咨询与建议

限定检索结果

文献类型

  • 3 篇 会议
  • 2 篇 期刊文献

馆藏范围

  • 5 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 5 篇 工学
    • 3 篇 信息与通信工程
    • 3 篇 计算机科学与技术...
    • 1 篇 电气工程
  • 2 篇 医学
    • 2 篇 临床医学
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 5 篇 generative image...
  • 2 篇 learned image co...
  • 2 篇 image compressio...
  • 1 篇 progressive comp...
  • 1 篇 ai
  • 1 篇 deep image compr...
  • 1 篇 learning based c...
  • 1 篇 cnn
  • 1 篇 invertible trans...
  • 1 篇 stylegan
  • 1 篇 image semantics
  • 1 篇 machine learning
  • 1 篇 neural network
  • 1 篇 display testing
  • 1 篇 video compressio...
  • 1 篇 gan

机构

  • 2 篇 harbin inst tech...
  • 1 篇 purple mt labs p...
  • 1 篇 dept of electric...
  • 1 篇 xiamen univ sch ...
  • 1 篇 jingce electroni...
  • 1 篇 interdigital inc...
  • 1 篇 southeast univ s...
  • 1 篇 heriot watt univ...

作者

  • 2 篇 bai yuanchao
  • 2 篇 jiang junjun
  • 2 篇 liu xianming
  • 1 篇 wei qingbin
  • 1 篇 mota joao f. c.
  • 1 篇 wang kai
  • 1 篇 hao tang
  • 1 篇 shukor mustafa
  • 1 篇 hellier pierre
  • 1 篇 jiakun liu
  • 1 篇 hong xuemin
  • 1 篇 zhai deming
  • 1 篇 damodaran bharat...
  • 1 篇 lei zhongyue
  • 1 篇 zhang feilong
  • 1 篇 duan peng
  • 1 篇 li daxin
  • 1 篇 yao xu
  • 1 篇 gang xu
  • 1 篇 shi jianghong

语言

  • 5 篇 英文
检索条件"主题词=Generative Image Compression"
5 条 记 录,以下是1-10 订阅
排序:
Progressive Deep image compression for Hybrid Contexts of image Classification and Reconstruction
收藏 引用
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2023年 第1期41卷 72-89页
作者: Lei, Zhongyue Duan, Peng Hong, Xuemin Mota, Joao F. C. Shi, Jianghong Wang, Cheng-Xiang Xiamen Univ Sch Informat Xiamen 361000 Peoples R China Heriot Watt Univ Sch Engn & Phys Sci Edinburgh EH14 4AS Midlothian Scotland Southeast Univ Sch Informat Sci & Engn Natl Mobile Commun Res Lab Nanjing 210096 Jiangsu Peoples R China Purple Mt Labs Nanjing 211111 Peoples R China
Progressive deep image compression (DIC) with hybrid contexts is an under-investigated problem that aims to jointly maximize the utility of a compressed image for multiple contexts or tasks under variable rates. In th... 详细信息
来源: 评论
Enhancing Privacy-Utility Tradeoff with Few-Round Strategy in Heterogeneous Federated Learning
Enhancing Privacy-Utility Tradeoff with Few-Round Strategy i...
收藏 引用
2024 Conference on Visual Communications and image Processing
作者: Wei, Qingbin Zhang, Feilong Bai, Yuanchao Zhai, Deming Jiang, Junjun Liu, Xianming Harbin Inst Technol Fac Comp Harbin Peoples R China
Federated learning inherently provides a certain level of privacy protection, which however is often inadequate in many real-world scenarios. Existing privacy-preserving methods frequently incur unbearable time overhe... 详细信息
来源: 评论
Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural image compression
Semantic Ensemble Loss and Latent Refinement for High-Fideli...
收藏 引用
2024 Conference on Visual Communications and image Processing
作者: Li, Daxin Bai, Yuanchao Wang, Kai Jiang, Junjun Liu, Xianming Harbin Inst Technol Fac Comp Harbin Peoples R China
Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements. However, at low bit-rates, these methods can introduce visually displeasing artifacts, such as blurring, co... 详细信息
来源: 评论
Video Coding using Learned Latent GAN compression  22
Video Coding using Learned Latent GAN Compression
收藏 引用
30th ACM International Conference on Multimedia (MM)
作者: Shukor, Mustafa Damodaran, Bharath Bhushan Yao, Xu Hellier, Pierre InterDigital Inc Rennes France
We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame i... 详细信息
来源: 评论
72-2: A Proposal for image-compression Algorithm for Display Test images
收藏 引用
SID Symposium Digest of Technical Papers 2022年 第1期53卷
作者: Hao Tang Jiakun Liu Gang Xu Jingce Electronic USA San Jose CA USA Dept of Electrical Engineering and Computer Sciences Univ. of California at Berkeley USA
A generative image compression algorithm is applied to display test images to reduce the need for storage spaces. The preliminary result showed better preservation of image details at roughly equal compression rate.
来源: 评论