Xiaofeng Xu

Anhui Polytechnic University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Damian Rouson

Lawrence Berkeley National Laboratory

Xianglin Bao

Anhui Polytechnic University

Li Xiong

Emory University

Joon Sang Lee

Yonsei University

Jim Xia

IBM (United States)

Ruiheng Zhang

Beijing Institute of Technology

Richard H. Pletcher

Iowa State University

Ivor W. Tsang

University of Technology Sydney

Jinfei Liu

Zhejiang University

Chuancai Liu

Nanjing University of Science and Technology

Cooperative Institutions

Chinese Academy of Sciences

Huazhong University of Science and Technology

Wuhan National Laboratory for Optoelectronics

Shanghai Jiao Tong University

Nanjing University of Science and Technology

Anhui Polytechnic University

Zhejiang University

University of Chinese Academy of Sciences

University of Science and Technology of China

Tsinghua University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

The Comparison of the Petty Bourgeoisie Image of Women in Mao Dun and Ding Ling's Works

Journal of Hengyang Normal University (2009)

Xiaofeng Xu

Mao Dun and Ding Ling described the petty bourgeois image of women as a creative center in their early works.The women have a distinct sense of individual liberation and strong tragic because of specific social background of the times.Because the writer's own gender and life experiences are different,the women's choice of the path and love and sex are also different in their works.This fit and differences have revealed a difficult course of the liberation of Chinese women.

Petite bourgeoisie

Source

Cite

Citations (0)

End-to-End Supervised Zero-Shot Learning with Meta-Learning Strategy

2020 7th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS) (2021)

Xiaofeng Xu Xianglin Bao Ruiheng Zhang Xingyu Lu

Zero-shot learning (ZSL) is a challenging but practical task in the computer vision field. ZSL tries to recognize new unknown categories by provided with training data from other known categories. Recently, the ZSL problem can be solved in a supervised learning way by using deep generative models to synthesize data as the training data for unknown categories. In this work, we design an end-to-end supervised ZSL method in which the data generation network and the object classification network are trained jointly. To enhance the generalization performance of the proposed supervised ZSL method, meta-learning strategy is introduced to mitigate the domain shift problem between the synthesized data and the real data of unknown categories. Experimental results on ZSL standard datasets demonstrate the significant superiority of the end-to-end strategy and the meta-learning strategy for the proposed model in ZSL tasks.

End-to-end principle

Supervised Learning

Training set

Labeled data

10.1109/iccss53909.2021.9721968

Cite

Citations (1)

A Tunable Multi-Port Fano Resonator Based on Mach-Zehnder Interferometers Coupling with Micro-Ring Resonators

Photonics (2022)

Yingjie Xu Lidan Lu Guang Chen Jie Liao Xiaofeng Xu

Fano resonance has an asymmetric and sharp resonance peak near the resonance wavelength, which can effectively enhance the all-optical signal processing capability and realize silicon photonic switches, sensors, and modulators. In this paper, a silicon photonic Fano resonator with Mach-Zehnder interferometer (MZI) structure coupling with micro-ring resonators (MRR) is designed. Two MRRs with different quality factors are coupled with two arms of an MZI, and the coupling zone is composed of two half-ring waveguides. Based on the transfer matrix method, the intrinsic and modulated transfer characteristics of the component are analyzed. By adjusting the optical amplitude and phase of MZIs and tuning the resonance wavelength of two MRRs, Fano resonance spectra are simulated at four output ports with the highest extinction ratios of 56.19 dB and maximum slope rates at 2175.74 dB/nm, and the transmission spectra of Fano resonance at the four output ports are experimentally demonstrated. As the four Fano resonance ports of the designed component have different performances, they can be used for various functions simultaneously. The advantage of the proposed scheme is the improvement of the multiplexing capacity and simultaneous utilization of the muti-port for the Fano resonator. Our four-port Fano resonator can be employed in the fields of optical switching, optical computing, and optical interconnect in the future.

Fano resonance

10.3390/photonics9100725

Cite

Citations (5)

[Protocol optimization and quality control of large-scale acupuncture clinical trial for infertility].

PubMed (2017)

Yingying Deng Jingshu Gao Hongli Ma Wang Rong Chen Xiu-hua

The design of research protocol and quality control are the key to ensure the quality of clinical trial. A randomized clinical trial regarding the effects of medication combined with acupuncture on live birth rate in polycystic ovary syndrome (PCOS), which was initially designed as a comparative effectiveness research, then added with an acupuncture control group and finally became a factorial analysis, is taken as an example to explain the protocol design and optimization process, demonstrating the high level of methodology design and international recognization. By a series of measurements, such as unified purchase of acupuncture equipment, multiple trainings and assessments for acupuncturists' knowledge and operation standardization, in-site supervision of local center experts, the standard operation of acupuncture could be ensured and the credibility and scientificity of research results could be improved.

Research Design

10.13703/j.0255-2930.2017.05.023

Cite

Citations (1)

Gas mask wearing detection based on Faster R-CNN

Journal of Ambient Intelligence and Smart Environments (2023)

Bangrong Wang Jun Wang Xiaofeng Xu Xianglin Bao

Gas masks are essential respiratory protective equipment commonly used by laborers who work in harsh environments. However, respiratory diseases and accidents can occur due to the absence of gas masks. To prevent these accidents, this paper developed an object detector that uses convolutional neural networks (CNNs) to detect whether workers are wearing gas masks. To achieve this goal, a gas mask detection dataset was constructed derived from real industrial scenarios and Faster R-CNN was improved for gas mask wearing detection. Firstly, to address the multi-scale problem in real scenes, the Feature Pyramid Network was introduced into Faster R-CNN to effectively fuse features between different levels and improve the detection ability of small objects. Secondly, the Online Hard Sample Mining algorithm was used to alleviate the class imbalance problems in the dataset. Finally, Mixup and Mosaic were used in the training process to augment the data and make the model better adapt to different scenes and complex backgrounds. After multiple experiments, the combination of the three optimization strategies improved the mAP 0.5 : 0.95 by 23.2%. This work is an initial attempt at gas mask wearing detection and there is still much room for improvement in terms of model and dataset.

Fuse (electrical)

Pyramid (geometry)

Feature (linguistics)

10.3233/ais-220460

Cite

Citations (0)

DPHMM: Customizable Data Release with Differential Privacy via Hidden Markov Model

arXiv (Cornell University) (2016)

Yonghui Xiao Yilin Shen Jinfei Liu Li Xiong Hongxia Jin

Hidden Markov model (HMM) has been well studied and extensively used. In this paper, we present DPHMM ({Differentially Private Hidden Markov Model}), an HMM embedded with a private data release mechanism, in which the privacy of the data is protected through a graph. Specifically, we treat every state in Markov model as a node, and use a graph to represent the privacy policy, in which "indistinguishability" between states is denoted by edges between nodes. Due to the temporal correlations in Markov model, we show that the graph may be reduced to a subgraph with disconnected nodes, which become unprotected and might be exposed. To detect such privacy risk, we define sensitivity hull and degree of protection based on the graph to capture the condition of information exposure. Then to tackle the detected exposure, we study how to build an optimal graph based on the existing graph. We also implement and evaluate the DPHMM on real-world datasets, showing that privacy and utility can be better tuned with customized policy graph.

Differential Privacy

Information sensitivity

10.48550/arxiv.1609.09172

Cite

Citations (7)

Block-based conditional entropy coding for medical image compression

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (2003)

Sriperumbudur V. Bharath Kumar Nithin Nagaraj Sudipta Mukhopadhyay Xiaofeng Xu

In this paper, we propose a block-based conditional entropy coding scheme for medical image compression using the 2-D integer Haar wavelet transform. The main motivation to pursue conditional entropy coding is that the first-order conditional entropy is always theoretically lesser than the first and second-order entropies. We propose a sub-optimal scan order and an optimum block size to perform conditional entropy coding for various modalities. We also propose that a similar scheme can be used to obtain a sub-optimal scan order and an optimum block size for other wavelets. The proposed approach is motivated by a desire to perform better than JPEG2000 in terms of compression ratio. We hint towards developing a block-based conditional entropy coder, which has the potential to perform better than JPEG2000. Though we don't indicate a method to achieve the first-order conditional entropy coder, the use of conditional adaptive arithmetic coder would achieve arbitrarily close to the theoretical conditional entropy. All the results in this paper are based on the medical image data set of various bit-depths and various modalities.

Conditional entropy

Arithmetic coding

JPEG 2000

Tunstall coding

10.1117/12.480466

Cite

Citations (2)

ABNT: Attention Binary Navigation Tree for Fine-Grained Visual Classification

2022 International Joint Conference on Neural Networks (IJCNN) (2024)

Boyu Ding Xiaofeng Xu Xianglin Bao Nan Yan Ruiheng Zhang

Tree (set theory)

Local Binary Patterns

10.1109/ijcnn60899.2024.10650181

Cite

Citations (0)

Battlefield of Life and Death: Another Interpretation of Xiao Hong's Little Woman Psychology

Journal of Chenzhou Teachers College (2005)

Xiaofeng Xu

In Battlefield of Life and Death, Xiao Hong pays, with her female intuitive feelings and her unique rational thought, her attention to the life courses of the female characters in her works, re-examines the significance and value of life and death. Her little woman psychology finds its strong expressions in Battlefield of Life and Death and the formation of such psychology has its deep-rooted causes.

Battlefield

Value of life

Value (mathematics)

Source

Cite

Citations (0)

Dynamic Memory De-allocation in Fortran 95/2003 Derived Type Calculus

Scientific Programming (2005)

Damian Rouson Karla Morris Xiaofeng Xu

Abstract data types developed for computational science and engineering are frequently modeled after physical objects whose state variables must satisfy governing differential equations. Generalizing the associated algebraic and differential operators to operate on the abstract data types facilitates high‐level program constructs that mimic standard mathematical notation. For non‐trivial expressions, multiple object instantiations must occur to hold intermediate results during the expression′s evaluation. When the dimension of each object′s state space is not specified at compile‐time, the programmer becomes responsible for dynamically allocating and de‐allocating memory for each instantiation. With the advent of allocatable components in Fortran 2003 derived types, the potential exists for these intermediate results to occupy a substantial fraction of a program′s footprint in memory. This issue becomes particularly acute at the highest levels of abstraction where coarse‐grained data structures predominate. This paper proposes a set of rules for de‐allocating memory that has been dynamically allocated for intermediate results in derived type calculus, while distinguishing that memory from more persistent objects. The new rules are applied to the design of a polymorphic time integrator for integrating evolution equations governing dynamical systems. Associated issues of efficiency and design robustness are discussed.

Memory footprint

Programmer

Fortran

Abstract data type

Data type

10.1155/2005/702048

Cite

Citations (9)