activity
20182021
most citedRepresentation Learning with Weighted Inner Product for Universal Approximation of General Similarities

2 citations · 2 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CL2021

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

Wonseok Hwang, Hyunji Lee, Jinyeong Yim +2

A real-world information extraction (IE) system for semi-structured document images often involves a long pipeline of multiple modules, whose complexity dramatically increases its…

cs.LG2020

Stochastic Neighbor Embedding of Multimodal Relational Data for Image-Text Simultaneous Visualization

Morihiro Mizutani, Akifumi Okuno, Geewook Kim +1

Multimodal relational data analysis has become of increasing importance in recent years, for exploring across different domains of data, such as images and their text tags obtained…

cs.CV2019

What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis

Jeonghun Baek, Geewook Kim, Junyeop Lee +5

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 technology, a holistic and fair…

cs.LG20192 cited

Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities

Geewook Kim, Akifumi Okuno, Kazuki Fukui +1

We propose (WIPS) for neural network-based graph embedding. In addition to the parameters of neural networks, we optimize the weights o…

stat.ML2018

Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability

Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira

We propose shifted inner-product similarity (SIPS), which is a novel yet very simple extension of the ordinary inner-product similarity (IPS) for neural-network based graph embeddi…

cs.CL2018

Segmentation-free Compositional -gram Embedding

Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira

We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated…