Zobrazeno 1 - 10
of 90
pro vyhledávání: '"Guo, Peiyao"'
Image coding for multi-task applications, catering to both human perception and machine vision, has been extensively investigated. Existing methods often rely on multiple task-specific encoder-decoder pairs, leading to high overhead of parameter and
Externí odkaz:
http://arxiv.org/abs/2409.19660
Autor:
Guo, Peiyao1 (AUTHOR), Yin, Zhichao2 (AUTHOR) yzc@cueb.edu.cn, Zhu, Hengbo1 (AUTHOR), Gou, Ke1 (AUTHOR)
Publikováno v:
Emerging Markets Finance & Trade. 2024, Vol. 60 Issue 12, p2703-2718. 16p.
Publikováno v:
In International Journal of Electrical Power and Energy Systems November 2024 162
A Transformer-based Image Compression (TIC) approach is developed which reuses the canonical variational autoencoder (VAE) architecture with paired main and hyper encoder-decoders. Both main and hyper encoders are comprised of a sequence of neural tr
Externí odkaz:
http://arxiv.org/abs/2111.06707
Publikováno v:
In Heliyon 30 April 2024 10(8)
Publikováno v:
In Journal of Non-Crystalline Solids 15 March 2024 628
Autor:
Guo, Peiyao1 (AUTHOR) peiyaoguo126@126.com, Luo, Dekun1 (AUTHOR) 2207301092@st.gxu.edu.cn, Wu, Yizhen1 (AUTHOR) 2107301146@st.gxu.edu.cn, He, Sheng1 (AUTHOR) hscestlavie@163.com, Deng, Jianyu1 (AUTHOR) ddjy2000@gmail.com, Yao, Huilu2 (AUTHOR) yhl@gxu.edu.cn, Sun, Wenhong1,3,4 (AUTHOR) youzi7002@gxu.edu.cn, Zhang, Jicai5 (AUTHOR) jczhang@mail.buct.edu.cn
Publikováno v:
Sensors (14248220). Jun2024, Vol. 24 Issue 11, p3418. 24p.
Publikováno v:
IEEE Transactions on Image Processing, vol. 30, pp. 3179-3191, 2021
This paper proposes a novel Non-Local Attention Optimized Deep Image Compression (NLAIC) framework, which is built on top of the popular variational auto-encoder (VAE) structure. Our NLAIC framework embeds non-local operations in the encoders and dec
Externí odkaz:
http://arxiv.org/abs/1904.09757
A deep image compression scheme is proposed in this paper, offering the state-of-the-art compression efficiency, against the traditional JPEG, JPEG2000, BPG and those popular learning based methodologies. This is achieved by a novel conditional proba
Externí odkaz:
http://arxiv.org/abs/1902.10480
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.