Zobrazeno 1 - 10
of 70
pro vyhledávání: '"Ligu Zhu"'
Publikováno v:
Applied Sciences, Vol 13, Iss 18, p 10165 (2023)
Super-resolution in image and video processing has been a challenge in computer vision, with its progression creating substantial societal ramifications. More specifically, video super-resolution methodologies aim to restore spatial details while uph
Externí odkaz:
https://doaj.org/article/0177d98cd55e4362bb83f6b4aca68b08
Publikováno v:
Applied Sciences, Vol 13, Iss 7, p 4571 (2023)
Cross-modal retrieval aims to elucidate information fusion, imitate human learning, and advance the field. Although previous reviews have primarily focused on binary and real-value coding methods, there is a scarcity of techniques grounded in deep re
Externí odkaz:
https://doaj.org/article/f0423bb92d9e4d678c429ffdc18bfedc
Publikováno v:
Computers, Materials & Continua; 2024, Vol. 79 Issue 3, p3955-3975, 21p
A Cloud-Edge Collaborative Gaming Framework Using AI-Powered Foveated Rendering and Super Resolution
Publikováno v:
International Journal on Semantic Web and Information Systems. 19:1-19
Cloud gaming (CG) has gradually gained popularity. By leveling shared computing resources on the cloud, CG technology allows those without expensive hardware to enjoy AAA games using a low-end device. However, the bandwidth requirement for streaming
With the development of information technology, the speed and scope of dissemination have been greatly improved, the content of information directly affects the social order, and the mining of communication laws has become a hot issue. At present, th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5c3b2463cb966d68805e29b7de7525b
https://doi.org/10.21203/rs.3.rs-2763842/v1
https://doi.org/10.21203/rs.3.rs-2763842/v1
Publikováno v:
Electronics; Volume 12; Issue 1; Pages: 240
To accelerate the inference of machine-learning (ML) model serving, clusters of machines require the use of expensive hardware accelerators (e.g., GPUs) to reduce execution time. Advanced inference serving systems are needed to satisfy latency servic
Publikováno v:
2021 International Conference on Computer Information Science and Artificial Intelligence (CISAI).
Autor:
Ligu Zhu, Suping Wang
Publikováno v:
2021 IEEE 4th International Conference on Computer and Communication Engineering Technology (CCET).
Deep learning is based on the characteristics of the metadata information from input data to train and test data. It deals with high-dimensional and raw data. Through layer-by-layer stacking transformation, deep neural networks are trained, new rules
Publikováno v:
2021 International Conference on Communications, Information System and Computer Engineering (CISCE).
With the increasing number of deep learning models started to rely on the high computing throughput of GPUs, many institutes, such as universities, have invested a lot in purchasing GPU devices and servers and building data centers. However, providin
Publikováno v:
2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications( AEECA).
The deep learning model has a large number of parameters that need to be adjusted during the training process, so training a model that can perform well in object detection requires a large amount of valid data. And the accuracy and generalization ab