作者： Ji, Hangxu¹;Jiang, Su¹;Zhao, Yuhai¹;Wu, Gang¹;Wang, Guoren²;Yuan, George Y³; （¹School of Computer Science and Engineering, Northeastern University, No. 3-11, Wenhua Road, Heping District, Shenyang, 110819, PR China ²School of Computer Science and Technology, Beijing Institute of Technology, No. 5, South Street, Zhongguancun, Haidian District, Beijing, 100081, PR China ³Thinvent Digital Technology Co.,Ltd., No. 681 Torch Avenue, High-Tech Development Zone, Nanchang, 410000, PR China）

出处： Future Generation Computer Systems 2023 Vol.141 Suppl C P67-80

关键词： Cache;Flink;Hotspot awareness;Mixed batch-stream data join;Skip list

摘要： The new computing model, mixed batch-stream data processing, plays a crucial role in big spatiotemporal data managements. As the core of the above com ...

发明人： 黄华，赵天琦

申请人： 北京理工大学

申请号： 202310825876.9

申请日期： 2023.07.06

摘要： 一种基于扩散模型的高真实感神经渲染方法，属于多模态视觉生成领域。采用扩散模型作为条件生成模型，利用语义编码器将人脸模型与目标人脸部图像压缩到语义空间提取条件信息，进而生成在语义条件隐变量下人脸模型的渲染结果，提高生成人脸图像的高真实感和准确性。通过显示地学习三维人脸模型到二维图像的映射关系，在采样过 ...

发明人： 朱林，张鹏杰，王立志，张磊，黄华

申请人： 北京理工大学

申请号： 202311252300.4

申请日期： 2023.09.26

摘要： 本发明公开的一种基于事件相机的多模态光流估计方法，属于光流估计领域。将事件、图像两种模态数据作为输入，利用事件的高时间分辨率、低延迟、高动态范围的优势提升光流估计算法在低光、高速场景下的性能。通过将事件数据流转化为事件体素，神经网络能被用于事件数据的处理；通过循环神经网络和特征残差连接，实现事件特征 ...

作者： Li, Yang¹; Li, Kan¹;

出处： 6th International Conference on Frontiers in Cyber Security, FCS 2023 Chengdu, China 2023

摘要： Federated learning is a privacy-preserving framework that collaboratively trains the global model without sharing raw data among clients. However, one ...

作者： Zhang, Yan¹; Gao, Guangyu¹; Wang, Qianxiang¹; Ge, Jing¹;

出处： 6th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2023 Xiamen, China 2023

摘要： Utilizing part-level features provides a more detailed representation, leading to improved results in person re-identification (ReID). Yet existing wo ...

作者： Xiang, Chao¹; Feng, Chen²; Xie, Xiaopo²; Shi, Botian³; Lu, Hao⁴; Lv, Yisheng⁴; Yang, Mingchuan⁵; Niu, Zhendong⁶ （¹Beijing Institute of Technology, Beijing, China;²China Telecom Beijing Research Institute, Beijing, China;³Shanghai AI Laboratory, Shanghai, China;⁴State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China;⁵Institute of Big Data and Artificial Intelligence, China Telecom Beijing Research Institute, Beijing, China;⁶School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China）

出处： IEEE Intelligent Transportation Systems Magazine 2023 P2-24

作者： Li, Rongqing¹; Yu, Jiaqi¹; Li, Changsheng¹; Luo, Wenhan²; Yuan, Ye¹; Wang, Guoren¹ （¹The School of Computer Science and Technology, Beijing Institute of Technology, Beijing; 100081, China;²The School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Guangdong, Shenzhen; 518107, China）

出处： arXiv 2023

作者： Gong, Weijun¹; Qian, Yurong^{1, 2, 3}; Zhou, Weihang³; Leng, Hongyong^{3, 4} （¹School of Information Science and Engineering, Xinjiang University, Urumqi; 830046, China;²Xinjiang Key Laboratory of Signal Detection and Processing, Xinjiang University, Urumqi; 830046, China;³School of Software, Xinjiang University, Urumqi; 830046, China;⁴School of Computer Science, Beijing Institute of Technology, Beijing; 100081, China）

出处： Biomedical Signal Processing and Control 2023

作者： Wu, Ping¹; Liu, Zhengyang¹; Lu, Haolin¹; Huang, Heyan² （¹School of Computer Science and Technology, Beijing Institute of Technology, Beijing; 100081, China;²Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications, China）

出处： SSRN 2023

作者： Feng, Chen¹; Xiang, Chao¹; Xie, Xiaopo¹; Zhang, Yuan¹; Yang, Mingchuan¹; Li, Xuesong² （¹China Telecom Corporation Ltd, Beijing Research Institute, Beijing, China;²School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China）

出处： IEEE Transactions on Computational Social Systems 2023 P1-11