咨询与建议

限定检索结果

文献类型

  • 65 篇 期刊文献
  • 52 篇 会议

馆藏范围

  • 117 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 110 篇 工学
    • 92 篇 计算机科学与技术...
    • 56 篇 电气工程
    • 25 篇 软件工程
    • 22 篇 信息与通信工程
    • 6 篇 电子科学与技术(可...
    • 6 篇 控制科学与工程
    • 4 篇 测绘科学与技术
    • 2 篇 机械工程
    • 1 篇 水利工程
    • 1 篇 网络空间安全
  • 13 篇 医学
    • 12 篇 临床医学
    • 5 篇 基础医学(可授医学...
  • 9 篇 理学
    • 3 篇 地球物理学
    • 2 篇 数学
    • 2 篇 物理学
    • 1 篇 地理学
    • 1 篇 生物学
  • 6 篇 管理学
    • 4 篇 管理科学与工程(可...
    • 2 篇 图书情报与档案管...
  • 1 篇 教育学
    • 1 篇 体育学
  • 1 篇 文学
    • 1 篇 新闻传播学
  • 1 篇 农学
    • 1 篇 作物学

主题

  • 117 篇 text-to-image sy...
  • 37 篇 generative adver...
  • 16 篇 generative adver...
  • 13 篇 semantics
  • 12 篇 deep learning
  • 12 篇 task analysis
  • 12 篇 visualization
  • 12 篇 image synthesis
  • 12 篇 generators
  • 8 篇 generative adver...
  • 7 篇 gallium nitride
  • 7 篇 generative model...
  • 7 篇 attention mechan...
  • 6 篇 diffusion model
  • 6 篇 training
  • 6 篇 gan
  • 5 篇 image generation
  • 5 篇 computer vision
  • 5 篇 generative adver...
  • 4 篇 multimodal learn...

机构

  • 3 篇 beijing jiaotong...
  • 3 篇 univ trento dept...
  • 2 篇 east china univ ...
  • 2 篇 dalian univ tech...
  • 2 篇 multimedia univ ...
  • 2 篇 kings coll londo...
  • 2 篇 mawlana bhashani...
  • 2 篇 univ sci & techn...
  • 2 篇 hosei univ grad ...
  • 2 篇 peking univ inst...
  • 2 篇 chinese univ hon...
  • 2 篇 microsoft res as...
  • 2 篇 amer int univ ba...
  • 2 篇 beijing inst tec...
  • 2 篇 hefei univ techn...
  • 2 篇 dalian univ tech...
  • 2 篇 southwest univ s...
  • 2 篇 auckland univ te...
  • 2 篇 hosei univ
  • 2 篇 nanjing univ pos...

作者

  • 4 篇 zhou jinjia
  • 4 篇 zhang zhiqiang
  • 4 篇 wang tao
  • 4 篇 wang min
  • 4 篇 melgani farid
  • 4 篇 bejiga mesay bel...
  • 4 篇 yu wenxin
  • 4 篇 lang congyan
  • 4 篇 peng yuxin
  • 4 篇 feng songhe
  • 3 篇 li xin
  • 3 篇 jiang ning
  • 3 篇 yin baocai
  • 3 篇 tan hongchen
  • 3 篇 cheng jun
  • 3 篇 wu fuxiang
  • 3 篇 yuan mingkuan
  • 3 篇 liang liqian
  • 3 篇 zhang han
  • 3 篇 liu xiuping

语言

  • 117 篇 英文
检索条件"主题词=Text-to-Image Synthesis"
117 条 记 录,以下是111-120 订阅
排序:
Retro-Remote Sensing: Generating images From Ancient texts
收藏 引用
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2019年 第3期12卷 950-960页
作者: Bejiga, Mesay Belete Melgani, Farid Vascotto, Antonio Univ Trento Dept Comp Sci & Informat Engn I-38123 Trento Italy
The data available in the world come in various modalities, such as audio, text, image, and video. Each data modality has different statistical properties. Understanding each modality, individually, and the relationsh... 详细信息
来源: 评论
On Conditioning GANs to Hierarchical Ontologies
On Conditioning GANs to Hierarchical Ontologies
收藏 引用
30th International Conference on Database and Expert Systems Applications (DEXA)
作者: Eghbal-zadeh, Hamid Fischer, Lukas Hoch, Thomas Johannes Kepler Univ Linz LIT AI Lab Altenberger Str 69 Linz Austria Johannes Kepler Univ Linz Inst Computat Percept Altenberger Str 69 Linz Austria Software Competence Ctr Hagenberg GmbH SCCH Softwarepk 21 A-4232 Hagenberg Austria
The recent success of Generative Adversarial Networks (GAN) is a result of their ability to generate high quality images given samples from a latent space. One of the applications of GANs is to generate images from a ... 详细信息
来源: 评论
TOWARDS GENERATING REMOTE SENSING imageS OF THE FAR PAST  39
TOWARDS GENERATING REMOTE SENSING IMAGES OF THE FAR PAST
收藏 引用
IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
作者: Bejiga, Mesay Belete Melgani, Farid Univ Trento Dept Informat Engn & Comp Sci I-38123 Trento Italy
text-to-image synthesis is a research topic that has not yet been addressed by the remote sensing community. It consists in learning a mapping from text description to image pixels. In this paper, we propose to addres... 详细信息
来源: 评论
LAYOUT AND CONtext UNDERSTANDING FOR image synthesis WITH SCENE GRAPHS  26
LAYOUT AND CONTEXT UNDERSTANDING FOR IMAGE SYNTHESIS WITH SC...
收藏 引用
26th IEEE International Conference on image Processing (ICIP)
作者: Talavera, Arces Tan, Daniel Stanley Azcarraga, Arnulfo Hua, Kai-Lung Natl Taiwan Univ Sci & Technol Dept CSIE Taipei Taiwan De La Salle Univ Software Technol Dept Manila Philippines
Advancements on text-to-image synthesis generate remarkable images from textual descriptions. However, these methods are designed to generate only one object with varying attributes. They face difficulties with comple... 详细信息
来源: 评论
PororoGAN: An Improved Story Visualization Model on Pororo-SV Dataset  2019
PororoGAN: An Improved Story Visualization Model on Pororo-S...
收藏 引用
Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence
作者: Gangyan Zeng Zhaohui Li Yuan Zhang School of Information and Communication Engineering Communication University of China Beijing China School of Data Science and Media Intelligence Communication University of China Beijing China
Generating a sequence of images from a multi-sentence paragraph is a recently proposed task called Story-Visualization. In this task, how to keep the global consistency across dynamic scenes and characters in the stor... 详细信息
来源: 评论
Retro-Remote Sensing With Doc2Vec Encoding
Retro-Remote Sensing With Doc2Vec Encoding
收藏 引用
Geoscience and Remote Sensing Symposium (M2GARSS), Mediterranean and Middle-East
作者: Mesay Belete Bejiga Genc Hoxha Farid Melgani Department of Information Engineering and Computer Science University of Trento Trento Italy
In this work, we attempt to address the issue of developing a sophisticated text encoder for retro-remote sensing application. The encoder converts ancient landscape descriptions into a fixed-size vector that, adequat... 详细信息
来源: 评论
Photo Realistic Generation from Arabic text Description Based on Generative Adversarial Networks
收藏 引用
ACM Transactions on Asian and Low-Resource Language Information Processing 1000年
作者: Sara Maher Mathematics Mohamed Loey Department Faculty of Science Benha University Benha Egypt Computer Science Department Faculty of Computer and Artificial intelligence Benha University Benha Egypt
Generating accurate high-resolution images from text representations is a difficult problem in computer vision that has a wide range of functional applications. text-to-image conversion is not dissimilar to the diffic... 详细信息
来源: 评论