咨询与建议

限定检索结果

文献类型

  • 82 篇 会议
  • 70 篇 期刊文献

馆藏范围

  • 152 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 120 篇 工学
    • 88 篇 计算机科学与技术...
    • 87 篇 软件工程
    • 37 篇 光学工程
    • 29 篇 生物医学工程(可授...
    • 24 篇 生物工程
    • 17 篇 机械工程
    • 15 篇 信息与通信工程
    • 13 篇 控制科学与工程
    • 12 篇 电气工程
    • 9 篇 电子科学与技术(可...
    • 8 篇 交通运输工程
    • 5 篇 化学工程与技术
    • 3 篇 仪器科学与技术
    • 3 篇 建筑学
    • 2 篇 力学(可授工学、理...
    • 2 篇 材料科学与工程(可...
    • 2 篇 轻工技术与工程
  • 60 篇 理学
    • 26 篇 数学
    • 25 篇 生物学
    • 21 篇 物理学
    • 5 篇 化学
    • 5 篇 系统科学
    • 4 篇 统计学(可授理学、...
    • 2 篇 大气科学
  • 23 篇 管理学
    • 12 篇 管理科学与工程(可...
    • 11 篇 图书情报与档案管...
    • 6 篇 工商管理
  • 18 篇 医学
    • 16 篇 临床医学
    • 14 篇 基础医学(可授医学...
    • 10 篇 药学(可授医学、理...
  • 2 篇 农学
  • 1 篇 经济学
  • 1 篇 教育学

主题

  • 13 篇 computer graphic...
  • 12 篇 cameras
  • 10 篇 computer vision
  • 9 篇 object detection
  • 7 篇 visualization
  • 7 篇 robustness
  • 6 篇 generative adver...
  • 6 篇 laboratories
  • 6 篇 augmented realit...
  • 5 篇 three-dimensiona...
  • 5 篇 virtual reality
  • 4 篇 target tracking
  • 4 篇 feature extracti...
  • 4 篇 detectors
  • 4 篇 classification (...
  • 4 篇 solid modeling
  • 4 篇 training
  • 3 篇 magnetic resonan...
  • 3 篇 lighting
  • 3 篇 computational mo...

机构

  • 18 篇 institute for co...
  • 15 篇 computer algorit...
  • 13 篇 institute of com...
  • 10 篇 partner site ess...
  • 9 篇 key laboratory o...
  • 9 篇 christian dopple...
  • 8 篇 university medic...
  • 8 篇 christian dopple...
  • 7 篇 christian dopple...
  • 7 篇 institute for co...
  • 6 篇 university medic...
  • 6 篇 institute of com...
  • 6 篇 computer vision ...
  • 4 篇 institute for co...
  • 4 篇 computer vision ...
  • 4 篇 institute of com...
  • 4 篇 school of comput...
  • 3 篇 ucla computer gr...
  • 3 篇 ucla center for ...
  • 3 篇 institute of com...

作者

  • 26 篇 egger jan
  • 22 篇 bischof horst
  • 15 篇 possegger horst
  • 13 篇 gsaxner christin...
  • 11 篇 pepe antonio
  • 11 篇 li jianning
  • 10 篇 lin wei
  • 10 篇 horst bischof
  • 10 篇 kleesiek jens
  • 8 篇 vincent lepetit
  • 8 篇 kozinski mateusz
  • 7 篇 pascal fua
  • 6 篇 horst possegger
  • 6 篇 fraundorfer frie...
  • 6 篇 zucker sw
  • 5 篇 fruhwirth-reisin...
  • 5 篇 mirza muhammad j...
  • 5 篇 ferreira andré
  • 5 篇 wei lin
  • 5 篇 alves victor

语言

  • 145 篇 英文
  • 7 篇 其他
检索条件"机构=Computer Graphics and Computer Vision Laboratory"
152 条 记 录,以下是21-30 订阅
排序:
ActMAD: Activation Matching to Align Distributions for Test-Time-Training
arXiv
收藏 引用
arXiv 2022年
作者: Mirza, Muhammad Jehanzeb Soneira, Pol Jané Lin, Wei Kozinski, Mateusz Possegger, Horst Bischof, Horst Institute for Computer Graphics and Vision TU Graz Austria Christian Doppler Laboratory for Embedded Machine Learning Institute of Control Systems KIT Germany Christian Doppler Laboratory for Semantic 3D Computer Vision
Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. We propose to perform this adaptation via Activation Match... 详细信息
来源: 评论
SAILOR: Scaling Anchors via Insights into Latent Object Representation
arXiv
收藏 引用
arXiv 2022年
作者: Malić, Dušan Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria
LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towards object sizes. However, object size... 详细信息
来源: 评论
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions  32
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo ba...
收藏 引用
32nd British Machine vision Conference, BMVC 2021
作者: Sormann, Christian Rossi, Mattia Kuhn, Andreas Fraundorfer, Friedrich Institute of Computer Graphics and Vision Graz University of Technology Austria Sony Europe B.V. R&D Center Stuttgart Laboratory 1 Germany
We present a novel deep-learning-based method for Multi-View Stereo. Our method estimates high resolution and highly precise depth maps iteratively, by traversing the continuous space of feasible depth values at each ... 详细信息
来源: 评论
MATE: Masked Autoencoders are Online 3D Test-Time Learners
MATE: Masked Autoencoders are Online 3D Test-Time Learners
收藏 引用
International Conference on computer vision (ICCV)
作者: M. Jehanzeb Mirza Inkyu Shin Wei Lin Andreas Schriebl Kunyang Sun Jaesung Choe Mateusz Kozinski Horst Possegger In So Kweon Kuk-Jin Yoon Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Korea Advanced Institute of Science and Technology (KAIST) South Korea Southeast University China
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data. Like existing TTT meth...
来源: 评论
CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video
arXiv
收藏 引用
arXiv 2022年
作者: Lin, Wei Kukleva, Anna Sun, Kunyang Possegger, Horst Kuehne, Hilde Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Max-Planck-Institute for Informatics Germany Southeast University China Goethe University Frankfurt Germany Christian Doppler Laboratory for Semantic 3D Computer Vision
Although action recognition has achieved impressive results over recent years, both collection and annotation of video training data are still time-consuming and cost intensive. Therefore, image-to-video adaptation ha... 详细信息
来源: 评论
MATE: Masked Autoencoders are Online 3D Test-Time Learners
arXiv
收藏 引用
arXiv 2022年
作者: Mirza, M. Jehanzeb Shin, Inkyu Lin, Wei Schriebl, Andreas Sun, Kunyang Choe, Jaesung Possegger, Horst Kozinski, Mateusz Kweon, In So Yoon, Kuk-Jin Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Korea Republic of Southeast University China
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data. Like existing TTT meth... 详细信息
来源: 评论
Video Test-Time Adaptation for Action Recognition
arXiv
收藏 引用
arXiv 2022年
作者: Lin, Wei Mirza, Muhammad Jehanzeb Kozinski, Mateusz Possegger, Horst Kuehne, Hilde Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Semantic 3D Computer Vision Christian Doppler Laboratory for Embedded Machine Learning Goethe University Frankfurt Germany MIT-IBM Watson AI Lab United States
Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of vi... 详细信息
来源: 评论
CC-DCNet: Dynamic Convolutional Neural Network with Contrastive Constraints for Identifying Lung Cancer Subtypes on Multi-modality Images
arXiv
收藏 引用
arXiv 2024年
作者: Jin, Yuan Ma, Gege Chen, Geng Lyu, Tianling Egger, Jan Lyu, Junhui Zhang, Shaoting Zhu, Wentao Zhejiang Lab 311121 China Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi’an710072 China The Zhejiang University School of Medicine Sir Run Run Shaw Hospital Hangzhou310016 China Shanghai Artificial Intelligence Laboratory Shanghai200120 China
The accurate diagnosis of pathological subtypes of lung cancer is of paramount importance for follow-up treatments and prognosis managements. Assessment methods utilizing deep learning technologies have introduced nov... 详细信息
来源: 评论
MD-Net: Multi-Detector for Local Feature Extraction
arXiv
收藏 引用
arXiv 2022年
作者: Santellani, Emanuele Sormann, Christian Rossi, Mattia Kuhn, Andreas Fraundorfer, Friedrich Institute of Computer Graphics and Vision Graz University of Technology Austria R&D Center Stuttgart Laboratory 1 Sony Europe B.V. Germany
Establishing a sparse set of keypoint correspondences between images is a fundamental task in many computer vision pipelines. Often, this translates into a computationally expensive nearest neighbor search, where ever... 详细信息
来源: 评论
DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo
arXiv
收藏 引用
arXiv 2022年
作者: Sormann, Christian Santellani, Emanuele Rossi, Mattia Kuhn, Andreas Fraundorfer, Friedrich Graz University of Technology Institute of Computer Graphics and Vision Austria Sony Europe B.V. R&D Center Stuttgart Laboratory 1 Germany
We propose a novel approach for deep learning-based Multi-View Stereo (MVS). For each pixel in the reference image, our method leverages a deep architecture to search for the corresponding point in the source image di... 详细信息
来源: 评论