Results 11 to 20 of about 305,410 (295)
Long-Tailed Visual Recognition via Improved Cross-Window Self-Attention and TrivialAugment
IEEE Access, 2023 In the real world, large-scale image data sets usually present long-tailed distribution. When traditional visual recognition methods are applied to long-tail image data sets, problems such as model failure and sudden decline in recognition accuracy occur.
Ying Song, Mengxing Li, Bo Wang
doaj +1 more source
BPR: An Erasure Coding Batch Parallel Repair Approach in Distributed Storage Systems
IEEE Access, 2023 Today, Erasure Coding is one of the most significant techniques widely used in distributed systems because it can improve reliability for large amounts of data with low storage overhead.
Ying Song, Wenxuan Zhao, Bo Wang
doaj +1 more source
FACHS: Adaptive Hybrid Storage Strategy Based on File Access Characteristics
IEEE Access, 2023 With the widespread use of distributed systems and the development of big data technology, the storage redundancy, data availability and persistence of distributed systems have become a concern.
Ying Song, Qiang Zhang, Bo Wang
doaj +1 more source
LiteDEKR: End‐to‐end lite 2D human pose estimation network
IET Image Processing, 2023 The 2D human pose estimation plays an important role in human‐computer interaction and action recognition. Although the method based on high‐resolution network has superior performance, there is still room for improvement in terms of speed and ...
Xueqiang Lv +5 more
doaj +1 more source
A Long-Tailed Image Classification Method Based on Enhanced Contrastive Visual Language
Sensors, 2023 To solve the problem that the common long-tailed classification method does not use the semantic features of the original label text of the image, and the difference between the classification accuracy of most classes and minority classes are large, the ...
Ying Song, Mengxing Li, Bo Wang
doaj +1 more source
Study on Transmission Optimization for Hierarchical Federated Learning [PDF]
Jisuanji kexue, 2022 Compared with traditional machine learning,federated learning effectively solves the problems of user data privacy and security protection,but a large number of model exchanges between massive nodes and cloud servers will produce high communication costs.
ZOU Sai-lan, LI Zhuo, CHEN Xin
doaj +1 more source
Interactive website on information dissemination
TELKOMNIKA (Telecommunication Computing Electronics and Control), 2021 A school is an educational institution for imparting knowledge to children. In an age where information acquisition about a school is assuming astronomical heights, the need for cost-effective and efficient information transmission methods cannot be overemphasized; hence the use of the website of a school to disseminate information is advised.
Peter O. Sadiku +3 more
openaire +4 more sources
A study on the subject classification of the NBA match reports
MATEC Web of Conferences, 2018 In this paper, we study the task of template building in automatically generate NBA match reports from NBA live text. As a preliminary study, we collect and process the historical reports compiled by the editors and get different kinds of sentences.
Wang Zhe +3 more
doaj +1 more source
A Searching Method of Candidate Segmentation Point in SPRINT Classification
Journal of Electrical and Computer Engineering, 2016 SPRINT algorithm is a classical algorithm for building a decision tree that is a widely used method of data classification. However, the SPRINT algorithm has high computational cost in the calculation of attribute segmentation. In this paper, an improved
Zhihao Wang +4 more
doaj +1 more source
The Dissemination Model of Cultural Information Using Instagram
Khizanah al-Hikmah, 2021 Instagram is one of the social media that is used massively to disseminate information, particularly regarding cultural information. This paper describes a model for disseminating cultural information using social media Instagram.
Walda Khoiriyah +2 more
doaj +1 more source