Xiaokai Luo

Nanjing University of Posts and Telecommunications

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Fei Wu

Nanjing University of Posts and Telecommunications

Zhiyong Wu

University of Hong Kong

Xiwei Dong

Jiujiang University

Qinghua Huang

Sun Yat-sen University

Xiao‐Yuan Jing

Wuhan University

Yimu Ji

Nanjing University of Posts and Telecommunications

Carlos Misael Madrid Padilla

Daren Wang

The Ohio State University

Oscar Hernán Madrid Padilla

University of California, Los Angeles

Zhi Zhang

Southwest Petroleum University

Cooperative Institutions

Nanjing University of Posts and Telecommunications

Nanjing University

Shanghai Research Center for Wireless Communications

Institute of High Performance Computing

Nanjing University of Science and Technology

Sun Yat-sen University

Tsinghua University

Wuhan University

State Key Laboratory of Software Engineering

Zhejiang Sci-Tech University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Modality Consistent Generative Adversarial Network for Cross-Modal Retrieval

Lecture notes in computer science (2019)

Zhiyong Wu Fei Wu Xiaokai Luo Xiwei Dong Cailing Wang

Discriminator

Modality (human–computer interaction)

Modalities

Discriminative model

10.1007/978-3-030-31726-3_1

Cite

Citations (0)

Modality-specific and shared generative adversarial network for cross-modal retrieval

Pattern Recognition (2020)

Fei Wu Xiao‐Yuan Jing Zhiyong Wu Yimu Ji Xiwei Dong

Modality (human–computer interaction)

Discriminative model

Feature (linguistics)

Benchmark (surveying)

Modalities

Similarity (geometry)

Feature Learning

10.1016/j.patcog.2020.107335

Cite

Citations (71)

Semantic Preserving Generative Adversarial Network For Cross-Modal Hashing

2022 IEEE International Conference on Image Processing (ICIP) (2021)

Fei Wu Xiaokai Luo Qinghua Huang Pengfei Wei Ying Sun

Cross-modal hashing has achieved significant progress in recent years. However, how to effectively learn more discriminative hash codes of each modality and simultaneous alleviate the loss of modality information is still a challenging problem. Focusing on this problem, in this paper, we propose a novel cross-modal hashing approach named Semantic Preserving Generative Adversarial Network (SPGAN). The overall network architecture consists of two sub-networks, i.e., a semantic preserving generative adversarial network module and a discriminative hashing module. The generator maps text features into the image feature space. And the discriminator judges whether the feature representations are real image features or generated image features. The adversarial learning process can effectively reduce modality difference and preserve information of the image modality as much as possible. The discriminative hashing module projects the real and generated image features into a Hamming space to obtain hash codes, and explores semantic similarities for enhancing the discriminant ability of hash codes. Experiments on two widely used datasets demonstrate that SPGAN can outperform state-of-the-art related works.

Discriminative model

Feature hashing

Hamming space

Semantic feature

Discriminator

Modality (human–computer interaction)

Feature (linguistics)

Feature vector

10.1109/icip42928.2021.9506623

Cite

Citations (0)

Dense ReLU Neural Networks for Temporal-spatial Model

arXiv (Cornell University) (2024)

Zhi Zhang Carlos Misael Madrid Padilla Xiaokai Luo Oscar Hernán Madrid Padilla Daren Wang

In this paper, we focus on fully connected deep neural networks utilizing the Rectified Linear Unit (ReLU) activation function for nonparametric estimation. We derive non-asymptotic bounds that lead to convergence rates, addressing both temporal and spatial dependence in the observed measurements. By accounting for dependencies across time and space, our models better reflect the complexities of real-world data, enhancing both predictive performance and theoretical robustness. We also tackle the curse of dimensionality by modeling the data on a manifold, exploring the intrinsic dimensionality of high-dimensional data. We broaden existing theoretical findings of temporal-spatial analysis by applying them to neural networks in more general contexts and demonstrate that our proof techniques are effective for models with short-range dependence. Our empirical simulations across various synthetic response functions underscore the superior performance of our method, outperforming established approaches in the existing literature. These findings provide valuable insights into the strong capabilities of dense neural networks for temporal-spatial modeling across a broad range of function classes.

10.48550/arxiv.2411.09961

Cite

Citations (0)