Fiber to the Room (FTIR) is an evolution of the Fiber to the Home (FTTH) technology that relies on an in-home passive optical network and WiFi6 access points in each room to deliver Gb/s data rates with consistent and ubiquitous quality of service to ...

Natural untrimmed videos provide rich visual content for self-supervised learning. Yet most previous efforts to learn spatio-temporal representations rely on manually trimmed videos, such as Kinetics dataset (Carreira and Zisserman 2017), resulting in ...

The deep multi-view stereo (MVS) approaches generally construct 3D cost volumes to regularize and regress the depth map. These methods are limited with high-resolution outputs since the memory and time costs grow cubically as the volume resolution ...

Urban rail transit (URT) is an essential part of urban public transportation. Accurate ridership prediction is increasingly important for the safe operation and efficient management of URT. However, existing studies regard the URT stations with different ...

This paper presents a 4.5–8.5 GHz three-stage power amplifier(PA) fabricated in a 0.5 μm GaAs process. The PA adopts gain compensation technology with gain flatness and power transmission in the broadband. Furthermore, the size of the ...

Sparse-view CT is an efficient way for low dose scanning but degrades image quality. Inspired by the successful use of non-local attention in natural image denoising and compression artifact removal, we proposed a network combining integrated ...

• A satisfying image will be obtained after only one forward-back-projection computations.
• Self-adaptative integrated attention can replenish texture information.
• The proposed method shortens the reconstruction time, improves PSNR, ...

We propose a novel method that aims to automatically generate outdoor building layouts based on given boundary constraints. It effectively solves the problem of irregular shapes that occur in practical application scenarios, where boundary and ...

Discovering causal structure from purely observational data (i.e., causal discovery), aiming to identify causal relationships among variables, is a fundamental task in machine learning.The recent invention of differentiable score-based DAG learners is a ...

Event forecasting has been a demanding and challenging task throughout the entire human history. It plays a pivotal role in crisis alarming and disaster prevention in various aspects of the whole society. The task of event forecasting aims to model the ...

Visual query is a vital technique for comprehending and analyzing knowledge graphs, which provides an effective method to lower the barrier of querying knowledge graphs for non-professional users. Nevertheless, visual query techniques for knowledge ...

In this study, we developed a comprehensive modeling framework for simulation of ozonation process using combination of artificial intelligence and computational fluid dynamics (CFD). The process is carried out in a hollow-fiber membrane ...

Current few-shot action recognition approaches have achieved impressive performance using only a few labeled examples. However, they usually assume the base (train) and target (test) videos typically come from the same domain, which may limit ...

• Few-shot action recognition methods perform poorly in cross-domain situations.
• Self-supervised learning can alleviate domain shift.
• Temporal modeling is important in the cross-domain few-shot action setting.
• This is the first ...

At present, area has become one of the main bottlenecks restricting the development of EDA. The area optimization for XNOR/OR-based fixed polarity Reed–Muller (FPRM) circuits aims to find an FPRM circuit with a minimum area. Because the area ...

• A hybrid genetic algorithm is proposed to solve the switching sequence problem.
• An adaptive bacterial foraging algorithm is proposed to solve the combinatorial problem.
• An area optimization approach for FPRM logic circuits is ...

Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art image classification models ...

A bundle is a group of items that provides improved services to users and increased profits for sellers. However, locating the desired bundles that match the users' tastes still challenges us, due to the sparsity issue. Despite the remarkable performance ...

Multimedia recommendation methods aim to discover the user preference on the multi-modal information to enhance the collaborative filtering (CF) based recommender system. Nevertheless, they seldom consider the impact of feature extraction on the user ...

Leading sequential recommendation (SeqRec) models adopt empirical risk minimization (ERM) as the learning framework, which inherently assumes that the training data (historical interaction sequences) and the testing data (future interactions) are drawn ...

• An energy-efficient classification system is proposed for classifying different ripeness of peaches based on their visual and tactile characteristics on ...

Peach is a kind of popular fruit with significant economic value, but it is commonly sorted through manual labor on sorting lines, which can negatively affect the economic efficiency. To address this issue, this paper proposes a system ...

We propose an exponential spectral process (ESP) method for time discretization of spatial-temporal equations. The proposed ESP method uses explicit iterations at each time step, which allows us to use simple initializations at each ...

• The ESP method is able to have high accuracy and large time step sizes at same time.

Detecting code functional similarity forms the basis of various software engineering tasks. However, the detection is challenging as functionally similar code fragments can be implemented differently, e.g., with irrelevant syntax. Recent studies ...