咨询与建议

限定检索结果

文献类型

  • 204 篇 期刊文献
  • 198 篇 会议
  • 1 册 图书

馆藏范围

  • 403 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 266 篇 工学
    • 183 篇 计算机科学与技术...
    • 156 篇 软件工程
    • 68 篇 信息与通信工程
    • 62 篇 光学工程
    • 61 篇 生物医学工程(可授...
    • 58 篇 生物工程
    • 35 篇 电气工程
    • 31 篇 控制科学与工程
    • 21 篇 电子科学与技术(可...
    • 18 篇 机械工程
    • 12 篇 化学工程与技术
    • 9 篇 仪器科学与技术
    • 8 篇 建筑学
    • 7 篇 土木工程
    • 7 篇 交通运输工程
    • 7 篇 网络空间安全
  • 175 篇 理学
    • 86 篇 数学
    • 61 篇 生物学
    • 58 篇 物理学
    • 27 篇 统计学(可授理学、...
    • 14 篇 化学
    • 14 篇 系统科学
  • 77 篇 管理学
    • 48 篇 图书情报与档案管...
    • 28 篇 管理科学与工程(可...
    • 9 篇 工商管理
  • 47 篇 医学
    • 40 篇 临床医学
    • 34 篇 基础医学(可授医学...
    • 28 篇 药学(可授医学、理...
    • 14 篇 公共卫生与预防医...
  • 9 篇 法学
    • 9 篇 社会学
  • 7 篇 农学
  • 6 篇 教育学
  • 5 篇 经济学
  • 2 篇 哲学
  • 2 篇 文学
  • 2 篇 艺术学
  • 1 篇 历史学
  • 1 篇 军事学

主题

  • 28 篇 computer vision
  • 22 篇 image segmentati...
  • 16 篇 feature extracti...
  • 12 篇 deep learning
  • 12 篇 semantics
  • 10 篇 machine intellig...
  • 9 篇 neural networks
  • 8 篇 computer science
  • 8 篇 data mining
  • 8 篇 classification (...
  • 8 篇 object recogniti...
  • 7 篇 gabor filters
  • 7 篇 convolution
  • 7 篇 fuzzy systems
  • 7 篇 computational mo...
  • 7 篇 forecasting
  • 7 篇 training
  • 6 篇 humans
  • 6 篇 image analysis
  • 6 篇 shape

机构

  • 8 篇 university of sc...
  • 6 篇 centre for medic...
  • 6 篇 hessian ai
  • 6 篇 graduate institu...
  • 6 篇 centre for cogni...
  • 6 篇 key lab. of shan...
  • 6 篇 machine & hybrid...
  • 6 篇 center for brain...
  • 6 篇 nanjing universi...
  • 6 篇 heidelberg
  • 6 篇 department of el...
  • 5 篇 shanghai jiao to...
  • 5 篇 south china univ...
  • 5 篇 department of qu...
  • 5 篇 department of ra...
  • 5 篇 university of pe...
  • 5 篇 pazhou lab
  • 5 篇 department of pa...
  • 5 篇 department of co...
  • 5 篇 school of comput...

作者

  • 17 篇 zhi-qiang liu
  • 11 篇 singh koushlendr...
  • 10 篇 timofte radu
  • 10 篇 nair madhu s.
  • 9 篇 jha debesh
  • 9 篇 bakas spyridon
  • 9 篇 lu bao-liang
  • 9 篇 kersting kristia...
  • 9 篇 bagci ulas
  • 8 篇 kofler florian
  • 7 篇 reinke annika
  • 7 篇 menze bjoern
  • 6 篇 chen chen
  • 6 篇 zhao hai
  • 6 篇 nandy anup
  • 6 篇 li hao
  • 5 篇 galdran adrian
  • 5 篇 zhang dafeng
  • 5 篇 ezhov ivan
  • 5 篇 glocker ben

语言

  • 366 篇 英文
  • 36 篇 其他
  • 1 篇 中文
检索条件"机构=Computer Vision and Machine Intelligence Lab Department of Computer Science"
403 条 记 录,以下是121-130 订阅
Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers
arXiv
收藏 引用
arXiv 2023年
作者: Czech, Johannes Blüml, Jannis Kersting, Kristian Steingrimsson, Hedinn Artificial Intelligence and Machine Learning Lab TU Darmstadt Germany Darmstadt Germany Centre for Cognitive Science TU Darmstadt Germany Darmstadt Germany Department of Electrical and Computer Engineering Rice University HoustonTX United States HoustonTX United States
While transformers have gained recognition as a versatile tool for artificial intelligence (AI), an unexplored challenge arises in the context of chess — a classical AI benchmark. Here, incorporating vision Transform... 详细信息
来源: 评论
Deformable Symmetry Attention for Nuclear Medicine Image Segmentation
SSRN
收藏 引用
SSRN 2024年
作者: Zhang, Zeao Yang, Pei Liu, Ruomeng Cai, Huawei Zhao, Zhen Guo, Quan Yi, Zhang Machine Intelligence Lab College of Computer Science Sichuan University No. 24 Southern Section of First Ring Road Sichuan Chengdu610065 China Department of Nuclear Medicine West China Hospital of Sichuan University No. 17 Section 3 Renmin South Road Sichuan Chengdu610041 China
Prior knowledge of the medical domain has consistently enriched medical image analysis, yet its full potential remains to be explored. Our Deformable Symmetry Attention (DSA) aims to leverage anatomical symmetry prior... 详细信息
来源: 评论
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations
arXiv
收藏 引用
arXiv 2023年
作者: Mai, Gengchen Lao, Ni He, Yutong Song, Jiaming Ermon, Stefano Spatially Explicit Artificial Intelligence Lab Department of Geography University of Georgia United States Department of Computer Science Stanford University United States School of Computing University of Georgia United States Google Inc United States Machine Learning Department Carnegie Mellon University United States
Geo-tagged images are publicly available in large quantities, whereas labels such as object classes are rather scarce and expensive to collect. Meanwhile, contrastive learning has achieved tremendous success in variou...
来源: 评论
A Typology for Exploring the Mitigation of Shortcut Behavior
arXiv
收藏 引用
arXiv 2022年
作者: Friedrich, Felix Stammer, Wolfgang Schramowski, Patrick Kersting, Kristian Technical University of Darmstadt Computer Science Department Artificial Intelligence and Machine Learning Lab Darmstadt Germany Darmstadt Germany LAION Germany Germany Technical University of Darmstadt Centre for Cognitive Science Darmstadt Germany
As machine learning models become larger, and are increasingly trained on large and uncurated data sets in weakly supervised mode, it becomes important to establish mechanisms for inspecting, interacting, and revising... 详细信息
来源: 评论
Deep Learning Meets Teleconnections: Improving S2S Predictions for European Winter Weather
arXiv
收藏 引用
arXiv 2025年
作者: Bommer, Philine L. Kretschmer, Marlene Spuler, Fiona R. Bykov, Kirill Höhne, Marina M.-C. Understandable Machine Intelligence Lab TU Berlin Berlin Germany Department of Data Science ATB Potsdam Germany Leipzig Institute for Meteorology Leipzig University Leipzig Germany Department of Meteorology University of Reading Reading United Kingdom The Alan Turing Institute London United Kingdom Institute of Computer Science University of Potsdam Potsdam Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin Germany
Predictions on subseasonal-to-seasonal (S2S) timescales—ranging from two weeks to two months—are crucial for early warning systems but remain challenging owing to chaos in the climate system. Teleconnections, such a... 详细信息
来源: 评论
Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks
arXiv
收藏 引用
arXiv 2022年
作者: Lei, Yunwen Jin, Rong Ying, Yiming School of Computer Science University of Birmingham United Kingdom Machine Intelligence Technology Lab Alibaba Group China Department of Mathematics and Statistics State University of New York Albany United States
While significant theoretical progress has been achieved, unveiling the generalization mystery of overparameterized neural networks still remains largely elusive. In this paper, we study the generalization behavior of... 详细信息
来源: 评论
ROBUST EARLY-LEARNING: HINDERING THE MEMORIZATION OF NOISY labELS  9
ROBUST EARLY-LEARNING: HINDERING THE MEMORIZATION OF NOISY L...
收藏 引用
9th International Conference on Learning Representations, ICLR 2021
作者: Xia, Xiaobo Liu, Tongliang Han, Bo Gong, Chen Wang, Nannan Ge, Zongyuan Chang, Yi Trustworthy Machine Learning Lab School of Computer Science The University of Sydney Australia Department of Computer Science Hong Kong Baptist University Hong Kong School of Computer Science and Engineering Nanjing University of Science and Technology China ISN State Key Laboratory School of Telecommunications Engineering Xidian University China Medical AI Group Faculty of Engineering Monash University Australia Airdoc Research Monash University Australia School of Artificial Intelligence Jilin University China
The memorization effects of deep networks show that they will first memorize training data with clean labels and then those with noisy labels. The early stopping method therefore can be exploited for learning with noi... 详细信息
来源: 评论
label Alignment Regularization for Distribution Shift
arXiv
收藏 引用
arXiv 2022年
作者: Imani, Ehsan Zhang, Guojun Li, Runjia Luo, Jun Poupart, Pascal Torr, Philip H.S. Pan, Yangchen University of Alberta Alberta Machine Intelligence Institute Canada Huawei Noah’s Ark Lab Hong Kong Department of Engineering Science University of Oxford United Kingdom School of Computer Science University of Waterloo Canada
Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of all labels in the dataset is mostly in the span of the top few singular vectors of the data matrix. Drawing in... 详细信息
来源: 评论
Domain-independent video summarization based on transfer learning using convolutional neural network  1st
Domain-independent video summarization based on transfer lea...
收藏 引用
1st International Conference on Advances in Electrical and computer Technologies, ICAECT 2019
作者: Mohan, Jesna Nair, Madhu S. Department of Computer Science University of Kerala Kariavattom ThiruvananthapuramKerala695581 India Department of Computer Science and Engineering Mar Baselios College of Engineering and Technology Nalanchira ThiruvananthapuramKerala695015 India Artificial Intelligence & Computer Vision Lab Department of Computer Science Cochin University of Science and Technology KochiKerala682022 India
Video summarization methods generate a compact representation of the original video preserving the essential content of the input video. Video summaries utilize less storage space compared to the original video. The s... 详细信息
来源: 评论
Is L2 physics-informed loss always suitable for training physics-informed neural network?  22
Is L2 physics-informed loss always suitable for training phy...
收藏 引用
Proceedings of the 36th International Conference on Neural Information Processing Systems
作者: Chuwei Wang Shanda Li Di He Liwei Wang School of Mathematical Sciences Peking University Machine Learning Department School of Computer Science Carnegie Mellon University and Zhejiang Lab National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University and Center for Data Science Peking University
The Physics-Informed Neural Network (PINN) approach is a new and promising way to solve partial differential equations using deep learning. The L2 Physics- Informed Loss is the de-facto standard in training Physics-In...
来源: 评论