activity
20242026
collaborators

7 papers

cs.LG2026

Adaptive Forgetting for Nonstationary Optimization: Towards Robust EEG Decoding

Hongyu Zhu, Lin Chen, Jing Chen +2

Electroencephalography (EEG) provides non-invasive monitoring of brain activity and is widely used in emotion recognition, motor imagery and sleep staging. Although within-subject…

cs.HC2026

Physiological Prior-Driven Label Enhancement for Cross-Subject EEG Emotion Recognition

Hongyu Zhu, Lin Chen, Yuming Fu +2

Electroencephalography (EEG)-based emotion recognition captures affective neural signals with high temporal precision, but cross-subject variability and label noise remain critical…

cs.HC2026

BiMoE: Brain-Inspired Experts for EEG-Dominant Affective State Recognition

Hongyu Zhu, Lin Chen, Mingsheng Shang

Multimodal Sentiment Analysis (MSA) that integrates Electroencephalogram (EEG) with peripheral physiological signals (PPS) is crucial for the development of brain-computer interfac…

cs.CV2025

MS-Mix: Sentiment-Guided Adaptive Augmentation for Multimodal Sentiment Analysis

Hongyu Zhu, Lin Chen, Xin Jin +1

Multimodal Sentiment Analysis (MSA) integrates complementary features from text, video, and audio for robust emotion understanding in human interactions. However, models suffer fro…

cs.LG2025

Semantic-guided Representation Learning for Multi-Label Recognition

Ruhui Zhang, Hezhe Qiao, Pengcheng Xu +2

Multi-label Recognition (MLR) involves assigning multiple labels to each data instance in an image, offering advantages over single-label classification in complex scenarios. Howev…

cs.CV2025

Temporal-contextual Event Learning for Pedestrian Crossing Intent Prediction

Hongbin Liang, Hezhe Qiao, Wei Huang +3

Ensuring the safety of vulnerable road users through accurate prediction of pedestrian crossing intention (PCI) plays a crucial role in the context of autonomous and assisted drivi…

cs.LG2024

Self-Supervised Spatial-Temporal Normality Learning for Time Series Anomaly Detection

Yutong Chen, Hongzuo Xu, Guansong Pang +3

Time Series Anomaly Detection (TSAD) finds widespread applications across various domains such as financial markets, industrial production, and healthcare. Its primary objective is…