Lan Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lan Yao has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Feng Zeng
Central South University
9 shared publications - Dong-Hui Li
South China Normal University
2 shared publications - Feng Zeng
Hunan International Economics University
2 shared publications Baoling Wu
School of Computer Science and Engineering Central South University Changsha China
1 shared publication- Chao-Hsien Chu
The Pennsylvania State University
1 shared publication Feng Zeng
School of Software, Central South University, Changsha 410083, China
1 shared publication
Latest Publications
- 1 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (1) , 91-104
A Lightweight Model for Fast and Detail-Preserving Human Segmentation in Video
With the rapid development of artificial intelligence, human segmentation in video is becoming increasingly important in the field of computer vision. However, existing segmentation models suffer from inaccurate segmentation, slow processing, and large model size that limit their deployment on resource-constrained devices. To this end, we propose a lightweight model called Efficient Memory Aggregation U-shaped Network (EMAUnet) for human segmentation in video, which is based on a traditional U-shaped network and attention mechanism. In EMAUnet, memory modules are combined with segmentation modules, enabling end-to-end learning of semantic extraction patterns for human images. Mobile-inverse bottleneck convolution (MBConv) is used as the network backbone that has relatively few parameters and computational complexity. Inverted sub-pixel down-sampling (ISP) is proposed to minimize information loss and achieve detail-preserving of segmentation. Coordinate attention (CA) is adopted to precisely locate the portrait area. Moreover, bidirectional memory update (BMU) and memory update trigger (MUT) are proposed to improve memory resource utilization and reduce unnecessary computation. Experimental results show that, compared with the classic model ISNet, EMAUnet has the mIoU, FPS and pixel accuracy increased by 2.3%, 25.0% and 1.8%, respectively, while the amount of parameters and the size of model decreased by 33.3% and 45.7%, respectively.
- 1 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (1) , 91-104
A Lightweight Model for Fast and Detail-Preserving Human Segmentation in Video
With the rapid development of artificial intelligence, human segmentation in video is becoming increasingly important in the field of computer vision. However, existing segmentation models suffer from inaccurate segmentation, slow processing, and large model size that limit their deployment on resource-constrained devices. To this end, we propose a lightweight model called Efficient Memory Aggregation U-shaped Network (EMAUnet) for human segmentation in video, which is based on a traditional U-shaped network and attention mechanism. In EMAUnet, memory modules are combined with segmentation modules, enabling end-to-end learning of semantic extraction patterns for human images. Mobile-inverse bottleneck convolution (MBConv) is used as the network backbone that has relatively few parameters and computational complexity. Inverted sub-pixel down-sampling (ISP) is proposed to minimize information loss and achieve detail-preserving of segmentation. Coordinate attention (CA) is adopted to precisely locate the portrait area. Moreover, bidirectional memory update (BMU) and memory update trigger (MUT) are proposed to improve memory resource utilization and reduce unnecessary computation. Experimental results show that, compared with the classic model ISNet, EMAUnet has the mIoU, FPS and pixel accuracy increased by 2.3%, 25.0% and 1.8%, respectively, while the amount of parameters and the size of model decreased by 33.3% and 45.7%, respectively.
- 24 June 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 195, 110446
BrainCHEF: Cross-Level Hypergraph Enhanced Fusion model for brain networks
- 24 June 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 195, 110446
BrainCHEF: Cross-Level Hypergraph Enhanced Fusion model for brain networks
- 8 January 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 31 (1) , 1-14
An effective retrieval model for home textile images based on deep feature extraction
- 8 January 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 31 (1) , 1-14
An effective retrieval model for home textile images based on deep feature extraction
- Open Access
- 11 July 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (14) , 2172
Feature Fusion-Based Re-Ranking for Home Textile Image Retrieval
In existing image retrieval algorithms, negative samples often appear at the forefront of retrieval results. To this end, in this paper, we propose a feature fusion-based re-ranking method for home textile image retrieval, which utilizes high-level semantic similarity and low-level texture similarity information of an image and strengthens the feature expression via late fusion. Compared with single-feature re-ranking, the proposed method combines the ranking diversity of multiple features to improve the retrieval accuracy. In our re-ranking process, Markov random walk is used to update the similarity metrics, and we propose local constraint diffusion based on contextual similarity. Finally, the fusion–diffusion algorithm is used to optimize the sorted list via combining multiple similarity metrics. We set up a large-scale home textile image dataset, which contains home textile product images from categories, and evaluate the image retrieval performance of the proposed model with the Recall@k and mAP@K metrics. The experimental results show that the proposed re-ranking method can effectively improve the retrieval results and enhance the performance of home textile image retrieval.- 11 July 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (14) , 2172
Open AccessFeature Fusion-Based Re-Ranking for Home Textile Image Retrieval
In existing image retrieval algorithms, negative samples often appear at the forefront of retrieval results. To this end, in this paper, we propose a feature fusion-based re-ranking method for home textile image retrieval, which utilizes high-level semantic similarity and low-level texture similarity information of an image and strengthens the feature expression via late fusion. Compared with single-feature re-ranking, the proposed method combines the ranking diversity of multiple features to improve the retrieval accuracy. In our re-ranking process, Markov random walk is used to update the similarity metrics, and we propose local constraint diffusion based on contextual similarity. Finally, the fusion–diffusion algorithm is used to optimize the sorted list via combining multiple similarity metrics. We set up a large-scale home textile image dataset, which contains home textile product images from categories, and evaluate the image retrieval performance of the proposed model with the Recall@k and mAP@K metrics. The experimental results show that the proposed re-ranking method can effectively improve the retrieval results and enhance the performance of home textile image retrieval. - 4 March 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (2) , 1-14
Reducing blind spots in esophagogastroduodenoscopy examinations using a novel deep learning model
- 4 March 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (2) , 1-14
Reducing blind spots in esophagogastroduodenoscopy examinations using a novel deep learning model
- Open Access
- 28 December 2023
- Published by MDPI AG in Electronics
- Vol. 13 (1) , 129
LMFRNet: A Lightweight Convolutional Neural Network Model for Image Analysis
Convolutional neural networks (CNNs) have transformed the landscape of image analysis and are widely applied across various fields. With their widespread adoption in fields like medical diagnosis and autonomous driving, CNNs have demonstrated powerful capabilities. Despite their success, existing models face challenges in deploying and operating in resource-constrained environments, limiting their practicality in real-world scenarios. We introduce LMFRNet, a lightweight CNN model. Its innovation resides in a multi-feature block design, effectively reducing both model complexity and computational load. Achieving an exceptional accuracy of 94.6% on the CIFAR-10 dataset, this model showcases remarkable performance while demonstrating parsimonious resource utilization. We further validate the performance of the model on the CIFAR-100, MNIST, and Fashion-MNIST datasets, demonstrating its robustness and generalizability across diverse datasets. Furthermore, we conducted extensive experiments to investigate the influence of critical hyperparameters. These experiments provided valuable insights for effective model training.
- 28 December 2023
- Published by MDPI AG in Electronics
- Vol. 13 (1) , 129
Open AccessLMFRNet: A Lightweight Convolutional Neural Network Model for Image Analysis
Convolutional neural networks (CNNs) have transformed the landscape of image analysis and are widely applied across various fields. With their widespread adoption in fields like medical diagnosis and autonomous driving, CNNs have demonstrated powerful capabilities. Despite their success, existing models face challenges in deploying and operating in resource-constrained environments, limiting their practicality in real-world scenarios. We introduce LMFRNet, a lightweight CNN model. Its innovation resides in a multi-feature block design, effectively reducing both model complexity and computational load. Achieving an exceptional accuracy of 94.6% on the CIFAR-10 dataset, this model showcases remarkable performance while demonstrating parsimonious resource utilization. We further validate the performance of the model on the CIFAR-100, MNIST, and Fashion-MNIST datasets, demonstrating its robustness and generalizability across diverse datasets. Furthermore, we conducted extensive experiments to investigate the influence of critical hyperparameters. These experiments provided valuable insights for effective model training.
- 1 February 2023
- Published by OOO Zhurnal Voprosy Istorii in Ooo "zhurnal "voprosy Istorii"
- Vol. 2023 (2-2) , 176-183
A study on the musical artistic conception and charm of the classical poetry “Everlasting longing for each other” by the Chinese poet Li Bai
The Zheng music “Everlasting longing for each other” is adapted from the poems of the same name created by the famous poet Li Bai. Although the forms of expression are different, the artistic conception and emotion described are exactly the same. This paper aims to study the musical mood and charm of the classical poem “Everlasting longing for each other”.
- 1 February 2023
- Published by OOO Zhurnal Voprosy Istorii in Ooo "zhurnal "voprosy Istorii"
- Vol. 2023 (2-2) , 176-183
A study on the musical artistic conception and charm of the classical poetry “Everlasting longing for each other” by the Chinese poet Li Bai
The Zheng music “Everlasting longing for each other” is adapted from the poems of the same name created by the famous poet Li Bai. Although the forms of expression are different, the artistic conception and emotion described are exactly the same. This paper aims to study the musical mood and charm of the classical poem “Everlasting longing for each other”.
- Open Access$l_{1-2}$ GLasso: $L_{1-2}$ Regularized Multi-task Graphical Lasso for Joint Estimation of eQTL Mapping and Gene NetworkA critical problem in genetics is to discover how gene expression is regulated within cells. Two major tasks of regulatory association learning are : (i) identifying SNP-gene relationships, known as eQTL mapping, and (ii) determining gene-gene relationships, known as gene network estimation. To share information between these two tasks, we focus on the unified model for joint estimation of eQTL mapping and gene network, and propose a $L_{1-2}$ regularized multi-task graphical lasso, named $L_{1-2}$ GLasso. Numerical experiments on artificial datasets demonstrate the competitive performance of $L_{1-2}$ GLasso on capturing the true sparse structure of eQTL mapping and gene network. $L_{1-2}$ GLasso is further applied to real dataset of ADNI-1 and experimental results show that $L_{1 -2}$ GLasso can obtain sparser and more accurate solutions than other commonly-used methods.Open Access$l_{1-2}$ GLasso: $L_{1-2}$ Regularized Multi-task Graphical Lasso for Joint Estimation of eQTL Mapping and Gene NetworkA critical problem in genetics is to discover how gene expression is regulated within cells. Two major tasks of regulatory association learning are : (i) identifying SNP-gene relationships, known as eQTL mapping, and (ii) determining gene-gene relationships, known as gene network estimation. To share information between these two tasks, we focus on the unified model for joint estimation of eQTL mapping and gene network, and propose a $L_{1-2}$ regularized multi-task graphical lasso, named $L_{1-2}$ GLasso. Numerical experiments on artificial datasets demonstrate the competitive performance of $L_{1-2}$ GLasso on capturing the true sparse structure of eQTL mapping and gene network. $L_{1-2}$ GLasso is further applied to real dataset of ADNI-1 and experimental results show that $L_{1 -2}$ GLasso can obtain sparser and more accurate solutions than other commonly-used methods.
- Open Access
- 11 March 2021
- Published by Association for Health Sciences and Education in Journal of Nursing Education and Practice
- Vol. 11 (7) , 68
Participants’ perspectives of a fall prevention exercise program in older Arab Americans: A focus group study
Background and objective: Physical exercise is an important intervention to maintain health, reduce falls and improve quality-of-life outcomes in older adults. Falls are the leading cause of fatal and non-fatal injuries, and the use of Tai Chi exercise is well-supported by the general older population. Currently, there is little evidence to support the acceptance of Tai Chi by Arab Americans who have no cultural ties to Tai Chi. It is important to understand the perspective of participants in order to gain insight into the attitudes and opinions of the target group. Purpose: To explore participants' perspectives in a small group setting about the implementation of a culturally sensitive Tai Chi fall prevention group exercise program.Methods: Participants were eight older Arab American women who completed a 12-week Tai Chi fall prevention exercise program at a non-for-profit Arab community center. A semi-structured interview and focus group study was conducted with the participants and was audiotaped. The audio recordings were translated into English, transcribed, and analyzed for emergent themes.Results: Participants’ views of the program were positive. The key elements that contributed to the positive outcomes reported by participants were the characteristics of Tai Chi, the Tai Chi instructor, and the use of bilingual staff as a facilitator. The data showed three themes of self-reported benefits, including prevention awareness, physical benefits and mental health benefits, and two program-related factors: program barriers and promoters.Conclusions: Findings indicated that the Tai Chi program implemented in a culturally sensitive manner can be accepted by older Arab American women. Collaborating with a community-based organization and using bilingual staff from the same culture are key factors to promote the success of the program.
- 11 March 2021
- Published by Association for Health Sciences and Education in Journal of Nursing Education and Practice
- Vol. 11 (7) , 68
Open AccessParticipants’ perspectives of a fall prevention exercise program in older Arab Americans: A focus group study
Background and objective: Physical exercise is an important intervention to maintain health, reduce falls and improve quality-of-life outcomes in older adults. Falls are the leading cause of fatal and non-fatal injuries, and the use of Tai Chi exercise is well-supported by the general older population. Currently, there is little evidence to support the acceptance of Tai Chi by Arab Americans who have no cultural ties to Tai Chi. It is important to understand the perspective of participants in order to gain insight into the attitudes and opinions of the target group. Purpose: To explore participants' perspectives in a small group setting about the implementation of a culturally sensitive Tai Chi fall prevention group exercise program.Methods: Participants were eight older Arab American women who completed a 12-week Tai Chi fall prevention exercise program at a non-for-profit Arab community center. A semi-structured interview and focus group study was conducted with the participants and was audiotaped. The audio recordings were translated into English, transcribed, and analyzed for emergent themes.Results: Participants’ views of the program were positive. The key elements that contributed to the positive outcomes reported by participants were the characteristics of Tai Chi, the Tai Chi instructor, and the use of bilingual staff as a facilitator. The data showed three themes of self-reported benefits, including prevention awareness, physical benefits and mental health benefits, and two program-related factors: program barriers and promoters.Conclusions: Findings indicated that the Tai Chi program implemented in a culturally sensitive manner can be accepted by older Arab American women. Collaborating with a community-based organization and using bilingual staff from the same culture are key factors to promote the success of the program.