Associate Researcher Qilu University of Technology (Shandong Academy of Sciences) China
Dr. Xiang Li is an accomplished Associate Researcher at the Qilu University of Technology (Shandong Academy of Sciences) in China, where he has been serving since 2019. With a strong academic foundation in computer science and a research focus spanning EEG-based emotion recognition, multimodal sentiment analysis, and contrastive learning, Dr. Li has published widely in high-impact journals and conferences. His work is recognized internationally, with over 1,700 citations on Google Scholar, reflecting his significant influence in the field of artificial intelligence and affective computing.
Profile
Google Scholar
Orcid
๐ Education
Dr. Li earned his Ph.D. in Computer Science from the College of Intelligence and Computing at Tianjin University in 2019. He previously received his Master’s degree in Computer Science (2014) and a Bachelorโs degree in Network Engineering (2011), both from the School of Information Science and Technology at Shandong University of Science and Technology.
๐ผ Experience
Since 2019, Dr. Xiang Li has held the position of Associate Researcher at the Qilu University of Technology. In addition to his research role, he contributes significantly to teaching, instructing several undergraduate and graduate-level courses since 2020, including English for Computer Science, Information Retrieval, and Data Mining, Analysis, and Visualization. His multidisciplinary expertise allows him to merge theory with practice, especially in the intersection of artificial intelligence, neuroscience, and ocean data analytics.
๐ฌ Research Interests
Dr. Liโs research interests lie in EEG-based emotion recognition, multimodal deep learning, contrastive learning, and affective computing. He has also made substantial contributions to intelligent quality control in ocean observation, shipborne wind speed correction, and biomedical signal processing. His innovative approaches often employ supervised and self-supervised learning frameworks, with a focus on enhancing data-driven decision-making using limited or noisy data.
๐ Awards
- ๐ง ESI Highly Cited Paper for “EEG based emotion recognition: A tutorial and review” (2022)
- ๐
Recognized for over 1,700 citations on Google Scholar
- ๐ Several publications with >100 citations, such as his works on quantum-inspired sentiment analysis and cross-subject EEG emotion recognition
- ๐งช Multiple papers published in SCI Tier-1 journals and top CCF-ranked conferences
๐ Publications Top Notes:ย ย
Below is a selection of Dr. Xiang Liโs publications, presented with hyperlinks, publication years, journals/conferences, and citation data (when available):
๐ 2025: Multi-Affection Prompt Learning for Sentiment, Emotion and Sarcasm Joint Detection in Conversations โ Tsinghua Science and Technology [SCI-1]
๐ 2024: A Supervised Information Enhanced Multi-granularity Contrastive Learning Framework for EEG based Emotion Recognition โ ICASSP 2024 [CCF-B]
๐ 2024: Self-Supervised Pretraining-Enhanced Intelligent Quality Control for Ocean Observations โ ICONIP 2024 [CCF-C]
๐ 2024: An Adaptive Time-convolutional Network Online Prediction Method for Ocean Observation Data โ SEKE 2024 [CCF-C]
๐ 2024: Fusion of Time-Frequency Features in Contrastive Learning for Wind Speed Correction โ Journal of Ocean University of China [SCI-3]
๐ 2023: EEG-based Parkinson Detection through Supervised Contrastive Learning โ BIBM 2023 [CCF-B]
๐ 2022: EEG based Emotion Recognition: A Tutorial and Review โ ACM Computing Surveys, 55(4) [SCI-1, IF=23.8, Cited by: 272]
๐ 2021: Emotion Recognition via Dual-pipeline Graph Attention Network โ BIBM 2021 [CCF-B]
๐ 2020: Latent Factor Decoding of Multi-channel EEG through Neural Networks โ Frontiers in Neuroscience, [SCI-2, Cited by: 81]
๐ 2018: Exploring EEG Features in Cross-subject Emotion Recognition โ Frontiers in Neuroscience, [SCI-2, Cited by: 369]
๐ 2016: Emotion Recognition from Multi-channel EEG via CNN-RNN โ BIBM 2016 [CCF-B, Cited by: 320]
๐ 2015: EEG-based Emotion Identification Using Deep Feature Learning โ ACM SIGIR NeuroIR Workshop [CCF-A Workshop, Cited by: 92]