Lei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lei Chen has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Shunxiang Zhang
Anhui University of Science and Technology
2 shared publications - Zhengyan Sun
Huainan Normal University
2 shared publications - Deyu Wang1 shared publication
- Guangli Zhu
Anhui University of Science and Technology
1 shared publication - Jiajia Liu
School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, China and Artificial Intelligence Research Institute, Hefei Comprehensive National Science Center, Hefei, China
1 shared publication - Jiawen Guan1 shared publication
Latest Publications
- 4 July 2026
- Published by Springer Nature
- p. 371-379
A Review of Heterogeneous Data Fusion and Dynamic Optimization Methods Based on Large Models
- 4 July 2026
- Published by Springer Nature
- p. 371-379
A Review of Heterogeneous Data Fusion and Dynamic Optimization Methods Based on Large Models
- Open Access
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
A Multimodal Semantic Fusion Network with Cross-Modal Alignment for Multimodal Sentiment Analysis
User-generated multimodal data can provide powerful sentiment clues for sentiment analysis task. Existing works have aligned common sentiment features in different modalities through various multimodal fusion methods. However, these works have certain limitations: (1) Previous research works only align common sentiment features between image and text, without fully exploring interactions among these features, leading to suboptimal analysis results. (2) Redundant noise in image and text increases the risk of feature misalignment during cross-modal alignment. To address these issues, we propose a multimodal semantic fusion network (MSFN) to deeply explore the semantic relationship between image and text for Multimodal Sentiment Analysis (MSA). Specifically, we align image region and text word features related to sentiment by using a gated attention mechanism. Subsequently, we employ graph convolutional networks to model the interactions among these features to obtain explicit sentiment semantics. The proposed gated attention mechanism corrects potential feature misalignment during cross-modal alignment using a gating mechanism. Moreover, considering not all image-text pairs have explicit corresponding sentiment features, we integrate implicit sentiment semantics to our model for enhancing reliability in analysis. Experimental results on benchmark datasets demonstrate the effectiveness of our proposed model compared to baselines.
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Open AccessA Multimodal Semantic Fusion Network with Cross-Modal Alignment for Multimodal Sentiment Analysis
User-generated multimodal data can provide powerful sentiment clues for sentiment analysis task. Existing works have aligned common sentiment features in different modalities through various multimodal fusion methods. However, these works have certain limitations: (1) Previous research works only align common sentiment features between image and text, without fully exploring interactions among these features, leading to suboptimal analysis results. (2) Redundant noise in image and text increases the risk of feature misalignment during cross-modal alignment. To address these issues, we propose a multimodal semantic fusion network (MSFN) to deeply explore the semantic relationship between image and text for Multimodal Sentiment Analysis (MSA). Specifically, we align image region and text word features related to sentiment by using a gated attention mechanism. Subsequently, we employ graph convolutional networks to model the interactions among these features to obtain explicit sentiment semantics. The proposed gated attention mechanism corrects potential feature misalignment during cross-modal alignment using a gating mechanism. Moreover, considering not all image-text pairs have explicit corresponding sentiment features, we integrate implicit sentiment semantics to our model for enhancing reliability in analysis. Experimental results on benchmark datasets demonstrate the effectiveness of our proposed model compared to baselines.
- Open Access
- 30 December 2023
- Published by Taylor & Francis in Connection Science
- Vol. 36 (1)
PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection
- 30 December 2023
- Published by Taylor & Francis in Connection Science
- Vol. 36 (1)
Open AccessPS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection