Yi Gao

Yi Gao

A true master is an eternal student

Posts by Collection

portfolio

publications

Population and cultural disasters caused by sea level rise based on regression model

Published in Journal 1616, 2020

With the worsening environment, more people become EDPs since their homeland become inhabitable. Leaving the place they once called home, their rights may not be guaranteed. Meanwhile, their unique culture are also facing the edge of extinction. To determine the scope of the issue, we discuss the number of people at risk and specify the cultural loss. When predicting EDP population, we start by using the regression model to predict the trend of sea level rise due to the greenhouse effect and find out by 2120, the world’s average sea level will probably rise by 60mm. Considering the effect of greenhouse gas makes this model more persuasive than if we only use sea level data to predict. Then, we build a spherical cap model to resemble to geographical features of tropical islands. It greatly simplifies the complexity of island topography and extends our prospective from a few islands to the whole world. With the help of the spherical cap model, on conservative estimate, the current number of EDP is about 67 million; by 2050, the potential EDPs will reach 130 million and over 400,000 square kilometers of land will be submerged. In the aspect of culture, with island residents becoming refugees, the potential lost of religious rituals, folk stories, traditional techniques, intangible arts and unique languages lead to the huge loss of cultural heritage.

Recommended citation: Wang, J., Gao, Y., & Lin, H. (2020). Population and Cultural Disasters Caused by Sea Level Rise Based on Regression Model. Journal of Physics: Conference Series, 1616. https://iopscience.iop.org/article/10.1088/1742-6596/1616/1/012081

Semi-Supervised Land-Cover Mapping Based on Multimodal Fusion and Pseudo-Label

Published in pp. 4599-4602, 2022

Land-cover mapping is of great significance for remote sensing and earth observation. However, due to the high cost of label acquisition, how to use limited labeled samples and multimodal data to achieve large-scale and high-precision land-cover mapping is still a great challenge. In this paper, a multimodal fusion and pseudo-label based method is proposed for semi-supervised land-cover mapping (SLM). For the problem of domain incompatibility, we use strong data enhancement and multimodal fusion module to strengthen the generalization performance of the method from data level and model level respectively. For a large amount of unlabeled data, we combine the pseudo-label self-training technology and propose Fusion-Finetune-Fusion training strategy to achieve large-scale, high-precision land-cover mapping under semi-supervised conditions. In the track SLM of the 2022 Data Fusion Contest (DFC22-SLM), the proposed method achieves a mean intersection over union (mIoU) of 0.4962 in phase 2, ranking fourth place.

Recommended citation: Y. Gao, X. Ding and G. Yang, "Semi-Supervised Land-Cover Mapping Based on Multimodal Fusion and Pseudo-Label," IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, 2022, pp. 4599-4602, doi: 10.1109/IGARSS46834.2022.9884536. https://ieeexplore.ieee.org/document/9884536

Continuous Sign Language Recognition in Complex Background Based on Attention Mechanism

Published in Journal 69, 2022

In this work, an attention-based 3D convolutional neural network (ACN) is proposed for continuous sign language recognition in complex background. Firstly, the sign language video containing complex background is preprocessed with the background removal module. Then, the spatio-temporal fusion information is extracted by 3D-ResNet (3D residual convolutional neural network) based on spatial attention mechanism. Finally, the long short-term memory (LSTM) network combined with the time attention mechanism is used for sequence learning to obtain the final recognition result. Extensive experiments show that the algorithm performs well on the large-scale Chinese continuous sign language dataset CSL100. The algorithm shows good generalization performance facing different complex background, and the spatio-temporal attention mechanism introduced by the model is effective.

Recommended citation: YANG Guangyi, DING Xingyu, GAO Yi, et al. Continuous Sign Language Recognition in Complex Background Based on Attention Mechanism [J]. J Wuhan Univ (Nat Sci Ed), 2023, 69 (01): 1-9. DOI: 10. 14188/j. 1671-8836. 2021. 0350 (Ch) https://www.cnki.com.cn/Article/CJFDTOTAL-WHDY20221128002.htm

Residual Dense Swin Transformer for Continuous-Scale Super-Resolution Algorithm

Published in Journal 19, 2024

The single-image super-resolution task benefits has a wide range of application scenarios, so has long been a hotspot in the field of computer vision. However, designing a continuous-scale super-resolution algorithm with excellent performance is still a difficult problem to solve. In order to solve this problem, we propose a continuous-scale SR algorithm based on a Transformer, which is called residual dense Swin Transformer (RDST). Firstly, we design a residual dense Transformer block (RDTB) to enhance the information flow before and after the network and extract local fusion features. Then, we use multilevel feature fusion to obtain richer feature information. Finally, we use the upsampling module based on the local implicit image function (LIIF) to obtain continuous-scale super-resolution results. We test RDST on multiple benchmarks. The experimental results show that RDST achieves SOTA performance in the fixed scale of super-resolution tasks in the distribution, and significantly improves (0.1∼0.6 dB) the arbitrary scale of super-resolution tasks out of distribution. Sufficient experiments show that our RDST can use fewer parameters, and its performance is better than the SOTA SR method.

Recommended citation: Liu, J.; Gui, Z.; Yuan, C.; Yang, G.; Gao, Y. Residual Dense Swin Transformer for Continuous-Scale Super-Resolution Algorithm. Appl. Sci. 2024, 14, 3678. https://doi.org/10.3390/app14093678 https://www.mdpi.com/2076-3417/14/9/3678

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.