37 citations · 39 across the 10 of their papers we have counts for
12 papers · 1 filter
MoRGS: Efficient Per-Gaussian Motion Reasoning for Streamable Dynamic 3D Scenes
Wonjoon Lee, Sungmin Woo, Donghyeong Kim +3
Online reconstruction of dynamic scenes aims to learn from streaming multi-view inputs under low-latency constraints. The fast training and real-time rendering capabilities of 3D G…
Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning
Minseok Kang, Minhyeok Lee, Minjung Kim +5
Weakly-supervised video scene graph generation (WS-VSGG) aims to parse video content into structured relational triplets without bounding box annotations and with only sparse tempo…
Cross Pseudo Labeling For Weakly Supervised Video Anomaly Detection
Dayeon Lee, Donghyeong Kim, Chaewon Park +2
Weakly supervised video anomaly detection aims to detect anomalies and identify abnormal categories with only video-level labels. We propose CPL-VAD, a dual-branch framework with c…
DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints
Sungmin Woo, Sangyoun Lee
Depth-from-Focus (DFF) enables precise depth estimation by analyzing focus cues across a stack of images captured at varying focal lengths. While recent learning-based approaches h…
Improving Unsupervised Video Object Segmentation via Fake Flow Generation
Suhwan Cho, Minhyeok Lee, Jungho Lee +4
Unsupervised video object segmentation (VOS), also known as video salient object detection, aims to detect the most prominent object in a video at the pixel level. Recently, two-st…
ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
Sungmin Woo, Wonjoon Lee, Woo Jin Kim +2
Self-supervised multi-frame monocular depth estimation relies on the geometric consistency between successive frames under the assumption of a static scene. However, the presence o…
FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction
Sungmin Woo, Minjung Kim, Donghyeong Kim +2
Multi-agent motion prediction is a crucial concern in autonomous driving, yet it remains a challenge owing to the ambiguous intentions of dynamic agents and their intricate interac…
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
Jungho Lee, Minhyeok Lee, Suhwan Cho +3
Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body's skeletal sructure. Many recent methods have achieved re…
MKConv: Multidimensional Feature Representation for Point Cloud Analysis
Sungmin Woo, Dogyoon Lee, Sangwon Hwang +2
Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains elusive owing to their irregular data structure. Existing methods mainly f…
Regularization Strategy for Point Cloud via Rigidly Mixed Sample
Dogyoon Lee, Jaeha Lee, Junhyeop Lee +4
Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks. However, data augmentation is rar…
PMVOS: Pixel-Level Matching-Based Video Object Segmentation
Suhwan Cho, Heansung Lee, Sungmin Woo +2
Semi-supervised video object segmentation (VOS) aims to segment arbitrary target objects in video when the ground truth segmentation mask of the initial frame is provided. Due to t…
False Positive Removal for 3D Vehicle Detection with Penetrated Point Classifier
Sungmin Woo, Sangwon Hwang, Woojin Kim +3
Recently, researchers have been leveraging LiDAR point cloud for higher accuracy in 3D vehicle detection. Most state-of-the-art methods are deep learning based, but are easily affe…