Related papers: Graph Query Networks for Object Detection with Aut…

Depth estimation plays a pivotal role in autonomous driving, facilitating a comprehensive understanding of the vehicle's 3D surroundings. Radar, with its robustness to adverse weather conditions and capability to measure distances, has…

Molecular property prediction is of crucial importance in many disciplines such as drug discovery, molecular biology, or material and process design. The frequently employed quantitative structure-property/activity relationships…

The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns. Conventional point-based models exploit local patterns through a symmetric function (e.g. max pooling)…

To enable intelligent automated driving systems, a promising strategy is to understand how human drives and interacts with road users in complicated driving situations. In this paper, we propose a 3D-aware egocentric spatial-temporal…

Accurate and robust object detection is critical for autonomous driving. Image-based detectors face difficulties caused by low visibility in adverse weather conditions. Thus, radar-camera fusion is of particular interest but presents…

Edge vision systems combining sensing and embedded processing promise low-latency, decentralized, and energy-efficient solutions that forgo reliance on the cloud. As opposed to conventional frame-based vision sensors, event-based cameras…

A detailed environment perception is a crucial component of automated vehicles. However, to deal with the amount of perceived information, we also require segmentation strategies. Based on a grid map environment representation, well-suited…

A graph neural network (GNN) for image understanding based on multiple cues is proposed in this paper. Compared to traditional feature and decision fusion approaches that neglect the fact that features can interact and exchange information,…

Robust 3D object detection is critical for safe autonomous driving. Camera and radar sensors are synergistic as they capture complementary information and work well under different environmental conditions. Fusing camera and radar data is…

Region proposal algorithms play an important role in most state-of-the-art two-stage object detection networks by hypothesizing object locations in the image. Nonetheless, region proposal algorithms are known to be the bottleneck in most…

Graph Neural Networks (GNNs) are a family of graph networks inspired by mechanisms existing between nodes on a graph. In recent years there has been an increased interest in GNN and their derivatives, i.e., Graph Attention Networks (GAT),…

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…

The visual cues from multiple support regions of different sizes and resolutions are complementary in classifying a candidate box in object detection. Effective integration of local and contextual visual cues from these regions has become a…

Graphs are essential for modeling complex relationships and capturing structured interactions in data. Graph Neural Networks (GNNs) are particularly effective when such relational structure is explicitly available, but many real-world…

This paper presents a contextualized graph attention network that combines edge features and multiple sub-graphs for improving relation extraction. A novel method is proposed to use multiple sub-graphs to learn rich node representations in…

This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The…

Endowing robots with human-like physical reasoning abilities remains challenging. We argue that existing methods often disregard spatio-temporal relations and by using Graph Neural Networks (GNNs) that incorporate a relational inductive…

This paper considers object detection and 3D estimation using an FMCW radar. The state-of-the-art deep learning framework is employed instead of using traditional signal processing. In preparing the radar training data, the ground truth of…

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…

3D meshes are fundamental data representations for capturing complex geometric shapes in computer vision and graphics applications. While Convolutional Neural Networks (CNNs) have excelled in structured data like images, extending them to…