Zobrazeno 1 - 10 of 72 pro vyhledávání: '"Benyong Liu"'
1
Toward Efficient Execution of Mainstream Deep Learning Frameworks on Mobile Devices: Architectural Implications
Autor: Benyong Liu, Tao Li, Rui Zhang, Yuting Dai, Rui Xue
Publikováno v: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 40:453-466
In recent years, continuous growing interests have been seen in bringing artificial intelligence capabilities to mobile devices. However, the related work still faces several issues, such as constrained computation and memory resources, power drain,
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::cdeb73e46bd819cf5fdb5c9dd0265eff
https://doi.org/10.1109/tcad.2020.3003233
Zobrazit plný text záznamu
3
Acceleration for proximal stochastic dual coordinate ascent algorithm in solving regularised loss minimisation with norm
Autor: Beibei Tan, Benyong Liu
Publikováno v: Electronics Letters. 54:315-317
An accelerated version of the proximal stochastic dual coordinate ascent (SDCA) algorithm in solving regularised loss minimisation with l 2 norm is presented, wherein a momentum is introduced and the strong theoretical guarantees of SDCA are shared.
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::47592fe01e7f0f6c90c6f6b3c73ca4ad
https://doi.org/10.1049/el.2017.4544
Zobrazit plný text záznamu
4
Forgery Detection and Tampering Localization of Double JPEG Compression Based on First Digit Features of DCT Coefficients and KNR
Autor: Hongli Liu, Benyong Liu
Publikováno v: 2018 2nd IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC).
A337 improved forgery detection and tampering localization method is proposed for double JPEG compression images based on first digit feature of discrete cosine transform (DCT) coefficients and kernel-based nonlinear representor (KNR). First, a to-be
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::74f5468cc1fae34df1789a5264f61f76
https://doi.org/10.1109/imcec.2018.8469354
Zobrazit plný text záznamu
5
Support Vector Machine Improvement with Kemel-Based Nonlinear Representor
Autor: Benyong Liu, Zhuang Xiong
Publikováno v: 2018 2nd IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC).
B334 introducing the idea of optimal feature representation in kernel-based nonlinear representor (KNR), the traditional support vector machine (SVM) is improved in this manuscript to a new version called KNR-SVM. Firstly, the $\boldsymbol{k}$ -means
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6dee38cd623482228696e51e78f44718
https://doi.org/10.1109/imcec.2018.8469496
Zobrazit plný text záznamu
6
Action Recognition Combining Trajectory Feature with KNR
Autor: Benyong Liu, Yang Hu
Publikováno v: 2018 2nd IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC).
D338 trajectory feature is combined with kernel-based nonlinear representor (KNR) for video-based human action recognition. Initially, feature points are filtered through the Shi-Tomasi discrimination criterion after uniform sampling. Then dense traj
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::803780dc350936e2b1cf3c786289c977
https://doi.org/10.1109/imcec.2018.8469609
Zobrazit plný text záznamu
7
Exploiting Dynamic Thermal Energy Harvesting for Reusing in Smartphone with Mobile Applications
Autor: Huixiang Chen, Yuting Dai, Tao Li, Mingcong Song, Benyong Liu
Publikováno v: ASPLOS
Recently, mobile applications have gradually become performance- and resource- intensive, which results in a massive battery power drain and high surface temperature, and further degrades the user experience. Thus, high power consumption and surface
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::904d981e3c5b5e2acfb06ed360743227
https://doi.org/10.1145/3173162.3173188
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje