Related papers: GCNv2: Efficient Correspondence Prediction for Rea…

Recent advances in deep convolutional neural networks (CNNs) have motivated researchers to adapt CNNs to directly model points in 3D point clouds. Modeling local structure has been proven to be important for the success of convolutional…

Zero-shot action recognition can recognize samples of unseen classes that are unavailable in training by exploring common latent semantic representation in samples. However, most methods neglected the connotative relation and extensional…

By leveraging recent progress of stochastic gradient descent methods, several works have shown that graphs could be efficiently laid out through the optimization of a tailored objective function. In the meantime, Deep Learning (DL)…

Vision-based depth reconstruction is a challenging problem extensively studied in computer vision but still lacking universal solution. Reconstructing depth from single image is particularly valuable to mobile robotics as it can be embedded…

Graph convolutional neural networks (GCNs) generalize tradition convolutional neural networks (CNNs) from low-dimensional regular graphs (e.g., image) to high dimensional irregular graphs (e.g., text documents on word embeddings). Due to…

This paper presents a collaborative implicit neural simultaneous localization and mapping (SLAM) system with RGB-D image sequences, which consists of complete front-end and back-end modules including odometry, loop detection, sub-map…

The training of deep and/or convolutional neural networks (DNNs/CNNs) is traditionally done on servers with powerful CPUs and GPUs. Recent efforts have emerged to localize machine learning tasks fully on the edge. This brings advantages in…

Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to…

This study evaluates the use of Quantum Convolutional Neural Networks (QCNNs) for identifying signals resembling Gamma-Ray Bursts (GRBs) within simulated astrophysical datasets in the form of light curves. The task addressed here focuses on…

We propose an online object-level SLAM system which builds a persistent and accurate 3D graph map of arbitrary reconstructed objects. As an RGB-D camera browses a cluttered indoor scene, Mask-RCNN instance segmentations are used to…

Short-term passenger flow forecasting is a crucial task for urban rail transit operations. Emerging deep-learning technologies have become effective methods used to overcome this problem. In this study, the authors propose a deep-learning…

Attention models have recently emerged as a powerful approach, demonstrating significant progress in various fields. Visualization techniques, such as class activation mapping, provide visual insights into the reasoning of convolutional…

Deep neural networks (DNN) are powerful models for many pattern recognition tasks, yet their high computational complexity and memory requirement limit them to applications on high-performance computing platforms. In this paper, we propose…

Recently, the convolutional neural network has brought impressive improvements for object detection. However, detecting tiny objects in large-scale remote sensing images still remains challenging. First, the extreme large input size makes…

Recent advancements have led to a proliferation of machine learning systems used to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations of these systems. For robot…

Despite their tremendous successes, convolutional neural networks (CNNs) incur high computational/storage costs and are vulnerable to adversarial perturbations. Recent works on robust model compression address these challenges by combining…

SLAM is a fundamental component of modern autonomous systems, providing robots and their operators with a deeper understanding of their environment. SLAM systems often encounter challenges due to the dynamic nature of robotic motion,…

The reconstruction of the 3D permittivity map from ground-penetrating radar (GPR) data is of great importance for mapping subsurface environments and inspecting underground structural integrity. Traditional iterative 3D reconstruction…

Deep learning-based models, such as recurrent neural networks (RNNs), have been applied to various sequence learning tasks with great success. Following this, these models are increasingly replacing classic approaches in object tracking…

Modern top-performing object detectors depend heavily on backbone networks, whose advances bring consistent performance gains through exploring more effective network structures. In this paper, we propose a novel and flexible backbone…