9 papers
Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis
Hangil Park, Seungheon Kim, Tae-Kyun Kim
Training-free language-based video anomaly detection (VAD) uses frozen vision--language models (VLMs) and large language models (LLMs) to localize abnormal events without task-spec…
Learning Temporal Evidence Selection for Video Anomaly Understanding
Hangil Park, Seungheon Kim, Tae-Kyun Kim
Video anomaly understanding (VAU) aims to generate language-level interpretations of anomalous events in long videos, requiring visual evidence that supports explanation beyond ano…
Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation
Seunghyun Lee, Tae-Kyun Kim
Latest diffusion models have shown promising results in category-level 6D object pose estimation by modeling the conditional pose distribution with depth image input. The existing…
Generalist Multi-Class Anomaly Detection via Distillation to Two Heterogeneous Student Networks
Hangil Park, Yongmin Seo, Tae-Kyun Kim
Anomaly detection (AD) plays an important role in various real-world applications. Recent advancements in AD, however, are often biased towards industrial inspection, struggle to g…
SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit 3D Meshes
Minje Kim, Tae-Kyun Kim
Reconstructing detailed hand avatars plays a crucial role in various applications. While prior works have focused on capturing high-fidelity hand geometry, they heavily rely on hig…
Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detection
Taehun Kong, Tae-Kyun Kim
Semi-supervised 3D object detection (SS3DOD) aims to reduce costly 3D annotations utilizing unlabeled data. Recent studies adopt pseudo-label-based teacher-student frameworks and d…
MGHanD: Multi-modal Guidance for authentic Hand Diffusion
Taehyeon Eum, Jieun Choi, Tae-Kyun Kim
Diffusion-based methods have achieved significant successes in T2I generation, providing realistic images from text prompts. Despite their capabilities, these models face persisten…
BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction
Ruochen Li, Stamos Katsigiannis, Tae-Kyun Kim +1
Trajectory prediction allows better decision-making in applications of autonomous vehicles or surveillance by predicting the short-term future movement of traffic agents. It is cla…
Semi-Supervised 3D Object Detection with Channel Augmentation using Transformation Equivariance
Minju Kang, Taehun Kong, Tae-Kyun Kim
Accurate 3D object detection is crucial for autonomous vehicles and robots to navigate and interact with the environment safely and effectively. Meanwhile, the performance of 3D de…