Picture for Geewook Kim

Geewook Kim

CREPE: Coordinate-Aware End-to-End Document Parser

May 01, 2024
Figure 1 for CREPE: Coordinate-Aware End-to-End Document Parser
Figure 2 for CREPE: Coordinate-Aware End-to-End Document Parser
Figure 3 for CREPE: Coordinate-Aware End-to-End Document Parser
Figure 4 for CREPE: Coordinate-Aware End-to-End Document Parser
Viaarxiv icon

HyperCLOVA X Technical Report

Add code
Apr 13, 2024
Viaarxiv icon

Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation

Add code
Jan 12, 2024
Viaarxiv icon

SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap

Add code
Sep 21, 2023
Figure 1 for SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
Figure 2 for SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
Figure 3 for SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
Figure 4 for SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
Viaarxiv icon

Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models

Add code
May 24, 2023
Figure 1 for Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Figure 2 for Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Figure 3 for Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Figure 4 for Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Viaarxiv icon

Technical Report on Web-based Visual Corpus Construction for Visual Document Understanding

Add code
Nov 07, 2022
Figure 1 for Technical Report on Web-based Visual Corpus Construction for Visual Document Understanding
Figure 2 for Technical Report on Web-based Visual Corpus Construction for Visual Document Understanding
Figure 3 for Technical Report on Web-based Visual Corpus Construction for Visual Document Understanding
Figure 4 for Technical Report on Web-based Visual Corpus Construction for Visual Document Understanding
Viaarxiv icon

Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching

Feb 23, 2022
Figure 1 for Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching
Figure 2 for Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching
Figure 3 for Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching
Figure 4 for Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching
Viaarxiv icon

Donut: Document Understanding Transformer without OCR

Add code
Nov 30, 2021
Figure 1 for Donut: Document Understanding Transformer without OCR
Figure 2 for Donut: Document Understanding Transformer without OCR
Figure 3 for Donut: Document Understanding Transformer without OCR
Figure 4 for Donut: Document Understanding Transformer without OCR
Viaarxiv icon

Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings

Add code
May 18, 2021
Figure 1 for Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings
Figure 2 for Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings
Figure 3 for Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings
Figure 4 for Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings
Viaarxiv icon

Cost-effective End-to-end Information Extraction for Semi-structured Document Images

Add code
Apr 16, 2021
Figure 1 for Cost-effective End-to-end Information Extraction for Semi-structured Document Images
Figure 2 for Cost-effective End-to-end Information Extraction for Semi-structured Document Images
Figure 3 for Cost-effective End-to-end Information Extraction for Semi-structured Document Images
Figure 4 for Cost-effective End-to-end Information Extraction for Semi-structured Document Images
Viaarxiv icon