咨询与建议

限定检索结果

文献类型

  • 47 篇 期刊文献
  • 37 篇 会议

馆藏范围

  • 84 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 56 篇 工学
    • 44 篇 计算机科学与技术...
    • 38 篇 软件工程
    • 15 篇 光学工程
    • 11 篇 信息与通信工程
    • 11 篇 生物工程
    • 8 篇 生物医学工程(可授...
    • 7 篇 控制科学与工程
    • 5 篇 机械工程
    • 4 篇 电气工程
    • 2 篇 仪器科学与技术
    • 2 篇 材料科学与工程(可...
    • 2 篇 安全科学与工程
    • 1 篇 力学(可授工学、理...
    • 1 篇 电子科学与技术(可...
  • 27 篇 理学
    • 12 篇 生物学
    • 11 篇 数学
    • 8 篇 物理学
    • 6 篇 统计学(可授理学、...
    • 2 篇 系统科学
    • 1 篇 化学
  • 13 篇 管理学
    • 10 篇 图书情报与档案管...
    • 2 篇 管理科学与工程(可...
  • 8 篇 医学
    • 8 篇 临床医学
    • 3 篇 基础医学(可授医学...
    • 3 篇 药学(可授医学、理...
  • 2 篇 法学
    • 2 篇 社会学
  • 2 篇 教育学
    • 2 篇 心理学(可授教育学...
    • 1 篇 教育学
  • 1 篇 文学
    • 1 篇 中国语言文学
    • 1 篇 外国语言文学

主题

  • 6 篇 semantics
  • 4 篇 deep learning
  • 4 篇 three-dimensiona...
  • 3 篇 object detection
  • 3 篇 visualization
  • 3 篇 training
  • 2 篇 visual informati...
  • 2 篇 reinforcement le...
  • 2 篇 task analysis
  • 2 篇 generative adver...
  • 2 篇 fungi
  • 2 篇 image segmentati...
  • 2 篇 anomaly detectio...
  • 2 篇 medical imaging
  • 2 篇 cameras
  • 2 篇 convolution
  • 2 篇 benchmarking
  • 2 篇 machine learning
  • 2 篇 sensors
  • 2 篇 eye movements

机构

  • 6 篇 fraunhofer cente...
  • 5 篇 machine learning...
  • 5 篇 computer vision ...
  • 4 篇 fraunhofer iosb ...
  • 4 篇 institute for co...
  • 4 篇 centre for visio...
  • 4 篇 division of medi...
  • 4 篇 lab of vision co...
  • 3 篇 christian dopple...
  • 3 篇 fraunhofer iosb ...
  • 3 篇 machine learning...
  • 3 篇 department of co...
  • 3 篇 interactive mach...
  • 3 篇 vision and fusio...
  • 3 篇 christian dopple...
  • 3 篇 christian dopple...
  • 2 篇 university of sc...
  • 2 篇 applied computer...
  • 2 篇 fraunhofer cente...
  • 2 篇 universidad pomp...

作者

  • 5 篇 zimmerer david
  • 5 篇 jürgen beyerer
  • 5 篇 bischof horst
  • 5 篇 lienhart rainer
  • 5 篇 possegger horst
  • 5 篇 isensee fabian
  • 5 篇 maier-hein klaus...
  • 4 篇 lin wei
  • 4 篇 zhu jihua
  • 4 篇 kozinski mateusz
  • 4 篇 jäger paul f.
  • 4 篇 carneiro gustavo
  • 4 篇 beyerer jürgen
  • 4 篇 li zhongyu
  • 3 篇 van gool luc
  • 3 篇 wolf stefan
  • 3 篇 timofte radu
  • 3 篇 horst possegger
  • 3 篇 horst bischof
  • 3 篇 wei lin

语言

  • 83 篇 英文
  • 1 篇 其他
检索条件"机构=Vision and Machine Learning Lab"
84 条 记 录,以下是1-10 订阅
排序:
Pseudo-label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation  33
Pseudo-Label Noise Suppression Techniques for Semi-Supervise...
收藏 引用
33rd British machine vision Conference Proceedings, BMVC 2022
作者: Scherer, Sebastian Schön, Robin Lienhart, Rainer University of Augsburg Machine Learning and Computer Vision Lab Augsburg Germany
Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is ve... 详细信息
来源: 评论
EVALUATING THE SEARCH PHASE OF NEURAL ARCHITECTURE SEARCH  8
EVALUATING THE SEARCH PHASE OF NEURAL ARCHITECTURE SEARCH
收藏 引用
8th International Conference on learning Representations, ICLR 2020
作者: Yu, Kaicheng Sciuto, Christian Jaggi, Martin Musat, Claudiu Salzmann, Mathieu Computer vision lab EPFL Switzerland Daskell Machine learning and optimization lab EPFL Switzerland Swisscom Digital Lab Switzerland
Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks. Existing techniques rely on two stages: searching over the architecture space and validating the best architecture. NAS al...
来源: 评论
Image congealing via efficient feature selection
Image congealing via efficient feature selection
收藏 引用
2012 IEEE Workshop on the Applications of Computer vision, WACV 2012
作者: Xue, Ya Liu, Xiaoming Machine Learning Lab GE Global Research United States Computer Vision Lab GE Global Research United States
Congealing for an image ensemble is a joint alignment process to rectify images in the spatial domain such that the aligned images are as similar to each other as possible. Fruitful congealing algorithms were applied ... 详细信息
来源: 评论
VidHarm: A Clip Based Dataset for Harmful Content Detection  26
VidHarm: A Clip Based Dataset for Harmful Content Detection
收藏 引用
26th International Conference on Pattern Recognition / 8th International Workshop on Image Mining - Theory and Applications (IMTA)
作者: Edstedt, Johan Berg, Amanda Felsberg, Michael Karlsson, Johan Benavente, Francisca Novak, Anette Pihlgren, Gustav Grund Linkoping Univ Comp Vision Lab Linkoping Sweden Statens Medierad Stockholm Sweden Lulea Univ Technol EISLAB Machine Learning Lulea Sweden
Automatically identifying harmful content in video is an important task with a wide range of applications. However, there is a lack of professionally labeled open datasets available. In this work VidHarm, an open data... 详细信息
来源: 评论
Connecting language and vision to actions  56
Connecting language and vision to actions
收藏 引用
56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
作者: Anderson, Peter Das, Abhishek Wu, Qi Australian National University Australian Centre for Robotic Vision Australia Georgia Tech Machine Learning and Perception Lab United States University of Adelaide Australian Centre for Robotic Vision Australia
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical o... 详细信息
来源: 评论
SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects  16th
SESAME: Semantic Editing of Scenes by Adding, Manipulating o...
收藏 引用
16th European Conference on Computer vision, ECCV 2020
作者: Ntavelis, Evangelos Romero, Andrés Kastanis, Iason Van Gool, Luc Timofte, Radu Computer Vision Lab ETH Zurich Zürich Switzerland Robotics and Machine Learning CSEM SA Alpnach Switzerland PSI ESAT KU Leuven Leuven Belgium
Recent advances in image generation gave rise to powerful tools for semantic image editing. However, existing approaches can either operate on a single image or require an abundance of additional information. They are... 详细信息
来源: 评论
Recognition of Freely Selected Keypoints on Human Limbs
arXiv
收藏 引用
arXiv 2022年
作者: Ludwig, Katja Kienzle, Daniel Lienhart, Rainer Machine Learning and Computer Vision Lab University of Augsburg Germany
Nearly all Human Pose Estimation (HPE) datasets consist of a fixed set of keypoints. Standard HPE models trained on such datasets can only detect these keypoints. If more points are desired, they have to be manually a... 详细信息
来源: 评论
Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers
arXiv
收藏 引用
arXiv 2022年
作者: Einfalt, Moritz Ludwig, Katja Lienhart, Rainer Machine Learning and Computer Vision Lab University of Augsburg Germany
The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting. While the uplifting methods themselves are rather efficient, the true computational comple... 详细信息
来源: 评论
Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Masks
arXiv
收藏 引用
arXiv 2022年
作者: Ludwig, Katja Kienzle, Daniel Lorenz, Julian Lienhart, Rainer Machine Learning and Computer Vision Lab University of Augsburg Germany
Analyses based on the body posture are crucial for top-class athletes in many sports disciplines. If at all, coaches label only the most important keypoints, since manual annotations are very costly. This paper propos... 详细信息
来源: 评论
EARP: Integration with Entity Attribute and Relation Path for Event Knowledge Graph Representation learning
EARP: Integration with Entity Attribute and Relation Path fo...
收藏 引用
International Joint Conference on Neural Networks (IJCNN)
作者: Xu, Ze Zhou, Hao He, Ting Wang, Huazhen Huaqiao Univ Coll Comp Sci & Technol Xiamen Peoples R China Fujian Prov Univ Key Lab Comp Vision & Machine Learning Huaqiao Univ Xiamen Peoples R China
Event knowledge graph (EKG) as a special case of knowledge graph (KG) can realize the goal of event prediction, and has been proved useful in medical diagnosis and intelligent recommendation. To successfully build an ... 详细信息
来源: 评论