Sungjin Kim

Sung-Jin Kim, Dae-Hyeok Lee, Hyeon-Taek Han

Electroencephalography (EEG) is a generally used neuroimaging approach in brain-computer interfaces due to its non-invasive characteristics and convenience, making it an effective tool for understanding human intentions. Therefore, recent research has focused on decoding human intentions from EEG signals utilizing deep learning methods. However, since EEG signals are highly susceptible to noise during acquisition, there is a high possibility of the existence of noisy data in the dataset. Although pioneer studies have generally assumed that the dataset is well-curated, this assumption is not always met in the EEG dataset. In this paper, we addressed this issue by designing a dataset refinement algorithm that can eliminate noisy data based on metrics evaluating data influence during the training process. We applied the proposed algorithm to two motor imagery EEG public datasets and three different models to perform dataset refinement. The results indicated that retraining the model with the refined dataset consistently led to better generalization performance compared to using the original dataset. Hence, we demonstrated that removing noisy data from the training dataset alone can effectively improve the generalization performance of deep learning models in the EEG domain.

Junyeong Kim, Minuk Ma, Kyungsu Kim et al.

This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of vision and language. However, establishing large scale dataset for multi-modal video question answering is expensive and the existing benchmarks are relatively small to provide sufficient supervision. To overcome this challenge, this paper proposes a multi-task learning method which is composed of three main components: (1) multi-modal video question answering network that answers the question based on the both video and subtitle feature, (2) temporal retrieval network that predicts the time in the video clip where the question was generated from and (3) modality alignment network that solves metric learning problem to find correct association of video and subtitle modalities. By simultaneously solving related auxiliary tasks with hierarchically shared intermediate layers, the extra synergistic supervisions are provided. Motivated by curriculum learning, multi task ratio scheduling is proposed to learn easier task earlier to set inductive bias at the beginning of the training. The experiments on publicly available dataset TVQA shows state-of-the-art results, and ablation studies are conducted to prove the statistical validity.