Related papers: HEIR: Learning Graph-Based Motion Hierarchies
Compositional structures between parts and objects are inherent in natural scenes. Modeling such compositional hierarchies via unsupervised learning can bring various benefits such as interpretability and transferability, which are…
Modeling complex spatiotemporal dynamics, particularly in far-from-equilibrium systems, remains a grand challenge in science. The governing partial differential equations (PDEs) for these systems are often intractable to derive from first…
Human emotion is expressed, perceived and captured using a variety of dynamic data modalities, such as speech (verbal), videos (facial expressions) and motion sensors (body gestures). We propose a generalized approach to emotion recognition…
We study the problem of graph structure identification, i.e., of recovering the graph of dependencies among time series. We model these time series data as components of the state of linear stochastic networked dynamical systems. We assume…
Current approaches to video analysis of human motion focus on raw pixels or keypoints as the basic units of reasoning. We posit that adding higher-level motion primitives, which can capture natural coarser units of motion such as backswing…
We present a novel hierarchical model for human activity recognition. In contrast to approaches that successively recognize actions and activities, our approach jointly models actions and activities in a unified framework, and their labels…
Graph representation learning has made major strides over the past decade. However, in many relational domains, the input data are not suited for simple graph representations as the relationships between entities go beyond pairwise…
With the fast development of AI-related techniques, the applications of trajectory prediction are no longer limited to easier scenes and trajectories. More and more trajectories with different forms, such as coordinates, bounding boxes, and…
Scene graph aims to faithfully reveal humans' perception of image content. When humans analyze a scene, they usually prefer to describe image gist first, namely major objects and key relations in a scene graph. This humans' inherent…
Analyzing the interactions between humans and objects from a video includes identification of the relationships between humans and the objects present in the video. It can be thought of as a specialized version of Visual Relationship…
Motion prediction for automated vehicles in complex environments is a difficult task that is to be mastered when automated vehicles are to be used in arbitrary situations. Many factors influence the future motion of traffic participants…
Hypergraphs, as a generalization of traditional graphs, naturally capture high-order relationships. In recent years, hypergraph neural networks (HNNs) have been widely used to capture complex high-order relationships. However, most existing…
A graph theoretic approach is proposed for object shape representation in a hierarchical compositional architecture called Compositional Hierarchy of Parts (CHOP). In the proposed approach, vocabulary learning is performed using a hybrid…
Graph is a fundamental mathematical structure in characterizing relations between different objects and has been widely used on various learning tasks. Most methods implicitly assume a given graph to be accurate and complete. However, real…
This paper presents a novel framework to recover detailed human body shapes from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, and viewpoints. Prior methods typically attempt to…
Traditional model-based diagnosis relies on constructing explicit system models, a process that can be laborious and expertise-demanding. In this paper, we propose a novel framework that combines concepts of model-based diagnosis with deep…
Machine learning methods have a long history of applications in high energy physics (HEP). Recently, there is a growing interest in exploiting these methods to reconstruct particle signatures from raw detector data. In order to benefit from…
In this paper, we report a hierarchical deep learning model for classification of complex human activities using motion sensors. In contrast to traditional Human Activity Recognition (HAR) models used for event-based activity recognition,…
We present Hierarchical Motion Representation (HiMoR), a novel deformation representation for 3D Gaussian primitives capable of achieving high-quality monocular dynamic 3D reconstruction. The insight behind HiMoR is that motions in everyday…
Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects via inferring triplets of < human, verb, object >. However, recent HOI detection methods mostly rely on additional annotations (e.g.,…