kent0304

llid_proto

Language Learning Image Description Feedback

duo34

English learning service using DUO 3.0

Text2ImageRetrieval

Extract matching images from the input text in the dataset by using the triplet margin loss function.

Amato-MUSIC

First prize in the Rakuten Hackathon. Connects people who are far away from each other through music.

nlp100_knock

AttnGAN

benesseHack

bmi-calculator-flutter

Learn to Code While Building Apps - The Complete Flutter Development Bootcamp

Clima-Flutter

Starter code for the Clima Project from the Complete Flutter Development Bootcamp

co-embedding

llid_baseline

Official implementation of Image Description Dataset for Language Learners (LREC 2022)

cookpad-internship-2020-summer-pbl

Developed in a day during my summer internship at Cookpad. Photo sharing app for food you've cooked.

DesignSystemLab

MLP model developed in the Design Systems Laboratory that predicts user needs satisfaction from product design variables.

errant

ERRor ANnotation Toolkit: Automatically extract and classify grammatical errors in parallel original and corrected sentences.

fast-gector

gector

Official implementation of the paper “GECToR – Grammatical Error Correction: Tag, Not Rewrite” // Published on BEA15 Workshop (co-located with ACL 2020) https://www.aclweb.org/anthology/2020.bea-1.16.pdf

get-dream

予約困難な東京ディズニーリゾートの予約を自動化

GLACNet

k3ntblog

Personal blog powered by Gatsby.js.

kent0304.github.io

🦧 Self-description portfolio site

mmf

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

PyTorchTutorial

semantic-scoring

Automatic Scoring for Picture Description

sheepfold

StoryGAN

StoryGAN: A Sequential Conditional GAN for Story Visualization

text2video

Text to Video Generation Problem

twitter

React + Redux + Firebase

UNITER

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

visualbert

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

VL-BERT

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".