About Me

👋 Hi! I am a Ph.D. candidate at Southeast University (SEU), specializing in pattern recognition and representation learning in artificial intelligence. My research focuses on developing advanced learning techniques to improve the generalization and robustness of AI models.

🔬 Research Interests

My research interests include:

• Human Activity Recognition
• Skeleton-based Action Recognition
• Contrastive Learning
• Weakly Supervised Learning
• Unsupervised Domain Adaptation

🎓 Education

• 2021 – Present: Ph.D. Candidate, School of Cyber Science and Engineering, Southeast University
  • Advisor: Jiuxin Cao
• 2018 – 2021: M.S., School of Electrical and Automation Engineering, Nanjing Normal University
  • Advisor: Lei Zhang
• 2013 – 2017: B.S., School of Automation, Southeast University

📚 Publications

Google Scholar Link | ORCID

📝 First-Author Publications

• Dual-Domain Triple Contrast for Cross-Dataset Skeleton-based Action Recognition, K Wang, J Cao, J Ge, C Liu, B Liu, ACM Transactions on Multimedia Computing Communications and Applications (TOMM), 2025.

• Text-to-face synthesis based on facial landmarks prediction, K Wang, L Chen, B Cao, B Liu, J Cao, Machine Vision and Applications, 2025.

• EnsCLR: Unsupervised skeleton-based action recognition via ensemble contrastive learning of representation, K Wang, J Cao, B Cao, B Liu, Computer Vision and Image Understanding, 2024.

• Sequential weakly labeled multiactivity localization and recognition on wearable sensors using recurrent attention networks, K Wang, J He, L Zhang, IEEE Transactions on Human-Machine Systems (THMS), 2021.

• Attention-based convolutional neural network for weakly labeled human activities’ recognition with wearable sensors, K Wang, J He, L Zhang, IEEE Sensors Journal, 2019.

🤝 Co-Authored Publications

• Consistencies are all you need for semi-supervised vision-language tracking, J Ge, J Cao, X Zhu, X Zhang, C Liu, K Wang, B Liu, Proceedings of the 32nd ACM International Conference on Multimedia, 2024.

• Causal-story: Local causal attention utilizing parameter-efficient tuning for visual story synthesis, T Song, J Cao, K Wang, B Liu, X Zhang, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.

• The layer-wise training convolutional neural networks using local loss for sensor-based human activity recognition, Q Teng, K Wang, L Zhang, J He, IEEE Sensors Journal, 2020.

📬 Contact

• GitHub: KennCoder7
• Email: iskenn7@gmail.com; kun_wang@seu.edu.cn