Xianfei He
Papers
1
Total Citations
8
H-Index
1
About
Xianfei He is a rising researcher in multimodal artificial intelligence, with a primary focus on sentiment analysis and deep learning. His most notable contribution is the development of a text-guided deep correlation mining and self-learning feature fusion framework for multimodal sentiment analysis, published in 2025. This work, which has already garnered 8 citations, introduces a novel approach to integrating textual, visual, and acoustic data by leveraging text as a guiding modality to uncover cross-modal correlations and dynamically fuse features without manual intervention. He’s framework addresses a critical challenge in affective computing: how to effectively combine heterogeneous data streams to improve sentiment prediction accuracy. By enabling self-learning feature fusion, the model adapts to varying input qualities, making it robust for real-world applications like social media monitoring and human-computer interaction. Though early in his career, He’s work signals a shift toward more adaptive and context-aware multimodal systems. His research holds promise for advancing how machines understand human emotions, with potential impacts on personalized AI assistants and mental health analytics. As his citation count grows, Xianfei He is establishing himself as a thoughtful innovator at the intersection of natural language processing and computer vision.
Research Focus
Key Achievements
Top Papers
- 1