Recently, recommender systems based on knowledge graphs (KGs) have become a popular research direction. Graph neural network (GNN) is the key technology of KG-based recommendation systems. However, existing GNNs have a significant flaw: they cannot ...

We introduce a reusable automated model-based GUI testing technique for Android apps to accelerate the testing cycle. Our key insight is that the knowledge of event-activity transitions from the previous testing runs, i.e., executing which events can ...

Non-Volatile Memory (NVM) has been extensively researched as the alternative for DRAM-based system, however traditional Memory Controller (MC) cannot efficiently track and schedule operations for all the memory devices in heterogeneous systems due to ...

Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods due to their state-of-the-art performance. ...

Clothes attribution prediction is the key technology for users to automatically describe clothing characteristics. Most current methods are first to detect the multiple clothes, and then crop out the clothes and feed to a certain network for clothes ...

Recent years have witnessed remarkable progress on knowledge graph embedding (KGE) methods to learn the representations of entities and relations in static knowledge graphs (SKGs). However, knowledge changes over time. In order to represent the facts ...

Data-driven single image deraining (SID) models have achieved greater progress by simulations, but there is still a large gap between current deraining performance and practical high-level applications, since high-level semantic information is usually ...

Blind image deblurring (BID) remains a challenging and significant task. Benefiting from the strong fitting ability of deep learning, paired data-driven supervised BID methods have obtained great progress. However, paired data are usually synthesized by ...

Large-scale pixel-level annotations are scarce for current data-hungry medical image analysis models. For the fast acquisition of annotations, an economical and efficient interactive medical image segmentation method is urgently needed. However, current ...

Predicting the future trajectories of multiple agents is essential for various applications in real life, such as surveillance systems, autonomous driving and social robots. The trajectory prediction task is influenced by many factors, including the ...

Deep image inpainting methods have improved the inpainting performance greatly due to the powerful representation ability of deep learning. However, current deep inpainting networks still tend to produce unreasonable structures and blurry textures due ...

Blind image deblurring is still a challenging problem due to the inherent ill-posed properties. To improve the deblurring performance, many supervised methods have been proposed. However, obtaining labeled samples from a specific distribution (or a ...

Convolutional Neural Networks (CNNs) are powerful for image representation, but the convolution operation may be influenced and degraded by the included noise, and the deep features may not be fully learned. In this paper, we propose a new encoder-...

Synchronous Rain streaks and Raindrops Removal (SR^3) is a hard and challenging task, since rain streaks and raindrops are two wildly divergent real-world phenomena with different optical properties and mathematical distributions. As such, most existing ...

Objects with thin structures remain challenging for current image segmentation techniques. Their outputs often do well in the main body but with thin parts unsatisfactory. In practical use, they inevitably need post-processing. However, repairing them ...

Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods. STGNNs jointly model the spatial and ...

We all depend on mobility, and vehicular transportation affects the daily lives of most of us. Thus, the ability to forecast the state of traffic in a road network is an important functionality and a challenging task. Traffic data is often obtained from ...

This paper proposes a prediction method by combining second-order Volterra (SOV) model and Kalman filter to further improve prediction accuracy of the traditional Kalman model in short-term traffic flow forecasting. Nonlinear relationship may exist in ...

Unsupervised learning methods that treat depth estimation as image reconstruction has achieved promising results recently. Most existing methods generate disparity maps from multi-layers residual network by training image reconstruction loss for left ...

Asking questions is usually used by teachers to guide students to think and to interact with students. Bloom's Taxonomy has been used widely in the educational field to assess students’ intellectual abilities and skills. However, most questions lack a ...