Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels

no code implementations • 23 Jan 2024 • Seungho Lee, Seoungyoon Kang, Hyunjung Shim

This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT).

Language Modelling Segmentation +1

Discriminator Feature-based Inference by Recycling the Discriminator of GANs

no code implementations • 28 May 2018 • Duhyeon Bang, Seoungyoon Kang, Hyunjung Shim

Various studies assert that the latent space of a GAN is semanticallymeaningful and can be utilized for advanced data analysis and manipulation.

Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks

1 code implementation • ICCV 2017 • Inwoong Lee, Doyoung Kim, Seoungyoon Kang, Sang-Hoon Lee

In our network, we utilize an average ensemble among multiple parts as a final feature to capture various temporal dependencies.

Action Recognition Skeleton Based Action Recognition +1