Search Results - "Yun, Sangdoo"

Character Region Awareness for Text Detection by Baek, Youngmin, Lee, Bado, Han, Dongyoon, Yun, Sangdoo, Lee, Hwalsuk

“…Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level…”
Get full text

Rethinking Spatial Dimensions of Vision Transformers by Heo, Byeongho, Yun, Sangdoo, Han, Dongyoon, Chun, Sanghyuk, Choe, Junsuk, Oh, Seong Joon

“…Vision Transformer (ViT) extends the application range of transformers from language processing to computer vision tasks as being an alternative architecture…”
Get full text

Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning by Sangdoo Yun, Jongwon Choi, Youngjoon Yoo, Kimin Yun, Jin Young Choi

“…This paper proposes a novel tracker which is controlled by sequentially pursuing actions learned by deep reinforcement learning. In contrast to the existing…”
Get full text

Attentional Correlation Filter Network for Adaptive Visual Tracking by Jongwon Choi, Hyung Jin Chang, Sangdoo Yun, Fischer, Tobias, Demiris, Yiannis, Jin Young Choi

“…We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and…”
Get full text

Action-Driven Visual Object Tracking With Deep Reinforcement Learning by Yun, Sangdoo, Choi, Jongwon, Yoo, Youngjoon, Yun, Kimin, Choi, Jin Young

“…In this paper, we propose an efficient visual tracker, which directly captures a bounding box containing the target object in a video by means of sequential…”
Get full text

Context-Aware Deep Feature Compression for High-Speed Visual Tracking by Choi, Jongwon, Chang, Hyung Jin, Fischer, Tobias, Yun, Sangdoo, Lee, Kyuewang, Jeong, Jiyeoup, Demiris, Yiannis, Choi, Jin Young

“…We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among…”
Get full text

How Much a Model be Trained by Passive Learning Before Active Learning? by Jo, Dae Ung, Yun, Sangdoo, Choi, Jin Young

“…Most pool-based active learning studies have focused on query strategy for active learning. In this paper, via empirical analysis on the effect of passive…”
Get full text

Observations on K-image Expansion of Image-Mixing Augmentation by Jeong, Joonhyun, Cha, Sungmin, Choi, Jongwon, Yun, Sangdoo, Moon, Taesup, Yoo, Youngjoon

“…Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image…”
Get full text

Detecting and Removing Text in the Wild by Cho, Junho, Yun, Sangdoo, Han, Dongyoon, Heo, Byeongho, Choi, Jin Young

“…Scene text removal is a challenging task that aims to erase wild text regions that include text strokes and their ambiguous boundaries, such as embossing,…”
Get full text

Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold by Youngjoon Yoo, Sangdoo Yun, Hyung Jin Chang, Demiris, Yiannis, Jin Young Choi

“…This paper proposes a new high dimensional regression method by merging Gaussian process regression into a variational autoencoder framework. In contrast to…”
Get full text

Visual Path Prediction in Complex Scenes with Crowded Moving Objects by Youngjoon Yoo, Kimin Yun, Sangdoo Yun, Jonghee Hong, Hawook Jeong, Jin Young Choi

“…This paper proposes a novel path prediction algorithm for progressing one step further than the existing works focusing on single target path prediction. In…”
Get full text

Attention-inspired moving object detection in monocular dashcam videos by Kimin Yun, Jongin Lim, Sangdoo Yun, Soo Wan Kim, Jin Young Choi

“…This paper proposes a moving object detection algorithm for a monocular dashcam mounted on a vehicle. To deal with dynamic changes of the scene from the…”
Get full text

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild by Moon, Gyeongsik, Choi, Hongsuk, Chun, Sanghyuk, Lee, Jiyoung, Yun, Sangdoo

“…Recovering 3D human mesh in the wild is greatly challenging as in-the-wild (ITW) datasets provide only 2D pose ground truths (GTs). Recently, 3D pseudo-GTs…”
Get full text

Category Attentional Search for Fast Object Detection by Mimicking Human Visual Perception by Hawook Jeong, Sangdoo Yun, Kwang Moo Yi, Jin Young Choi

“…In this paper, we propose a novel selective search method to speed up the object detection via category-based attention scheme. The proposed attentional…”
Get full text

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features by Yun, Sangdoo, Han, Dongyoon, Chun, Sanghyuk, Oh, Seong Joon, Yoo, Youngjoon, Choe, Junsuk

“…Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding…”
Get full text

A Comprehensive Overhaul of Feature Distillation by Heo, Byeongho, Kim, Jeesoo, Yun, Sangdoo, Park, Hyojin, Kwak, Nojun, Choi, Jin Young

“…We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the…”
Get full text

Optimization-based method removing highlights with flash/no-flash image by Choi, Jongwon, Yun, Sangdoo, Choi, Jin Young

“…This paper proposes an optimization-based method to remove highlights from specular surfaces without any special device other than a flash, or any limited…”
Get full text

Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels by Yun, Sangdoo, Oh, Seong Joon, Heo, Byeongho, Han, Dongyoon, Choe, Junsuk, Chun, Sanghyuk

“…ImageNet has been the most popular image classification benchmark, but it is also the one with a significant level of label noise. Recent studies have shown…”
Get full text

What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis by Baek, Jeonghun, Kim, Geewook, Lee, Junyeop, Park, Sungrae, Han, Dongyoon, Yun, Sangdoo, Oh, Seong Joon, Lee, Hwalsuk

“…Many new proposals for scene text recognition (STR) models have been introduced in recent years. While each claim to have pushed the boundary of the…”
Get full text

PaletteNet: Image Recolorization with Given Color Palette by Junho Cho, Sangdoo Yun, Kyoungmu Lee, Jin Young Choi

“…Image recolorization enhances the visual perception of an image for design and artistic purposes. In this work, we present a deep neural network, referred to…”
Get full text