Search

Your search keyword '"Li, Xiaohe"' showing total 700 results
Start Over Author "Li, Xiaohe"
700 results on '"Li, Xiaohe"'

3. MetaTra: Meta-Learning for Generalized Trajectory Prediction in Unseen Domain

Author

Li, Xiaohe, Huang, Feilong, Fan, Zide, Mou, Fangli, Hou, Yingyan, Qian, Chen, and Wen, Lijie

Subjects
Computer Science - Robotics, Computer Science - Computer Vision and Pattern Recognition
Abstract

Trajectory prediction has garnered widespread attention in different fields, such as autonomous driving and robotic navigation. However, due to the significant variations in trajectory patterns across different scenarios, models trained in known environments often falter in unseen ones. To learn a generalized model that can directly handle unseen domains without requiring any model updating, we propose a novel meta-learning-based trajectory prediction method called MetaTra. This approach incorporates a Dual Trajectory Transformer (Dual-TT), which enables a thorough exploration of the individual intention and the interactions within group motion patterns in diverse scenarios. Building on this, we propose a meta-learning framework to simulate the generalization process between source and target domains. Furthermore, to enhance the stability of our prediction outcomes, we propose a Serial and Parallel Training (SPT) strategy along with a feature augmentation method named MetaMix. Experimental results on several real-world datasets confirm that MetaTra not only surpasses other state-of-the-art methods but also exhibits plug-and-play capabilities, particularly in the realm of domain generalization.

Published
2024

8. Local-to-Global Point Supervised Object Detector via Aggregation of Discriminative Parts

Author

Zhang, Yidan, Hou, Yingyan, Liu, Xiaoxuan, Li, Xiaohe, Mou, Fangli, Zhang, Peirong, Qi, Xiyu, Jia, Jie, Wang, Lei, Zhao, Xinyu, Akan, Ozgur, Editorial Board Member, Bellavista, Paolo, Editorial Board Member, Cao, Jiannong, Editorial Board Member, Coulson, Geoffrey, Editorial Board Member, Dressler, Falko, Editorial Board Member, Ferrari, Domenico, Editorial Board Member, Gerla, Mario, Editorial Board Member, Kobayashi, Hisashi, Editorial Board Member, Palazzo, Sergio, Editorial Board Member, Sahni, Sartaj, Editorial Board Member, Shen, Xuemin, Editorial Board Member, Stan, Mircea, Editorial Board Member, Jia, Xiaohua, Editorial Board Member, Zomaya, Albert Y., Editorial Board Member, Yu, Weng, editor, and Xuan, Liu, editor

Published
2024
Full Text
View/download PDF

9. PCB Large Color Variation Image Registration with Local Optimization LoFTR

Author

Hou, Yingyan, Zhang, Yidan, Liu, Xiaoxuan, Wu, Hui, Jia, Jie, Li, Xiaohe, Liu, Shixiong, Wang, Lei, Zhao, Xinyu, Akan, Ozgur, Editorial Board Member, Bellavista, Paolo, Editorial Board Member, Cao, Jiannong, Editorial Board Member, Coulson, Geoffrey, Editorial Board Member, Dressler, Falko, Editorial Board Member, Ferrari, Domenico, Editorial Board Member, Gerla, Mario, Editorial Board Member, Kobayashi, Hisashi, Editorial Board Member, Palazzo, Sergio, Editorial Board Member, Sahni, Sartaj, Editorial Board Member, Shen, Xuemin, Editorial Board Member, Stan, Mircea, Editorial Board Member, Jia, Xiaohua, Editorial Board Member, Zomaya, Albert Y., Editorial Board Member, Yu, Weng, editor, and Xuan, Liu, editor

Published
2024
Full Text
View/download PDF

13. Graph Neural Network with Curriculum Learning for Imbalanced Node Classification

Author

Li, Xiaohe, Wen, Lijie, Deng, Yawen, Feng, Fuli, Hu, Xuming, Wang, Lei, and Fan, Zide

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Graph Neural Network (GNN) is an emerging technique for graph-based learning tasks such as node classification. In this work, we reveal the vulnerability of GNN to the imbalance of node labels. Traditional solutions for imbalanced classification (e.g. resampling) are ineffective in node classification without considering the graph structure. Worse still, they may even bring overfitting or underfitting results due to lack of sufficient prior knowledge. To solve these problems, we propose a novel graph neural network framework with curriculum learning (GNN-CL) consisting of two modules. For one thing, we hope to acquire certain reliable interpolation nodes and edges through the novel graph-based oversampling based on smoothness and homophily. For another, we combine graph classification loss and metric learning loss which adjust the distance between different nodes associated with minority class in feature space. Inspired by curriculum learning, we dynamically adjust the weights of different modules during training process to achieve better ability of generalization and discrimination. The proposed framework is evaluated via several widely used graph datasets, showing that our proposed model consistently outperforms the existing state-of-the-art methods.

Published
2022

15. Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction

Author

Hu, Xuming, Zhang, Chenwei, Yang, Yawen, Li, Xiaohe, Lin, Li, Wen, Lijie, and Yu, Philip S.

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Low-resource Relation Extraction (LRE) aims to extract relation facts from limited labeled corpora when human annotation is scarce. Existing works either utilize self-training scheme to generate pseudo labels that will cause the gradual drift problem, or leverage meta-learning scheme which does not solicit feedback explicitly. To alleviate selection bias due to the lack of feedback loops in existing LRE learning paradigms, we developed a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate the gradient descent direction on labeled data and bootstrap its optimization capability through trial and error. We also propose a framework called GradLRE, which handles two major scenarios in low-resource relation extraction. Besides the scenario where unlabeled data is sufficient, GradLRE handles the situation where no unlabeled data is available, by exploiting a contextualized augmentation method to generate data. Experimental results on two public datasets demonstrate the effectiveness of GradLRE on low resource relation extraction when comparing with baselines., Comment: In EMNLP 2021 as a long paper. Code and data available at https://github.com/THU-BPM/GradLRE

Published
2021

23. Digital measurement and clinical significance of proximal femur in the older people of Inner Mongolia population, China

Author

Li Jiawei, Zhang Kai, Wang Haiyan, Wu Chao, Zhang Yunfeng, Ding Liangjia, Liu Qinghua, Li Canran, Jin Feng, and Li Xiaohe

Subjects
Age, Gender, Inner Mongolia population, China, Morphometric measurement of proximal femur, Femoral prosthesis design, Geriatrics, RC952-954.6
Abstract

Abstract Objective This study aimed to measure the parameters of the proximal femur in the older people of Inner Mongolia, China and understand the influence of age and gender so as to provide guidance for the design and improvement of prosthesis for total hip arthroplasty. Methods A total of 236 patients who underwent CT angiography of lower limbs in the Department of Imaging, Affiliated Hospital of Inner Mongolia Medical University of China were collected. They were divided into 4 groups according to age: 80 years (group D). Four anatomical parameters, including femoral head diameter (FHD), femoral neck-shaft angle (FNSA), femoral offset (FO), femoral neck anteversion (FNA), were measured by Mimics 21.0. Comparisons were made between age groups of the same gender and between genders in the same age group to analyze the correlation of the 4 parameters of proximal femur with age and gender. In addition, the results of this study were compared with previous studies. Results There were no significant differences in FHD and FO between age groups, indicating no correlation with age. FNSA and FNA were no significantly different between group C and group D in the same gender, whereas there were significant differences between other age groups and were negatively correlated with age. There were significant differences in FHD and FO between genders in the same age group, with the males being larger than the females. FNSA and FNA were no significant differences between genders in the same age group. Conclusions FNSA and FNA decrease with age. FHD and FO were larger in males than in females in all age groups. Age and gender should be considered in the design of prosthesis.

Published
2023
Full Text
View/download PDF

29. GAHNE: Graph-Aggregated Heterogeneous Network Embedding

Author

Li, Xiaohe, Wen, Lijie, Qian, Chen, and Wang, Jianmin

Subjects
Computer Science - Social and Information Networks, Computer Science - Artificial Intelligence
Abstract

The real-world networks often compose of different types of nodes and edges with rich semantics, widely known as heterogeneous information network (HIN). Heterogeneous network embedding aims to embed nodes into low-dimensional vectors which capture rich intrinsic information of heterogeneous networks. However, existing models either depend on manually designing meta-paths, ignore mutual effects between different semantics, or omit some aspects of information from global networks. To address these limitations, we propose a novel Graph-Aggregated Heterogeneous Network Embedding (GAHNE), which is designed to extract the semantics of HINs as comprehensively as possible to improve the results of downstream tasks based on graph convolutional neural networks. In GAHNE model, we develop several mechanisms that can aggregate semantic representations from different single-type sub-networks as well as fuse the global information into final embeddings. Extensive experiments on three real-world HIN datasets show that our proposed model consistently outperforms the existing state-of-the-art methods.

Published
2020

32. A CiteSpace Analysis of Rural Accounting Research in the Perspective of Digital Rural Governance

Author

Li Xiaohe

Subjects
citespace, lda, perplexity, rural accounting, 65y04, Mathematics, QA1-939
Abstract

In digital rural governance, the effective integration of accounting and rural development is crucial for maximizing rural economic benefits. This paper uses CiteSpace software and LDA modeling to examine the current state and hot topics in rural accounting research from 2018 to 2022. The study was visualized by analyzing valid literature and using perplexity to determine the best effect of topic extraction. The results show that the number of annual publications in this field continues to grow, and the number of universities and institutions publishing relevant papers is also increasing yearly. Regarding research hotspots, the keyword “rural” appears most frequently, reaching 122 times, followed by “financial management” with a frequency of 106 times. The keyword with the highest centrality is “rural revitalization”, with a centrality as high as 0.38. The research keywords are mainly divided into rural revitalization and financial management, with the financial management group being the most dominant. However, the number of studies on rural revitalization has been increasing yearly, and the gap between them has been narrowing. The importance of accounting is growing in promoting rural revitalization and improving rural economic efficiency.

Published
2024
Full Text
View/download PDF

33. Pchatbot: A Large-Scale Dataset for Personalized Chatbot

Author

Qian, Hongjin, Li, Xiaohe, Zhong, Hanxun, Guo, Yu, Ma, Yueyuan, Zhu, Yutao, Liu, Zhanliang, Dou, Zhicheng, and Wen, Ji-Rong

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Natural language dialogue systems raise great attention recently. As many dialogue models are data-driven, high-quality datasets are essential to these systems. In this paper, we introduce Pchatbot, a large-scale dialogue dataset that contains two subsets collected from Weibo and Judicial forums respectively. To adapt the raw dataset to dialogue systems, we elaborately normalize the raw dataset via processes such as anonymization, deduplication, segmentation, and filtering. The scale of Pchatbot is significantly larger than existing Chinese datasets, which might benefit the data-driven models. Besides, current dialogue datasets for personalized chatbot usually contain several persona sentences or attributes. Different from existing datasets, Pchatbot provides anonymized user IDs and timestamps for both posts and responses. This enables the development of personalized dialogue models that directly learn implicit user personality from the user's dialogue history. Our preliminary experimental study benchmarks several state-of-the-art dialogue models to provide a comparison for future work. The dataset can be publicly accessed at Github., Comment: Camera-ready version, SIGIR 2021 (Resource Track), the dataset and codes are available at https://github.com/qhjqhj00/Pchatbot

Published
2020

47. 2019 Global NAFLD Prevalence: A Systematic Review and Meta-analysis

Author

Le, Michael H., Yeo, Yee Hui, Li, Xiaohe, Li, Jie, Zou, Biyao, Wu, Yuankai, Ye, Qing, Huang, Daniel Q., Zhao, Changqing, Zhang, Jie, Liu, Chenxi, Chang, Na, Xing, Feng, Yan, Shiping, Wan, Zi Hui, Tang, Natasha Sook Yee, Mayumi, Maeda, Liu, Xinting, Liu, Chuanli, Rui, Fajuan, Yang, Hongli, Yang, Yao, Jin, Ruichun, Le, Richard H.X., Xu, Yayun, Le, David M., Barnett, Scott, Stave, Christopher Donald, Cheung, Ramsey, Zhu, Qiang, and Nguyen, Mindie H.

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results