58 citations · 118 across the 7 of their papers we have counts for
7 papers
Learning Subjective Time-Series Data via Utopia Label Distribution Approximation
Wenxin Xu, Hexin Jiang, Xuefeng Liang +3
Subjective time-series regression (STR) tasks have gained increasing attention recently. However, most existing methods overlook the label distribution bias in STR data, which resu…
Gaussian-smoothed Imbalance Data Improves Speech Emotion Recognition
Xuefeng Liang, Hexin Jiang, Wenxin Xu +1
In speech emotion recognition tasks, models learn emotional representations from datasets. We find the data distribution in the IEMOCAP dataset is very imbalanced, which may harm m…
Tripartite: Tackle Noisy Labels by a More Precise Partition
Xuefeng Liang, Longshan Yao, Xingyu Liu +1
Samples in large-scale datasets may be mislabeled due to various reasons, and Deep Neural Networks can easily over-fit to the noisy label data. To tackle this problem, the key poin…
Unsupervised Outlier Detection using Memory and Contrastive Learning
Ning Huyan, Dou Quan, Xiangrong Zhang +3
Outlier detection is one of the most important processes taken to create good, reliable data in machine learning. The most methods of outlier detection leverage an auxiliary recons…
Multi-Classifier Interactive Learning for Ambiguous Speech Emotion Recognition
Ying Zhou, Xuefeng Liang, Yu Gu +2
In recent years, speech emotion recognition technology is of great significance in industrial applications such as call centers, social robots and health care. The combination of s…
Happy Travelers Take Big Pictures: A Psychological Study with Machine Learning and Big Data
Xuefeng Liang, Lixin Fan, Yuen Peng Loh +2
In psychology, theory-driven researches are usually conducted with extensive laboratory experiments, yet rarely tested or disproved with big data. In this paper, we make use of 418…
How Does the Low-Rank Matrix Decomposition Help Internal and External Learnings for Super-Resolution
Shuang Wang, Bo Yue, Xuefeng Liang +2
Wisely utilizing the internal and external learning methods is a new challenge in super-resolution problem. To address this issue, we analyze the attributes of two methodologies an…