作者： Jiancheng Du¹;Yang Gao¹; （¹School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China）

出处： IEEE Transactions on Knowledge and Data Engineering 2024 Vol.36 No.3 P1044-1055

关键词： Adaptation models;Task analysis;Data models;Training;Benchmark testing;Predictive models;Question answering (information retrieval);Domain Adaptation;Teacher Model;Benchmark Datasets;Target Domain;Good Initialization;Video Summarization;Parallel Corpus;Large Volume Of Information;Training Set;Validation Set;Natural Language;Data Generation;Transfer Learning;Scarcity Of Data;Latent Space;Adaptive Model;Question Answering;Language Model;Confidence Threshold;Variational Autoencoder;Pre-trained Language Models;Self-supervised Learning;Student Model;General Summary;Soft Labels;Source Documents;Types Of Queries;Smooth Distribution;Masked Language Model

摘要： Text summarizing is the task of reducing a document\'s length while maintaining its essential information. In the age of information explosion, how to ...

作者： Jiayue Geng¹;Chen Ling²;Jinyu Liu²;Kexin Qiao¹;Xiangjian Yi¹;Liehuang Zhu¹; （¹School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China ²School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China）

出处： IEEE Internet of Things Journal 2024 P1

关键词： Ciphers;Security;Internet of Things;Logic gates;Software;Resistance;Matrices

摘要： The proliferation of the Internet of Things (IoT) has amplified the necessity for secure data transmission. Lightweight block ciphers are pivotal in f ...

作者： Changyong Yu¹;Yuhai Zhao¹;Chu Zhao¹;Jianyu Jin¹;Keming Mao¹;Guoren Wang²; （¹College of Computer Science and Engineering, Northeastern University, Shenyang, China ²School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China）

出处： IEEE/ACM Transactions on Computational Biology and Bioinformatics 2024 Vol.21 No.1 P129-142

关键词： Bioinformatics;Genomics;Indexing;Costs;Task analysis;Memory management;Data structures

摘要： The De Bruijn graph (DBG) has been widely used in the algorithms for indexing or organizing read and reference sequences in bioinformatics. However, a ...

作者： Hao Wang¹;Bo Tang²;Chi Harold Liu¹;Shangqin Mao²;Jiahong Zhou²;Zipeng Dai¹;Yaqi Sun²;Qianlong Xie²;Xingxing Wang²;Dong Wang²; （¹School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China ²Meituan, Beijing, China）

出处： IEEE Transactions on Computers 2024 Vol.73 No.3 P815-828

关键词： Advertising;Resource management;Real-time systems;Reinforcement learning;Deep learning;Costs;Training;Deep Reinforcement Learning;Budget Allocation;Hierarchical Reinforcement Learning;Large-scale Data;Data Augmentation;Data Logger;Financial Constraints;Response Strategies;Auxiliary Loss;Deep Reinforcement Learning Framework;Bidding Strategy;High-level Planner;Resource Constraints;Lagrange Multiplier;Solution Space;Online Advertising;Allocation Scheme;Reward Function;Specific Channel;Mean Absolute Percentage Error;Bid Price;Conditional Variational Autoencoder;Off-line Training;Click-through;User Feedback;State-action Pair;Historical Statistics;Policy Learning;Online Prediction;Advertising Effectiveness

摘要： Online display advertising platforms service numerous advertisers by providing real-time bidding (RTB) for the scale of billions of ad requests every ...

作者： Mixue Xie¹;Shuang Li¹;CA1;Kaixiong Gong¹;Yulin Wang²;Gao Huang²; （¹School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China;²Department of Automation, Tsinghua University, Beijing, China）

出处： International Journal of Computer Vision 2024 Vol.132 No.4 P1417-1441

关键词： Domain shift;Domain adaptation;Semantic augmentation;Prototype constraint

摘要： The demand for reducing label annotation cost and adapting to new data distributions gives rise to the emergence of domain adaptation (DA). DA aims to ...

作者： Dapeng Yan¹;Gangyi Ding¹;Kexiang Huang¹;Chongzhi Bai¹;Lian He¹;Longfei Zhang¹; （¹Key Laboratory of Digital Performance and Simulation Technology, School of Computer Science, Beijing Institute of Technology, Beijing 100081, China）

出处： Electronics 2024 Vol.13 No.5 P934

关键词： crowd simulation;social force model;pedestrian simulation;physics-infused machine learning

摘要： The traditional social force model (SFM) in crowd simulation experiences difficulty coping with the complexity of the crowd, limited by singular physi ...

作者： Xiaochen Liu¹;Fan Li¹;Yetong Cao¹;Yu Wang²; （¹School of Computer Science, Beijing Institute of Technology, Beijing, China ²Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA）

出处： IEEE Transactions on Mobile Computing 2024 P1-15

关键词： Braille;Wrist;Character recognition;Sensors;Piezoelectric transducers;Motion detection;Mobile computing

摘要： With the ever-increasing demand for improving communication and independence for visually impaired people, automatic Braille recognition has gained in ...

作者： Jiang, Xiurong¹; Hou, Yifan¹; Tian, Hui¹; Zhu, Lin²; （¹State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China;²School of Computer Science, Beijing Institute of Technology, Beijing, China）

出处： IET Computer Vision 2024 Vol.18 No.1 P15-32

关键词： image segmentation;object detection

摘要： Conventional RGB-T salient object detection treats RGB and thermal modalities equally to locate the common salient regions. However, the authors obser ...

作者： Heyan Huang¹;1;Puhai Yang¹;CA2;Wei Wei²;3;Shumin Shi¹;4;Xian-Ling Mao¹;5 （¹School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China;²School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China）

出处： Knowledge-Based Systems 2024 P111677

摘要： As of present, the progress of conversational AI research has been greatly propelled by large-scale pre-trained language models. In particular, task-o ...

作者： Hao Wang¹;Chi Harold Liu¹;Haoming Yang¹;Guoren Wang¹;Kin K. Leung²; （¹School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China ²Electrical and Electronic Engineering (EEE) Department, and the Computing Department, Imperial College, London, U.K.）

出处： IEEE/ACM Transactions on Networking 2024 Vol.32 No.1 P566-581

关键词： Sensors;Optimization;Crowdsensing;Autonomous aerial vehicles;Data integrity;Trajectory;Trajectory planning;Deep Reinforcement Learning;Multi-agent Deep Reinforcement Learning;Mobile Crowdsensing;Unmanned Aerial Vehicles;Real-world Datasets;Specific Threshold;Cooperative Mechanism;Trajectory Planning;Intrinsic Rewards;Distributed Architecture;Optimization Problem;Deep Neural Network;Emergency Response;Time Data;Temporal Features;Lack Of Models;Path Planning;Path Loss;Penalty Function;Limited Capability;Policy Network;Deep Reinforcement Learning Method;Temporal Model;Proximal Policy Optimization;Division Of Work;Multiple Unmanned Aerial Vehicles;Reconfigurable Intelligent Surface;L2 Loss;Trajectory Design;Unmanned Aerial Vehicle Trajectory

摘要： Unmanned aerial vehicle (UAV) crowdsensing (UCS) is an emerging data collection paradigm to provide reliable and high quality urban sensing services, ...