no code implementations • ECCV 2020 • Woobin Im, Tae-Kyun Kim, Sung-Eui Yoon
Deep unsupervised learning for optical flow has been proposed, where the loss measures image similarity with the warping function parameterized by estimated flow.
1 code implementation • 12 Mar 2024 • Jumin Lee, Sebin Lee, Changho Jo, Woobin Im, Juhyeong Seon, Sung-Eui Yoon
In this paper, we concentrate on generating a real-outdoor scene through learning a diffusion model on a real-world outdoor dataset.
1 code implementation • 2 Jan 2023 • Jumin Lee, Woobin Im, Sebin Lee, Sung-Eui Yoon
To the best of our knowledge, our work is the first to apply discrete and latent diffusion for 3D categorical data on a scene-scale.
1 code implementation • 21 Jul 2022 • Woobin Im, Sebin Lee, Sung-Eui Yoon
A training pipeline for optical flow CNNs consists of a pretraining stage on a synthetic dataset followed by a fine tuning stage on a target dataset.
1 code implementation • 26 Jun 2021 • Changho Jo, Woobin Im, Sung-Eui Yoon
Our self-supervision method, In-N-Out, is summarized as a training approach that leverages the knowledge of the opposite task into the target model.
no code implementations • 11 Jul 2019 • Chiwan Song, Woobin Im, Sung-Eui Yoon
Understanding the content of videos is one of the core techniques for developing various helpful applications in the real world, such as recognizing various human actions for surveillance systems or customer behavior analysis in an autonomous shop.
2 code implementations • 22 Apr 2017 • Sungeun Hong, Woobin Im, Hyun S. Yang
Up to now, only limited research has been conducted on cross-modal retrieval of suitable music for a specified video or vice versa.
no code implementations • 15 Feb 2017 • Sungeun Hong, Jongbin Ryu, Woobin Im, Hyun S. Yang
A fully connected layer is used to select the key frames and key segments, while the convolutional layer is used to describe them.
1 code implementation • 14 Feb 2017 • Sungeun Hong, Woobin Im, Jongbin Ryu, Hyun S. Yang
In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversarial training.
no code implementations • 26 Dec 2016 • Gwangbeen Park, Woobin Im
We present novel method for image-text multi-modal representation learning.