咨询与建议

限定检索结果

文献类型

  • 307 篇 会议
  • 196 篇 期刊文献
  • 1 册 图书

馆藏范围

  • 504 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 328 篇 工学
    • 203 篇 计算机科学与技术...
    • 186 篇 软件工程
    • 68 篇 机械工程
    • 63 篇 控制科学与工程
    • 49 篇 信息与通信工程
    • 42 篇 生物工程
    • 41 篇 光学工程
    • 31 篇 仪器科学与技术
    • 22 篇 生物医学工程(可授...
    • 20 篇 化学工程与技术
    • 17 篇 电气工程
    • 16 篇 建筑学
    • 16 篇 航空宇航科学与技...
    • 14 篇 力学(可授工学、理...
    • 13 篇 土木工程
    • 12 篇 电子科学与技术(可...
    • 8 篇 材料科学与工程(可...
    • 7 篇 动力工程及工程热...
  • 145 篇 理学
    • 60 篇 数学
    • 46 篇 物理学
    • 44 篇 生物学
    • 17 篇 统计学(可授理学、...
    • 15 篇 化学
    • 9 篇 系统科学
  • 65 篇 管理学
    • 48 篇 管理科学与工程(可...
    • 22 篇 图书情报与档案管...
    • 10 篇 工商管理
  • 21 篇 医学
    • 19 篇 临床医学
    • 15 篇 基础医学(可授医学...
    • 13 篇 药学(可授医学、理...
  • 4 篇 经济学
  • 4 篇 法学
  • 4 篇 教育学
  • 4 篇 农学
  • 2 篇 艺术学
  • 1 篇 军事学

主题

  • 20 篇 training
  • 19 篇 three-dimensiona...
  • 18 篇 solid modeling
  • 17 篇 virtual reality
  • 15 篇 semantics
  • 14 篇 object detection
  • 13 篇 feature extracti...
  • 12 篇 computational mo...
  • 11 篇 convolution
  • 10 篇 deep learning
  • 9 篇 semantic segment...
  • 9 篇 image segmentati...
  • 8 篇 optimization
  • 8 篇 visualization
  • 8 篇 machine learning
  • 8 篇 joints
  • 8 篇 pose estimation
  • 7 篇 rendering (compu...
  • 7 篇 cameras
  • 7 篇 fingers

机构

  • 193 篇 state key labora...
  • 66 篇 state key labora...
  • 55 篇 hangzhou innovat...
  • 39 篇 zhongguancun lab...
  • 27 篇 peng cheng labor...
  • 18 篇 zhengzhou univer...
  • 18 篇 beihang universi...
  • 14 篇 state key labora...
  • 13 篇 state key labora...
  • 13 篇 beihang universi...
  • 12 篇 school of comput...
  • 12 篇 state key labora...
  • 12 篇 the state key la...
  • 10 篇 the state key la...
  • 10 篇 institute of art...
  • 10 篇 qingdao research...
  • 10 篇 state key labora...
  • 10 篇 jiangxi research...
  • 9 篇 school of new me...
  • 9 篇 international re...

作者

  • 41 篇 wang yunhong
  • 41 篇 liu qingjie
  • 27 篇 jianwei niu
  • 20 篇 yue qi
  • 17 篇 li jia
  • 16 篇 yunhong wang
  • 15 篇 qingjie liu
  • 13 篇 yuru zhang
  • 12 篇 aimin hao
  • 12 篇 tao ren
  • 12 篇 qi yue
  • 11 篇 xuefeng liu
  • 11 篇 shuai li
  • 11 篇 haibin duan
  • 10 篇 niu jianwei
  • 10 篇 jin xiao
  • 10 篇 xiaoguang hu
  • 9 篇 jiting li
  • 9 篇 hao aimin
  • 8 篇 fu zehua

语言

  • 488 篇 英文
  • 10 篇 其他
  • 7 篇 中文
检索条件"机构=State Key Laboratory of Virtual Reality Technology and Systems Robotics Institute"
504 条 记 录,以下是71-80 订阅
排序:
FEAT: Towards Fast Environment-Adaptive Task Offloading and Power Allocation in MEC  42
FEAT: Towards Fast Environment-Adaptive Task Offloading and ...
收藏 引用
42nd IEEE International Conference on Computer Communications, INFOCOM 2023
作者: Ren, Tao Hu, Zheyuan He, Hang Niu, Jianwei Liu, Xuefeng Institute of Software Chinese Academy of Sciences Laboratory for Internet Software Technologies Beijing China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China
Mobile edge computing (MEC) has been proposed to provide mobile devices with both satisfactory computing resources and latency. key issues in MEC include task offloading and power allocation (TOPA), for which deep rei... 详细信息
来源: 评论
NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting
arXiv
收藏 引用
arXiv 2024年
作者: Ji, Yiming Liu, Yang Xie, Guanghu Ma, Boyu Xie, Zongwu Liu, Hong State Key Laboratory of Robotics and Systems Harbin Institute of Technology China
We propose NEDS-SLAM, a dense semantic SLAM system based on 3D Gaussian representation, that enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in real-time. In the system, we pro... 详细信息
来源: 评论
SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking
arXiv
收藏 引用
arXiv 2025年
作者: Cai, Wenrui Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhongguancun Laboratory Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China
Most state-of-the-art trackers adopt one-stream paradigm, using a single Vision Transformer for joint feature extraction and relation modeling of template and search region images. However, relation modeling between d... 详细信息
来源: 评论
Enabling Communication-Efficient Federated Learning via Distributed Compressed Sensing  42
Enabling Communication-Efficient Federated Learning via Dist...
收藏 引用
42nd IEEE International Conference on Computer Communications, INFOCOM 2023
作者: Guan, Yixuan Liu, Xuefeng Ren, Tao Niu, Jianwei Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing China Zhongguancun Laboratory Beijing China Chinese Academy of Sciences Laboratory for Internet Software Technologies Institute of Software Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China
Federated learning (FL) trains a shared global model by periodically aggregating gradients from local devices. Communication overhead becomes a principal bottleneck in FL since participating devices usually suffer fro... 详细信息
来源: 评论
Continuous Review and Timely Correction: Enhancing the Resistance to Noisy Labels via Self-Not-True Distillation
Continuous Review and Timely Correction: Enhancing the Resis...
收藏 引用
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Jingyi Wang Da Huang Xinghao Wu Yuhua Tang Long Lan Institute for Quantum Information & State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China
Deep neural networks possess substantial learning capacities and robust expressive power, making them prone to overfitting mislabeled data. Fortunately, the memorization effect shows that the networks tend to memorize...
来源: 评论
A Survey on Remote Sensing Foundation Models: From Vision to Multimodality
arXiv
收藏 引用
arXiv 2025年
作者: Huang, Ziyue Yan, Hongxi Zhan, Qiqi Yang, Shuai Zhang, Mingming Zhang, Chenkai Lei, YiMing Liu, Zeming Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Hangzhou Innovation Institute Beihang University Hangzhou310051 China
The rapid advancement of remote sensing foundation models, particularly vision and multimodal models, has significantly enhanced the capabilities of intelligent geospatial data interpretation. These models combine var... 详细信息
来源: 评论
LBPE: Long-token-first Tokenization to Improve Large Language Models
LBPE: Long-token-first Tokenization to Improve Large Languag...
收藏 引用
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Haoran Lian Yizhe Xiong Zijia Lin Jianwei Niu Shasha Mo Hui Chen Peng Liu Guiguang Ding Beihang University Tsinghua University BNRist State Key Laboratory of Virtual Reality Technology and Systems Beihang University Zhongguancun Laboratory Zhengzhou University Research Institute of Industrial Technology Zhengzhou University Beijing Institute of Technology
The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persis... 详细信息
来源: 评论
Rapid Path Extraction and Three-Dimensional Roaming of the virtual Endonasal Endoscope
收藏 引用
Chinese Journal of Electronics 2021年 第3期30卷 397-405页
作者: WANG Yudong HAN Jing PAN Junjun WANG Jing CAO Yi ZHU Li LUO Yanlin School of Artificial Intelligence Beijing Normal University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Institute of Applied Physics and Computational Mathematics Department of Otolaryngology Head and Neck Surgery Peking University Third Hospital
Compared with traditional endonasal endoscope, virtual endonasal endoscope(VEE) is a computerized alternative solution with the advantages of being non-invasive, affordable, no perforation, low risk of infection, and ... 详细信息
来源: 评论
Pedestrian Attribute Recognition as Label-balanced Multi-label Learning
arXiv
收藏 引用
arXiv 2024年
作者: Zhou, Yibo Hu, Hai-Miao Xiang, Yirong Zhang, Xiaokang Wu, Haotian State Key Laboratory of Virtual Reality Technology and Systems Beihang University China Hangzhou Innovation Institute Beihang University China The University of Manchester United Kingdom
Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions... 详细信息
来源: 评论
Simultaneous Scene-independent Camera Localization and Category-level Object Pose Estimation via Multi-level Feature Fusion
Simultaneous Scene-independent Camera Localization and Categ...
收藏 引用
IEEE Annual International Symposium virtual reality
作者: Junyi Wang Yue Qi State Key Laboratory of Virtual Reality Technology and Systems Beihang University Peng Cheng Laboratory Qingdao Research Institute of Beihang University
In AR/MR applications, camera localization and object pose estimation both play crucial roles. The universality of learning techniques, often referred to as scene-independent localization and category-level pose estim... 详细信息
来源: 评论