Related papers: Pose-Graph Attentional Graph Neural Network for Li…

Deep learning offers a promising avenue for automating many recognition tasks in fields such as medicine and forensics. However, the black-box nature of these models hinders their adoption in high-stakes applications where trust and…

Bottom-up approaches for image-based multi-person pose estimation consist of two stages: (1) keypoint detection and (2) grouping of the detected keypoints to form person instances. Current grouping approaches rely on learned embedding from…

Simultaneous localization and mapping (SLAM) is a critical capability in autonomous navigation, but in order to scale SLAM to the setting of "lifelong" SLAM, particularly under memory or computation constraints, a robot must be able to…

Graph Neural Networks (GNNs) have shown remarkable success in graph representation learning. Unfortunately, current weight assignment schemes in standard GNNs, such as the calculation based on node degrees or pair-wise representations, can…

One-shot LiDAR localization refers to the ability to estimate the robot pose from one single point cloud, which yields significant advantages in initialization and relocalization processes. In the point cloud domain, the topic has been…

Accurate and timely traffic flow forecasting is crucial for intelligent transportation systems. This paper presents a novel deep learning model, the Spatial-Temporal Unified Graph Attention Network (STGAtt). By leveraging a unified graph…

Land-use monitoring is fundamental for spatial planning, particularly in view of compound impacts of growing global populations and climate change. Despite existing applications of deep learning in land use monitoring, standard…

Variants of Graph Neural Networks (GNNs) for representation learning have been proposed recently and achieved fruitful results in various fields. Among them, Graph Attention Network (GAT) first employs a self-attention strategy to learn…

The objective of pose SLAM or pose-graph optimization (PGO) is to estimate the trajectory of a robot given odometric and loop closing constraints. State-of-the-art iterative approaches typically involve the linearization of a non-convex…

In recent years, a plethora of diverse methods have been proposed for 3D pose estimation. Among these, self-attention mechanisms and graph convolutions have both been proven to be effective and practical methods. Recognizing the strengths…

Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by applying a non-uniform score (attending) to the features. Recent…

Previous works for LiDAR-based 3D object detection mainly focus on the single-frame paradigm. In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i.e., the point cloud videos. We empirically…

Knowledge graphs offer a structured representation of real-world entities and their relationships, enabling a wide range of applications from information retrieval to automated reasoning. In this paper, we conduct a systematic comparison…

Recent works on SLAM extend their pose graphs with higher-level semantic concepts like Rooms exploiting relationships between them, to provide, not only a richer representation of the situation/environment but also to improve the accuracy…

Technique of emotion recognition enables computers to classify human affective states into discrete categories. However, the emotion may fluctuate instead of maintaining a stable state even within a short time interval. There is also a…

Pose estimation and human action recognition (HAR) are pivotal technologies spanning various domains. While the image-based pose estimation and HAR are widely admired for their superior performance, they lack in privacy protection and…

Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames. In this paper, we propose an end-to-end online 3D video object detector…

Graph convolutional networks (GCN) is widely used to handle irregular data since it updates node features by using the structure information of graph. With the help of iterated GCN, high-order information can be obtained to further enhance…

Accurate identification of protein binding sites is crucial for understanding biomolecular interaction mechanisms and for the rational design of drug targets. Traditional predictive methods often struggle to balance prediction accuracy with…

Prediction with high accuracy is essential for various applications such as autonomous driving. Existing prediction models are easily prone to errors in real-world settings where observations (e.g. human poses and locations) are often…