김현우 교수

Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. In this paper, we propose Gr

Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels. Most existing methods have indirectly addressed this task by detecting human and object instances and individually inferring every pair of the detected instances. In this paper, we present a novel framework, referred by HOTR, which dir

Multi-label classification is the task of predicting a set of labels for a given input instance. Classifier chains are a state-of-the-art method for tackling such problems, which essentially converts this problem into a sequential prediction problem, where the labels are first ordered in an arbitrary fashion, and the task is to predict a sequence of binary values for these labels. In this paper, we replace classifier chains with recurrent neural networks, a sequence-to-sequence prediction algori

Finding 10 balloons across the U.S. illustrates how the Internet has changed the way we solve highly distributed problems.

Graph Neural Networks (GNNs) have been widely applied to various fields due to their powerful representations of graph-structured data. Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. To address these limitations, we propose Graph Transformer N

Linear regression is a parametric model which is ubiquitous in scientific analysis. The classical setup where the observations and responses, i.e., (x <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> , y <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> ) pairs, are Euclidean is well studied. The setting where yi is manifold valued is a topic of much interest, motivated by applications in s

Statistical machine learning models that operate on manifold-valued data are being extensively studied in vision, motivated by applications in activity recognition, feature tracking and medical imaging. While non-parametric methods have been relatively well studied in the literature, efficient formulations for parametric models (which may offer benefits in small sample size regimes) have only emerged recently. So far, manifold-valued regression models (such as geodesic regression) are restricted

최근 사회는 아날로그 시대를 거쳐 디지털, 스마트 시대로 접어들었고, 모든 분야의 기술은 끊임없는 변화와 매우 빠른 발전을 하고 있다. 이러한 경쟁사회에서 지식재산, 특히 특허분석을 통한 R&D 전략 수립은 기술경쟁력 향상에 많은 도움이 될 수 있다. 특허문서는 명칭, 요약, 상세한 설명, 청구항, 기술분류정보 등 서지정보, 기술문헌과 권리문헌으로 이루어져 있어 대중은 이를 통해 해당 기술에 대한 많은 정보를 수집할 수 있다. 특허문서의 특징을 정량적으로 활용하고 기술 분석을 실시함으로써 분석대상 기술의 동향을 파악하는 것뿐만 아니라, 해당 기술 분야의 핵심기술과 특허를 탐색하여 경쟁력을 향상시키는 것이 가능하다. 본 논문은 특허 데이터에 대한 정량적인 방법을 기반으로 한 핵심 기술과 핵심 특허의 도출 방법을 제안한다. 특허문서에 포함되어 있는 기술분류정보, IPC 코드에 통계분석과 사회네트워크분석을 적용하여 연구개발이 활발한 분야와 중심성이 높은 기술을 탐색한다. 그 후 특허의 인

, which we call Dirichlet process mixtures of multivariate general linear models (DP-MGLM) on Riemannian manifolds. Finally, we present proof of concept experiments to validate our model.

Many self-supervised representation learning methods have achieved high performance in image classification tasks. However, these methods have limited performance on localization tasks such as object detection or semantic segmentation. Most self-supervised representation learning methods are optimized with only one global representation, which does not pay much attention to the spatial information in an image. We propose a simple and effective method that uses the positional relationships betwee

Probability density functions (PDFs) are fundamental objects in mathematics with numerous applications in computer vision, machine learning and medical imaging. The feasibility of basic operations such as computing the distance between two PDFs and estimating a mean of a set of PDFs is a direct function of the representation we choose to work with. In this paper, we study the Gaussian mixture model (GMM) representation of the PDFs motivated by its numerous attractive features. (1) GMMs are argua