no code implementations • 5 Mar 2024 • Duy Tran Thanh, Yeejin Lee, Byeongkeun Kang
The proposed framework consists of three streams: global, local body part, and head streams.
no code implementations • 15 Dec 2023 • David Kim, Sinhae Cha, Byeongkeun Kang
This work addresses the task of weakly-supervised object localization.
no code implementations • 24 Oct 2023 • Cuong Manh Hoang, Byeongkeun Kang
Furthermore, we present an extension of the proposed method for unsupervised semantic segmentation.
1 code implementation • 17 Sep 2023 • Sejin Park, Taehyung Lee, Yeejin Lee, Byeongkeun Kang
To the best of our knowledge, we are the first to address this task.
1 code implementation • 20 Sep 2022 • Seongyeop Yang, Byeongkeun Kang, Yeejin Lee
Although remarkable progress has been made in the re-identification problem, it is still a challenging problem due to appearance variations of the same person as well as other people of similar appearance.
Ranked #3 on Person Re-Identification on LTCC
1 code implementation • 10 Dec 2021 • Yeonjun Bang, Yeejin Lee, Byeongkeun Kang
Towards robust EV charging inlet detection, we propose a new dataset (EVCI dataset) and a novel data augmentation method that is based on image-to-image translation where typical image-to-image translation methods synthesize a new image in a different domain given an image.
no code implementations • ICCV 2019 • Yoshikatsu Nakajima, Byeongkeun Kang, Hideo Saito, Kris Kitani
This work addresses the task of open world semantic segmentation using RGBD sensing to discover new semantic classes over time.
no code implementations • 23 Jan 2019 • Byeongkeun Kang, Truong Q. Nguyen
In this work, we present a random forest framework that learns the weights, shapes, and sparsities of feature representations for real-time semantic segmentation.
no code implementations • 23 Jan 2019 • Byeongkeun Kang, Subarna Tripathi, Truong Q. Nguyen
The proposed method is a promising baseline method for joint image generation and compression using generative adversarial networks.
1 code implementation • 28 Jun 2018 • Chen Du, Byeongkeun Kang, Zheng Xu, Ji Dai, Truong Nguyen
To overcome these problems, we propose a novel method consisting of segmentation using convolutional neural networks and a fast/robust recovery algorithm.
1 code implementation • 5 Aug 2017 • Byeongkeun Kang, Yeejin Lee, Truong Q. Nguyen
To overcome this challenge, we develop a neural network which is able to adapt the receptive field not only for each layer but also for each neuron at the spatial location.
no code implementations • 16 May 2017 • Subarna Tripathi, Gokce Dane, Byeongkeun Kang, Vasudev Bhaskaran, Truong Nguyen
Thus the consolidation of a CNN-based object detection for an embedded system is more challenging.
1 code implementation • 8 Mar 2016 • Byeongkeun Kang, Kar-Han Tan, Nan Jiang, Hung-Shuo Tai, Daniel Tretter, Truong Q. Nguyen
Thus, we propose hand segmentation method for hand-object interaction using only a depth map.
1 code implementation • 4 Oct 2015 • Byeongkeun Kang, Yeejin Lee, Truong Q. Nguyen
In our system, we track hand articulations by minimizing discrepancy between depth map from sensor and computer-generated hand model.
1 code implementation • 10 Sep 2015 • Byeongkeun Kang, Subarna Tripathi, Truong Q. Nguyen
We train CNNs for the classification of 31 alphabets and numbers using a subset of collected depth data from multiple subjects.
no code implementations • 30 Jun 2015 • Yuanyuan Wu, Xiaohai He, Byeongkeun Kang, Haiying Song, Truong Q. Nguyen
This letter presents a novel approach to extract reliable dense and long-range motion trajectories of articulated human in a video sequence.