Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    Text to Image Generation with Conformer-GAN

    Text-to-image generation (T2I) has been a popular research field in recent years, and its goal is to generate corresponding photorealistic images through natural language text descriptions. Existing T2I models...

    Zhiyu Deng, Wenxin Yu, Lu Che, Shiyu Chen, Zhiqiang Zhang in Neural Information Processing (2024)

  2. No Access

    Chapter and Conference Paper

    Text-to-Image Synthesis with Threshold-Equipped Matching-Aware GAN

    In this paper, we propose a novel Equipped with Threshold Matching-Aware Generative Adversarial Network (ETMA-GAN) for text-to-image synthesis. By filtering inaccurate negative samples, the discriminator can m...

    Jun Shang, Wenxin Yu, Lu Che, Zhiqiang Zhang, Hongjie Cai in Neural Information Processing (2024)

  3. No Access

    Chapter and Conference Paper

    Depth Normalized Stable View Synthesis

    Novel view synthesis (NVS) aims to synthesize photo-realistic images depicting a scene by utilizing existing source images. The synthesized images are supposed to be as close as possible to the scene content. ...

    **aodi Wu, Zhiqiang Zhang, Wenxin Yu, Shiyu Chen in Neural Information Processing (2024)

  4. No Access

    Chapter and Conference Paper

    Multi-view Consistency View Synthesis

    Novel view synthesis (NVS) aims to synthesize photo-realistic images depicting a scene by utilizing existing source images. The core objective is that the synthesized images are supposed to be as close as poss...

    **aodi Wu, Zhiqiang Zhang, Wenxin Yu, Shiyu Chen in Neural Information Processing (2024)

  5. No Access

    Chapter and Conference Paper

    FPD: Feature Pyramid Knowledge Distillation

    Knowledge distillation is a commonly used method for model compression, aims to compress a powerful yet cumbersome model into a lightweight model without much sacrifice of performance, giving the accuracy of a...

    Qi Wang, Lu Liu, Wenxin Yu, Zhiqiang Zhang, Yuxin Liu in Neural Information Processing (2023)

  6. No Access

    Chapter and Conference Paper

    Analysis of Swelling Shrinkage Cracks Development Effects in Improved Expansive Soil Using Image Processing Technology

    To study the development characteristic of the improved expansive soil fissure and its effect on the shear strength, the image processing technology is used to make a quantitative analysis on the surface of th...

    Cheng Chen, Jian-fei Liu, Jun Gong in Advances in Urban Geotechnical Engineering (2021)

  7. No Access

    Chapter and Conference Paper

    Analysis on the Influence of Rainfall Characteristics on the Stability of Granite Residual Soil Slope

    Rainfall characteristics have important impacts on slope stability. Aimed to analyze the influence of rainfall on granite residual soil slope stability. The finite element method is used for the calculation of...

    Cheng Chen, Jian-fei Liu, Jun Gong in Advancements in Geotechnical Engineering (2021)

  8. No Access

    Chapter and Conference Paper

    Progressive Inpainting Strategy with Partial Convolutions Generative Networks (PPCGN)

    Recently, there have been great advances in many one-stage image inpainting methods. They may have a slight advantage in computation time but lack sufficient context information for inpainting. These inpaintin...

    Liang Nie, Wenxin Yu, Siyuan Li, Zhiqiang Zhang in Neural Information Processing (2021)

  9. No Access

    Chapter and Conference Paper

    Deep Learning Based Placement Acceleration for 3D-ICs

    Placement plays an essential role in the very-large-scale integrated (VLSI) circuits physical design automation. But, it is a time-consuming step in the VLSI design stages. In this paper, we proposes algorithm...

    Wenxin Yu, **n Cheng, Zhiqiang Zhang, Jun Gong in Neural Information Processing (2021)

  10. No Access

    Chapter and Conference Paper

    QS-Hyper: A Quality-Sensitive Hyper Network for the No-Reference Image Quality Assessment

    Blind/no-reference image quality assessment (IQA) aims to provide a quality score for a single image without references. In this context, deep learning models can capture various image artifacts, which made si...

    Xuewen Zhang, Yunye Zhang, Wenxin Yu, Liang Nie in Neural Information Processing (2021)

  11. No Access

    Chapter and Conference Paper

    SCAN: Spatial and Channel Attention Normalization for Image Inpainting

    Image inpainting focuses on predicting contents with shape structure and consistent details in damaged regions. Recent approaches based on convolutional neural network (CNN) have shown promising results via ad...

    Shiyu Chen, Wenxin Yu, Liang Nie, Xuewen Zhang, Siyuan Li in Neural Information Processing (2021)

  12. No Access

    Chapter and Conference Paper

    Semi-supervised Learning with Conditional GANs for Blind Generated Image Quality Assessment

    Evaluating the quality of images generated by generative adversarial networks (GANs) is still an open problem. Metrics such as Inception Score(IS) and Fréchet Inception Distance (FID) are limited in evaluating...

    Xuewen Zhang, Yunye Zhang, Wenxin Yu, Liang Nie in Neural Information Processing (2021)

  13. No Access

    Chapter and Conference Paper

    Free-Form Image Inpainting with Separable Gate Encoder-Decoder Network

    Image inpainting refers to the process of reconstructing damaged areas of an image. For image inpainting, there are many means to generate not too bad inpainting results today. However, these methods either ma...

    Liang Nie, Wenxin Yu, Xuewen Zhang, Siyuan Li, Shiyu Chen in Neural Information Processing (2021)

  14. No Access

    Chapter and Conference Paper

    An FPGA Implementation of Rapid Switch Module for EtherCAT Slave Controller

    In this paper. We use FPGA to achieve high-performance cycle times for EtherCAT Slave Controller (ESC) internal data switch between ports. Commonly, ESC is implemented by a dedicated chip. Using FPGA to implem...

    Jun Gong, Yong Zhou, Senlin Luo in Advances in Natural Computation, Fuzzy Sys… (2021)

  15. No Access

    Chapter and Conference Paper

    Transformer with Prior Language Knowledge for Image Captioning

    The Transformer architecture represents state-of-the-art in image captioning tasks. However, even the transformer uses positional encodings to encode sentences, its performance still not good enough in grammar...

    Daisong Yan, Wenxin Yu, Zhiqiang Zhang, Jun Gong in Neural Information Processing (2021)

  16. No Access

    Chapter and Conference Paper

    A New Workforce Cross-Training Policy for a U-shaped Assembly Line

    This study addresses a U-shaped assembly line staffed by partially cross-trained workers with skill chaining. When a worker is absent, the performance of the production system must become worse. Cross-trained ...

    Jun Gong, Lijie Wang, Sen Zhang in Information and Management Engineering (2011)