1 code implementation • 8 Dec 2022 • Young-Jun Lee, Byungsoo Ko, Han-Gyu Kim, Jonghwan Hyeon, Ho-Jin Choi
Through this pipeline, we introduce DialogCC, a high-quality and diverse multi-modal dialogue dataset that surpasses existing datasets in terms of quality and diversity in human evaluation.
no code implementations • 8 Dec 2022 • Byungsoo Ko, Han-Gyu Kim, Byeongho Heo, Sangdoo Yun, Sanghyuk Chun, Geonmo Gu, Wonjae Kim
As ViT groups the channels via a multi-head attention mechanism, grouping the channels by GGeM leads to lower head-wise dependence while amplifying important channels on the activation maps.
no code implementations • 7 Oct 2021 • Namkyu Jung, Geonmin Kim, Han-Gyu Kim
In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model.
1 code implementation • ICCV 2021 • Byungsoo Ko, Geonmo Gu, Han-Gyu Kim
This can be undesirable for DML, where training and test data exhibit entirely different classes.
2 code implementations • 29 Mar 2021 • Geonmo Gu, Byungsoo Ko, Han-Gyu Kim
One of the main purposes of deep metric learning is to construct an embedding space that has well-generalized embeddings on both seen (training) classes and unseen (test) classes.
no code implementations • 22 Dec 2014 • Giljin Jang, Han-Gyu Kim, Yung-Hwan Oh
This paper proposes a novel framework for unsupervised audio source separation using a deep autoencoder.