Yusong Wang
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
Yusong Wang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Dongyuan Li
Center for Spatial Information Science, The University of Tokyo, Tokyo, Japan
2 shared publications - Kotaro Funakoshi
Laboratory for Future Interdisciplinary Research of Science and Technology, Institute of Integrated Research, Institute of Science Tokyo, Tokyo, Japan
2 shared publications - Manabu Okumura
Institute of Science Tokyo, Tokyo, Japan
2 shared publications Liguo Tian
Tianjin Key Laboratory of Information Sensing & Intelligent Control, Tianjin University of Technology and Education, Tianjin, China
1 shared publication- Meng Li
Hefei University of Technology, Hefei, China
1 shared publication - Shiyin Tan
Institute of Science Tokyo, Tokyo, Japan
1 shared publication
Latest Publications
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4059-4063
Temporal and Topological Augmentation-based Cross-view Contrastive Learning Model for Temporal Link Prediction
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4059-4063
Open AccessTemporal and Topological Augmentation-based Cross-view Contrastive Learning Model for Temporal Link Prediction
- Open Access
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 243-252
EMP: Emotion-guided Multi-modal Fusion and Contrastive Learning for Personality Traits Recognition
Multi-modal personality traits recognition aims to recognize personality traits precisely by utilizing different modality information, which has received increasing attention for its potential applications in human-computer interaction. Current methods almost fail to extract distinguishable features, remove noise, and align features from different modalities, which dramatically affects the accuracy of personality traits recognition. To deal with these issues, we propose an emotion-guided multi-modal fusion and contrastive learning framework for personality traits recognition. Specifically, we first use supervised contrastive learning to extract deeper and more distinguishable features from different modalities. After that, considering the close correlation between emotions and personalities, we use an emotion-guided multi-modal fusion mechanism to guide the feature fusion, which eliminates the noise and aligns the features from different modalities. Finally, we use an auto-fusion structure to enhance the interaction between different modalities to further extract essential features for final personality traits recognition. Extensive experiments on two benchmark datasets indicate that our method achieves state-of-the-art performance and robustness.
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 243-252
Open AccessEMP: Emotion-guided Multi-modal Fusion and Contrastive Learning for Personality Traits Recognition
Multi-modal personality traits recognition aims to recognize personality traits precisely by utilizing different modality information, which has received increasing attention for its potential applications in human-computer interaction. Current methods almost fail to extract distinguishable features, remove noise, and align features from different modalities, which dramatically affects the accuracy of personality traits recognition. To deal with these issues, we propose an emotion-guided multi-modal fusion and contrastive learning framework for personality traits recognition. Specifically, we first use supervised contrastive learning to extract deeper and more distinguishable features from different modalities. After that, considering the close correlation between emotions and personalities, we use an emotion-guided multi-modal fusion mechanism to guide the feature fusion, which eliminates the noise and aligns the features from different modalities. Finally, we use an auto-fusion structure to enhance the interaction between different modalities to further extract essential features for final personality traits recognition. Extensive experiments on two benchmark datasets indicate that our method achieves state-of-the-art performance and robustness.
- 23 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 271-274
Research on De-noising Method of Plant Electric Signal Based on EMD and Wavelet Threshold
Plant electrical signal is a complex non-stationary signal, which can reflect the growth state of plants and the changes in the surrounding environment. There will be a lot of noise in the acquisition process. The Kalman filter and wavelet domain denoising used in the current research have certain limitations. In order to solve this problem, this article takes the Liliaceae herb Aloe as the research object and adopts self-built signal acquisition. The system extracts the electrical signal of aloe, and combines the empirical mode decomposition (EMD) and improved wavelet threshold function to denoise the collected signal. The results show that the method can effectively separate the interference signals in the aloe electrical signal, use the improved wavelet threshold method to remove the interference signals, and retain the effective information in the aloe electrical signals as much as possible, which has certainly practical significance for the analysis and feature extraction of the plant electrical signals, lay the foundation for the next step of exploring the relationship between plant electrical signals and growth status.
- 23 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 271-274
Research on De-noising Method of Plant Electric Signal Based on EMD and Wavelet Threshold
Plant electrical signal is a complex non-stationary signal, which can reflect the growth state of plants and the changes in the surrounding environment. There will be a lot of noise in the acquisition process. The Kalman filter and wavelet domain denoising used in the current research have certain limitations. In order to solve this problem, this article takes the Liliaceae herb Aloe as the research object and adopts self-built signal acquisition. The system extracts the electrical signal of aloe, and combines the empirical mode decomposition (EMD) and improved wavelet threshold function to denoise the collected signal. The results show that the method can effectively separate the interference signals in the aloe electrical signal, use the improved wavelet threshold method to remove the interference signals, and retain the effective information in the aloe electrical signals as much as possible, which has certainly practical significance for the analysis and feature extraction of the plant electrical signals, lay the foundation for the next step of exploring the relationship between plant electrical signals and growth status.