no code implementations • 8 Mar 2023 • Varsha Suresh, Desmond C. Ong
Machine learning models automatically learn discriminative features from the data, and are therefore susceptible to learn strongly-correlated biases, such as using protected attributes like gender and race.
Facial Expression Recognition Facial Expression Recognition (FER) +1
1 code implementation • EMNLP 2021 • Varsha Suresh, Desmond C. Ong
Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them.
1 code implementation • 31 Jul 2021 • Varsha Suresh, Desmond C. Ong
Modern emotion recognition systems are trained to recognize only a small set of emotions, and hence fail to capture the broad spectrum of emotions people experience and express in daily life.
no code implementations • 29 Jun 2021 • Varsha Suresh, Gerard Yeo, Desmond C. Ong
Using a state-of-the-art model with twelve datasets (six collected in-lab and six ``in-the-wild"), we conduct extensive round-robin-style experiments to evaluate classification accuracies when given new data from an unseen dataset.
no code implementations • 22 Jul 2020 • Varsha Suresh, Wei Tsang Ooi
We found that existing approaches become less accurate when the underlying process is complex and generates large varieties of patterns in the time series.