network
Jisong Kim, Geonho Bang, Kwangjin Choi +4
In this paper, we present a novel point generation model, referred to as Pillar-based Point Generation Network (PillarGen), which facilitates the transformation of point clouds fro…
Unified Contrastive Fusion Transformer for Multimodal Human Action Recognition
Kyoung Ok Yang, Junho Koh, Jun Won Choi
Various types of sensors have been considered to develop human action recognition (HAR) models. Robust HAR performance can be achieved by fusing multimodal data acquired by differe…
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer
Youngseok Kim, Sanmin Kim, Jun Won Choi +1
Camera and radar sensors have significant advantages in cost, reliability, and maintenance compared to LiDAR. Existing fusion methods often fuse the outputs of single modalities at…
Learning from Data with Noisy Labels Using Temporal Self-Ensemble
Jun Ho Lee, Jae Soon Baik, Tae Hwan Hwang +1
There are inevitably many mislabeled data in real-world datasets. Because deep neural networks (DNNs) have an enormous capacity to memorize noisy labels, a robust training scheme i…