no code implementations • 3 Mar 2021 • Javier Hernandez, Daniel McDuff, Ognjen, Rudovic, Alberto Fung, Mary Czerwinski
We show that person-independent models yield significantly lower performance (55% average F1 and accuracy across 40 subjects) than person-dependent models (60. 3%), leading to a generalization gap of 5. 3%.
1 code implementation • 14 Nov 2019 • Alberto Fung, Daniel McDuff
We show that pre-training on a large diverse set of noisy data can result in even a simple CNN model improving over the current state-of-the-art DNN architectures. The average F1-score achieved with our proposed method on the DISFA dataset is 0. 60, compared to a previous state-of-the-art of 0. 57.