Alert button
Picture for Sungrae Park

Sungrae Park

Alert button

SRFormer: Empowering Regression-Based Text Detection Transformer with Segmentation

Add code
Bookmark button
Alert button
Aug 21, 2023
Qingwen Bu, Sungrae Park, Minsoo Khang, Yichuan Cheng

Figure 1 for SRFormer: Empowering Regression-Based Text Detection Transformer with Segmentation
Figure 2 for SRFormer: Empowering Regression-Based Text Detection Transformer with Segmentation
Figure 3 for SRFormer: Empowering Regression-Based Text Detection Transformer with Segmentation
Figure 4 for SRFormer: Empowering Regression-Based Text Detection Transformer with Segmentation
Viaarxiv icon

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

Add code
Bookmark button
Alert button
Mar 21, 2022
Junbum Cha, Kyungjae Lee, Sungrae Park, Sanghyuk Chun

Figure 1 for Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Figure 2 for Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Figure 3 for Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Figure 4 for Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Viaarxiv icon

Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features

Add code
Bookmark button
Alert button
Nov 30, 2021
Byeonghu Na, Yoonsik Kim, Sungrae Park

Figure 1 for Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Figure 2 for Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Figure 3 for Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Figure 4 for Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Viaarxiv icon

BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents

Add code
Bookmark button
Alert button
Sep 10, 2021
Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park

Figure 1 for BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
Figure 2 for BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
Figure 3 for BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
Figure 4 for BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
Viaarxiv icon

RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image

Add code
Bookmark button
Alert button
Jul 23, 2021
Junyeop Lee, Yoonsik Kim, Seonghyeon Kim, Moonbin Yim, Seung Shin, Gayoung Lee, Sungrae Park

Figure 1 for RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image
Figure 2 for RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image
Figure 3 for RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image
Figure 4 for RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image
Viaarxiv icon

SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models

Add code
Bookmark button
Alert button
Jul 20, 2021
Moonbin Yim, Yoonsik Kim, Han-Cheol Cho, Sungrae Park

Figure 1 for SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models
Figure 2 for SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models
Figure 3 for SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models
Figure 4 for SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models
Viaarxiv icon

Domain Generalization Needs Stochastic Weight Averaging for Robustness on Domain Shifts

Add code
Bookmark button
Alert button
Feb 17, 2021
Junbum Cha, Hancheol Cho, Kyungjae Lee, Seunghyun Park, Yunsung Lee, Sungrae Park

Figure 1 for Domain Generalization Needs Stochastic Weight Averaging for Robustness on Domain Shifts
Figure 2 for Domain Generalization Needs Stochastic Weight Averaging for Robustness on Domain Shifts
Figure 3 for Domain Generalization Needs Stochastic Weight Averaging for Robustness on Domain Shifts
Figure 4 for Domain Generalization Needs Stochastic Weight Averaging for Robustness on Domain Shifts
Viaarxiv icon

Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching

Add code
Bookmark button
Alert button
Feb 05, 2021
Mingi Ji, Byeongho Heo, Sungrae Park

Figure 1 for Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching
Figure 2 for Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching
Figure 3 for Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching
Figure 4 for Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching
Viaarxiv icon

Character Region Attention For Text Spotting

Add code
Bookmark button
Alert button
Jul 19, 2020
Youngmin Baek, Seung Shin, Jeonghun Baek, Sungrae Park, Junyeop Lee, Daehyun Nam, Hwalsuk Lee

Figure 1 for Character Region Attention For Text Spotting
Figure 2 for Character Region Attention For Text Spotting
Figure 3 for Character Region Attention For Text Spotting
Figure 4 for Character Region Attention For Text Spotting
Viaarxiv icon

CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks

Add code
Bookmark button
Alert button
Jun 11, 2020
Youngmin Baek, Daehyun Nam, Sungrae Park, Junyeop Lee, Seung Shin, Jeonghun Baek, Chae Young Lee, Hwalsuk Lee

Figure 1 for CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
Figure 2 for CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
Figure 3 for CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
Figure 4 for CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
Viaarxiv icon