Search

Your search keyword '"Wang, Yu-Chun"' showing total 996 results
Start Over Author "Wang, Yu-Chun"
996 results on '"Wang, Yu-Chun"'

6. Disentangled Representation with Dual-stage Feature Learning for Face Anti-spoofing

Author

Wang, Yu-Chun, Wang, Chien-Yi, and Lai, Shang-Hong

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

As face recognition is widely used in diverse security-critical applications, the study of face anti-spoofing (FAS) has attracted more and more attention. Several FAS methods have achieved promising performances if the attack types in the testing data are the same as training data, while the performance significantly degrades for unseen attack types. It is essential to learn more generalized and discriminative features to prevent overfitting to pre-defined spoof attack types. This paper proposes a novel dual-stage disentangled representation learning method that can efficiently untangle spoof-related features from irrelevant ones. Unlike previous FAS disentanglement works with one-stage architecture, we found that the dual-stage training design can improve the training stability and effectively encode the features to detect unseen attack types. Our experiments show that the proposed method provides superior accuracy than the state-of-the-art methods on several cross-type FAS benchmarks., Comment: WACV 2022

Published
2021

23. Drosophilaappear resistant to trans-synaptic tau propagation

Author

Catterson, James H, primary, Mouofo, Edmond N, additional, Soler, Inés López De Toledo, additional, Lean, Gillian, additional, Dlamini, Stella, additional, Liddell, Phoebe, additional, Voong, Graham, additional, Katsinelos, Taxiarchis, additional, Wang, Yu-Chun, additional, Schoovaerts, Nils, additional, Verstreken, Patrik, additional, Spires-Jones, Tara L, additional, and Durrant, Claire S, additional

Published
2024
Full Text
View/download PDF

31. Assessment of PM2.5-associated mortality burden among the elderly: Insights into demographic, socio-economic, and geographic factors.

Author

Sharma, Ayushi, Hsiao, Hsi-yu, Liu, Jia-Yi, Lung, Shih-Chun Candice, Su, Huey-Jen, Shen, Ching-Fen, Chen, Nai-Tzu, Wu, Pei-Chih, Lin, Cheng-Yu, Liang, Sheng-Fu, Cheng, Tain-Junn, Chan, Ta-Chien, Tsay, Yaw-Shyan, Chung, Hsin-Ying, and Wang, Yu-Chun

Abstract

Since long-term exposure to PM2.5 is a growing concern in Taiwan, therefore, our study aimed to investigate the association between different PM2.5 concentrations and cause-specific mortalities, as well as explore the influence of demographic, socio-economic, and geographic determinants on mortality. Utilizing a Distributed Lag Non-Linear Model (DLNM), we estimated the PM2.5-attributable mortality burden among the elderly population (above 65 years) in Taiwan from 2005 to 2018. Our analysis considered various thresholds defined by the World Health Organization (WHO) to assess the impact of PM2.5 concentrations, ranging from standard Air Quality Guidelines (AQG) levels (0–15 μg/m3) to higher interim targets (up to 80 μg/m3). Our study reveals that achieving AQG levels (< 15 μg/m3) in Taiwan could potentially prevent 5571 elderly deaths, including 889 deaths from CVDs, 934 deaths from RTIs, and 680 deaths from chronic diseases. We observed a rapid increase in attributable deaths at lower PM2.5 concentrations, with a subsequent marginal increase at higher levels of exposure. We also identified several factors that modify the effects of PM2.5 exposures among elderly. For example, we found that higher elderly population ratios and high-income households were associated with an elevated risk of PM2.5-related deaths. In contrast, higher social welfare expenditure, better availability of medical practitioners per square kilometer, and higher forest-to-land ratios were associated with positive effects, indicating their potential in reducing mortality risk. This study fills a knowledge gap by examining the health consequences of varying PM2.5 levels and explored the complex interplay between demographic, socio-economic, and geographic factors in relation to PM2.5-related mortality. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

33. Textual Analysis for Studying Chinese Historical Documents and Literary Novels

Author

Liu, Chao-Lin, Jin, Guan-Tao, Wang, Hongsu, Liu, Qing-Feng, Cheng, Wen-Huei, Chiu, Wei-Yun, Tsai, Richard Tzong-Han, and Wang, Yu-Chun

Subjects
Computer Science - Computation and Language, Computer Science - Digital Libraries
Abstract

We analyzed historical and literary documents in Chinese to gain insights into research issues, and overview our studies which utilized four different sources of text materials in this paper. We investigated the history of concepts and transliterated words in China with the Database for the Study of Modern China Thought and Literature, which contains historical documents about China between 1830 and 1930. We also attempted to disambiguate names that were shared by multiple government officers who served between 618 and 1912 and were recorded in Chinese local gazetteers. To showcase the potentials and challenges of computer-assisted analysis of Chinese literatures, we explored some interesting yet non-trivial questions about two of the Four Great Classical Novels of China: (1) Which monsters attempted to consume the Buddhist monk Xuanzang in the Journey to the West (JTTW), which was published in the 16th century, (2) Which was the most powerful monster in JTTW, and (3) Which major role smiled the most in the Dream of the Red Chamber, which was published in the 18th century. Similar approaches can be applied to the analysis and study of modern documents, such as the newspaper articles published about the 228 incident that occurred in 1947 in Taiwan., Comment: 11 pages, 7 figures, 2 tables, The Fourth ASE International Conference on Social Informatics

Published
2015
Full Text
View/download PDF

37. A Preliminary Study of Model-Generated Speech.

Author

Chu, Man-Ni and Wang, Yu-Chun

Subjects
CHINESE characters, ENCYCLOPEDIAS & dictionaries, MACHINE learning, ELECTRIC machines, PRONUNCIATION
Abstract

The goal of this study was to compare model-generated sounds with the process of sound acquisition in humans. The research utilized two dictionaries of the Chaoshan dialect spanning approximately one century. Identical Chinese characters were selected from each dictionary, and their contemporary pronunciations were documented. Subsequently, inconsistencies in pronunciation were manually rectified, following which three machine learning methods were employed to train the pronunciation of words from one dictionary to another. These methods comprised the attention-based sequence-to-sequence method, DirecTL+, and Sequitur. The accuracy of the model was evaluated using five-fold cross-validation, revealing a maximum accuracy of 68%. Additionally, the study investigated how the probability of a sound's subsequent unit influences the accuracy of the machine learning methods. The attention-based sequence-to-sequence model is not solely influenced by the frequency of input but also by the probability of the subsequent unit. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

38. Changes of Mycobacterium tuberculosis specific antigen-stimulated CD27−CD38+IFN-γ+CD4+ T cells before and after anti-tuberculosis treatment.

Author

Fang, Yong, Tang, Yuan, Luo, Qiao-Xia, Wang, Na, Tang, Liang, Yang, Xiao-Jun, You, Xiao-Fang, Wang, Yu-Chun, Liang, Li, Zhang, Jing-Bo, Su, Bo, and Sha, Wei

Subjects
MYCOBACTERIUM tuberculosis, T cells, BLOOD sedimentation, LATENT infection, TUBERCULOUS meningitis, C-reactive protein
Abstract

Background: The aim of the study was to investigate whether the expression of CD27−CD38+ in interferon (IFN)-γ+CD4+ T cells stimulated by the specific antigen early secreted antigenic target-6 (ESAT-6)/culture filter protein-10 (CFP-10) could be a potential new therapeutic evaluation indicator for anti-tuberculosis (TB) treatment. Methods: Newly diagnosed active pulmonary TB patients, latent TB infection (LTBI) and healthy controls were enrolled from January 2021 to December 2021. PTB patients were treated by standard anti-TB regimen 2HREZ/4HR (2 months of isoniazid (H), rifampin (R), ethambutol (E), and pyrazinamide (Z) followed by 4 months of isoniazid (H) and rifampin (R)). The difference of CD27−CD38+ expression in IFN-γ+CD4+ T cells before treatment, 2 months after treatment, and 6 months after treatment were compared. Results: Total 45 PTB patients, 38 LTBI cases and 43 healthy controls were enrolled. The expression of CD27−CD38+ decreased significantly after anti-TB treatment and was comparable with that in LTBI and healthy controls when the 6-month anti-TB treatment course was completed. The decline rate of CD27−CD38+ between 6 months after treatment and baseline was positively correlated with erythrocyte sedimentation rate (r = 0.766, P < 0.0001), C-reactive protein (r = 0.560, P = 0.003) and chest computerized tomography severity score (r = 0.632, P = 0.0005). The area under receiver operator characteristic curve of CD27−CD38+ in distinguish pulmonary TB patients before and after treatment was 0.779. Conclusion: The expression of CD27−CD38+ in ESAT-6/CFP-10 stimulated IFN-γ+CD4+T cells can well reflect the changes of the disease before and after anti-TB treatment, which is expected to be a potential new therapeutic evaluation index. Clinical Registry number chiCTR1800019966. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results