Search Results for author: Kwangjin Yoon

Found 10 papers, 5 papers with code

Bag of Tricks for Domain Adaptive Multi-Object Tracking

1 code implementation31 May 2022 Minseok Seo, Jeongwon Ryu, Kwangjin Yoon

To maximize the performance on real data, we first propose to use pseudo-labeling that generates imperfect labels for real data using a model trained with synthetic dataset.

Multi-Object Tracking

Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution

1 code implementation26 Jan 2022 Sangyun Lee, Sewoong Ahn, Kwangjin Yoon

Although the goal of training the degradation generator is to approximate the distribution of LR images given a HR image, previous works have heavily relied on the unrealistic assumption that the conditional distribution is a delta function and learned the deterministic mapping from the HR image to a LR image.

Image Super-Resolution SSIM

An End-to-End Trainable Video Panoptic Segmentation Method usingTransformers

no code implementations8 Oct 2021 Jeongwon Ryu, Kwangjin Yoon

In this paper, we present an algorithm to tackle a video panoptic segmentation problem, a newly emerging area of research.

Multi-Object Tracking Segmentation +1

Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion

1 code implementation31 Aug 2020 Young-min Song, Young-chul Yoon, Kwangjin Yoon, Moongu Jeon, Seong-Whan Lee, Witold Pedrycz

One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation filter.

Instance Segmentation Multi-Object Tracking +2

Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management

2 code implementations31 Jul 2019 Young-min Song, Kwangjin Yoon, Young-chul Yoon, Kin-Choong Yow, Moongu Jeon

In this paper, we propose an efficient online multi-object tracking framework based on the GMPHD filter and occlusion group management scheme where the GMPHD filter utilizes hierarchical data association to reduce the false negatives caused by miss detection.

Management Multiple Object Tracking +2

Online Multiple Pedestrians Tracking using Deep Temporal Appearance Matching Association

1 code implementation1 Jul 2019 Young-chul Yoon, Du Yong Kim, Young-min Song, Kwangjin Yoon, Moongu Jeon

The higher dimension of inherent information in the appearance model compared to the geometric model is problematic in many ways.

Multiple Hypothesis Tracking Algorithm for Multi-Target Multi-Camera Tracking with Disjoint Views

no code implementations25 Jan 2019 Kwangjin Yoon, Young-min Song, Moongu Jeon

Furthermore, multi-target tracking within a camera is performed simultaneously with the tree formation by manipulating a status of each track hypothesis.

Cannot find the paper you are looking for? You can Submit a new open access paper.