Zobrazeno 1 - 10 of 80 pro vyhledávání: '"Qiu Feng, Wang"'
1
Akademický článek
Eddy covariance-based differences in net ecosystem productivity values and spatial patterns between naturally regenerating forests and planted forests in China
Autor: Xian-Jin Zhu, Ren-Xue Fan, Zhi Chen, Qiu-Feng Wang, Gui-Rui Yu
Publikováno v: Scientific Reports, Vol 12, Iss 1, Pp 1-13 (2022)
Abstract Net ecosystem productivity (NEP), the difference between gross primary productivity (GPP) and ecosystem respiration (ER), is the basis of forest carbon sinks. Revealing NEP differences between naturally regenerating forests (NF) and planted
Externí odkaz: https://doaj.org/article/b1b0a104f62d4aab85c8557f398635d6
Zobrazit plný text záznamu
2
Akademický článek
Nonconvex matrix completion with Nesterov’s acceleration
Autor: Xiao-Bo Jin, Guo-Sen Xie, Qiu-Feng Wang, Guoqiang Zhong, Guang-Gang Geng
Publikováno v: Big Data Analytics, Vol 3, Iss 1, Pp 1-12 (2018)
Abstract Background In matrix completion fields, the traditional convex regularization may fall short of delivering reliable low-rank estimators with good prediction performance. Previous works use the alternation least squares algorithm to optimize
Externí odkaz: https://doaj.org/article/2b8f4efb893e4a128e85137e65a2d27c
Zobrazit plný text záznamu
3
Learngene: From Open-World to Your Learning Task
Autor: Qiu-Feng Wang, Xin Geng, Shu-Xia Lin, Shi-Yu Xia, Lei Qi, Ning Xu
Publikováno v: Proceedings of the AAAI Conference on Artificial Intelligence. 36:8557-8565
Although deep learning has made significant progress on fixed large-scale datasets, it typically encounters challenges regarding improperly detecting unknown/unseen classes in the open-world scenario, over-parametrized, and overfitting small samples.
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b10f7180043a3f2fd4f9d8f23178e58d
https://doi.org/10.1609/aaai.v36i8.20833
Zobrazit plný text záznamu
6
TextTriangle: An end-to-end textspotter with piecewise linear alignment
Autor: Hui Xu, Qiu-Feng Wang, Zhenghao Li, Yu Shi, Xiang-Dong Zhou
Scene text detection and recognition has attracted increasing research attention recently, especially for text of arbitrary shapes. In most of text spotting methods, text feature alignment is a key component to connect the detector and recognizer for
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::221bfd6a409da1867be0f74054333998
https://doi.org/10.21203/rs.3.rs-1743583/v1
Zobrazit plný text záznamu
7
Residual attention-based multi-scale script identification in scene text images
Autor: Shan Huang, Mengkai Ma, Qiu-Feng Wang, Kaizhu Huang, Shen Huang, Yannis Goulermas
Publikováno v: Neurocomputing. 421:222-233
Script identification is an essential step in the text extraction pipeline for multi-lingual application. This paper presents an effective approach to identify scripts in scene text images. Due to the complicated background, various text styles, char
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::592130f0e36a583622cbfa8bac66e95d
https://doi.org/10.1016/j.neucom.2020.09.015
Zobrazit plný text záznamu
9
Improving deep neural network performance by integrating kernelized Min-Max objective
Autor: Qiu-Feng Wang, Amir Hussain, Kai Yao, Kaizhu Huang, Rui Zhang
Publikováno v: Neurocomputing. 408:82-90
Deep neural networks (DNN), such as convolutional neural networks (CNN) have been widely used for object recognition. However, they are usually unable to ensure the required intra-class compactness and inter-class separability in the kernel space. Th
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::88a5bacd0a22a08dc4f2f25ae76432fb
https://doi.org/10.1016/j.neucom.2019.08.101
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje