Search

Your search keyword '"Yang, Lifang"' showing total 37 results
Start Over Author "Yang, Lifang" Publisher ieee
37 results on '"Yang, Lifang"'

6. Hybrid Transformer-CNN for Real Image Denoising.

Author

Zhao, Mo, Cao, Gang, Huang, Xianglin, and Yang, Lifang

Subjects
IMAGE denoising, RADIAL basis functions, CONVOLUTIONAL neural networks, COMPUTATIONAL complexity
Abstract

Transformer typically enjoys larger model capacity but higher computational loads than convolutional neural network (CNN) in vision tasks. In this letter, the advantages of such two networks are fused for achieving effective and efficient real image denoising. We propose a hybrid denoising model based on Transformer Encoder and Convolutional Decoder Network (TECDNet). The Transformer based on novel radial basis function (RBF) attention is used as encoder to improve the representation capability of overall model. In decoder, the residual CNN instead of Transformer is adopted to greatly reduce computational complexity of the whole denoising network. Extensive experimental results on real images show that TECDNet achieves the state-of-the-art denosing performance with relatively low computational cost. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

19. A Relevance Feedback System for CBIR with Long-Term Learning

Author

Huang Xianglin, Liu Min, Yang Lifang, and Lu Hui

Subjects
business.industry, Computer science, Feature extraction, Relevance feedback, Semantics, Machine learning, computer.software_genre, Content-based image retrieval, Support vector machine, Genetic algorithm, Table (database), Artificial intelligence, business, computer, Image retrieval
Abstract

Relevance feedback has been developed to improve retrieval performance effectively in Content Based Image Retrieval (CBIR). This paper introduces a relevance feedback system for CBIR with both short-term relevance feedback and long-term learning. In short-term relevance feedback, query reweighting algorithm, support vector machines (SVM), and genetic algorithm are adopted. In long-term learning, the expanded-judging model with index table is used for analyzing the historical log data. Experimental results show that among short-term feedback algorithms, the SVM gets the best feedback results, and for the use of our proposed expanded-judging model in long-term learning, the recall of the retrieval system is improved more than 30% in average.

Published
2010

20. Research and design of testing device of hand operating capacity

Author

Yang Lifang and Liu Jia

Subjects
Set (abstract data type), Engineering, Engineering drawing, Hand function, business.industry, Human factors and ergonomics, business, Tool design
Abstract

The ability of hand operation is an important part of ergonomics. The evaluation of hand works is theoretically and practically important to both the evaluation of human hands potential and ergonomically design of tools. The research is based on the theory of anthropometry and ergonomics, a set of device of hand operating capacity is designed through research of basic method and step of hand operating capacity. The method and discipline of hand function measurement are explored through the device of hand capacity evaluation.

Published
2009

21. The analysis and research on the factors of sound annoyance in the operating environment

Author

Gu Yaqi, Yang Lifang, Zhu Lei, and Zhang Rui

Subjects
geography, Engineering, geography.geographical_feature_category, Noise measurement, Noise pollution, business.industry, Acoustics, Speech recognition, Ambient noise level, Annoyance, Sound annoyance, Background noise, Noise, business, Sound (geography)
Abstract

A-weighted level is the main method to evaluate the noise. The method of noise evaluation has some drawbacks because it can not include all kinds of sound and all factors which affects the work efficiency of operators. The sound includes music and song, language, the nature sound and noise, which have different effect on the work efficiency of operators. The factors effecting human annoyance include the kind of sound, special sound, A-weighted level, the different operating environment, the sound relationship with operators and so on. In the paper, the sound factors effecting human annoyance would be found and analyzed and their validity would be analyzed through some examples. Through these factors and their weights, the value of annoyance on some noise can be got which can be used to control the sound of operating environment and improve the work efficiency of operators

Published
2006

Catalog

Books, media, physical & digital resources
See catalog results