Sorry, you need to enable JavaScript to visit this website.

Recent attempts show that factorizing 3D convolutional filters into separate spatial and temporal components brings impressive improvement in action recognition. However, traditional temporal convolution operating along the temporal dimension will aggregate unrelated features, since the feature maps of fast-moving objects have shifted spatial positions. In this paper, we propose a novel and effective Multi-Directional convolution (MDConv), which extracts features along different spatial-temporal orientations.

Categories:
10 Views

Recently, unsupervised learning is proposed to avoid the performance degrading caused by synthesized paired computed tomography (CT) images. However, existing unsupervised methods for metal artifact reduction (MAR) only use features in image space, which is not enough to restore regions heavily corrupted by metal artifacts. Besides, they lack the distinction and selection for effective features. To address these issues, we propose an attention-embedded decomposed network to reduce metal artifacts in both image space and sinogram space with unpaired images.

Categories:
8 Views

Unmanned aerial vehicles (UAV) often rely on GPS for navigation. GPS signals, however, are very low in power and easily jammed or otherwise disrupted. This paper presents a method for determining the navigation errors present at the beginning of a GPS-denied period utilizing data from a synthetic aperture radar (SAR) system. This is accomplished by comparing an online-generated SAR image with a reference image obtained a priori.

Categories:
11 Views

Unmanned aerial vehicles (UAV) often rely on GPS for navigation. GPS signals, however, are very low in power and easily jammed or otherwise disrupted. This paper presents a method for determining the navigation errors present at the beginning of a GPS-denied period utilizing data from a synthetic aperture radar (SAR) system. This is accomplished by comparing an online-generated SAR image with a reference image obtained a priori.

Categories:
18 Views

Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited number of samples for each task, the initial embedding network for meta-learning becomes an essential component and can largely affect the performance in practice. To this end, most of the existing methods highly rely on the efficient embedding network.

Categories:
7 Views

Convolutional neural networks (CNN) have emerged as a powerful tool for solving computational imaging reconstruction problems. However, CNNs are generally difficult-to-understand black-boxes. Accordingly, it is challenging to know when they will work and, more importantly, when they will fail.

Categories:
1 Views

The relatively low resolution of Time-of-Flight (ToF) cameras, together with high power consumption and motion artifacts due to long exposure times, have kept ToF sensors away from classical lidar application fields, such as mobile robotics and autonomous driving. In this paper we note that while attempting to address the last two issues, e. g., via burst mode, the lateral resolution can be effectively increased. Differently from prior approaches, we propose a stripped-down modular super-resolution framework that operates in the raw data domain.

Categories:
5 Views

Pages