seungjun45 Goto Github PK

ai607

Graph Mining and Social Networks!

avr_robot

A Robot (Autonomous Driving) building project with Jaeho Hwang (2013. 09 ~ 2014.08). We designed this robot from very basic by ourselves. We used Atmega128 with AVR Studio as Controller & System Supervisor, OpenCV (2.4.8) for Real-time Image Recognition (Stop, Start Sign and Arrow Direction Recognition), and Arduino Uno for Dead Reckoning Algorithm. Additional Sonar sensor and IR sensor are used in our robot. Here we provide source codes and some parts of demo video. Unfortunately, we could not implement SLAM in out robot, since we had no idea about the technique during our undergraduate.

cocoapi

Clone of COCO API - Dataset @ http://cocodataset.org/ - with changes to support Windows build and python3

cudnn_tmp

git-test

graph-rcnn.pytorch

Pytorch code for our ECCV 2018 paper "Graph R-CNN for Scene Graph Generation" and other papers

hamggae

Android App for Realtime Chatting

hbmp

Sentence Embeddings in NLI with Iterative Refinement Encoders

image-captioning-bottom-up-top-down

(modified) python3.0 version of bottom-up feature extractor

image-retargetting

My first year project under advisor Prof. Changick-Kim. Source Code open is not available (project funded by Hancom Company). Paper is published for this project.

knowledge-enabled-textual-entailment

Natural Language Inference is fundamental to many Natural Language Processing applications such as semantic search and question answering. The task of NLI has gained significant attention in the recent times due to the release of fairly large scale, challenging datasets. Present approaches that address NLI are largely focused on learning based on the given text in order to classify whether the given premise entails, contradicts, or is neutral to the given hypothesis. On the other hand, techniques for Inference, as a central topic in artificial intelligence, has had knowledge bases playing an important role, in particular for formal reasoning tasks. While, there are many open knowledge bases that comprise of various types of information, their use for natural language inference has not been well explored. In this work, we present a simple technique that can harnesses knowledge bases, provided in the form of a graph, for natural language inference.

mask-faster-rcnn

Mask R-CNN

mattnet

MAttNet: Modular Attention Network for Referring Expression Comprehension

nn

opengl_game

FOR MY FUN

patchwork

All the Git-it Workshop completers!

pytorch-yolov3-1

Minimal PyTorch implementation of YOLOv3

refer

Referring Expression Datasets API

rnn

Recurrent Neural Network library for Torch7's nn

roitransformer_dota

sana

Individual research with Hasan under advisor Prof. Changick Kim.

seal

SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction). "M. Zhang, Y. Chen, Link Prediction Based on Graph Neural Networks, NeurIPS 2018 spotlight".

self_attention_practice

Pytorch implementation of Squeeze_and_Excitation, Bottleneck_Attention_Module, and Convolutional_Block_Attention_Module : for EE898 class, KAIST

seq2seq2_kb_kaist

simsg

Semantic Image Manipulation using Scene Graphs

suspension-control

My undergraduate research with Professor Hyeongcheol Lee #ecsl.hanyang.ac.kr# (2013.01 ~ 2013.12). Project goal was developing control algorithm for trailing arm suspension in Armored Vehicle. Each trailing arm is controlled by electric motor, where controller outputs are electric signal. I solved this problem with the proposed method "Advanced Adaptive Linear Quadratic controller". Recurdyn (Multi-body Dynamics Simulator) is used for conducting experiment. Here, I provide simulink (MATLAB) file of the proposed controller.

updown-baseline

water-filling

My second year project under advisor Prof. Changick Kim (2015.09~2016.03). The technique is for removing illumination distortions for camera captured document images. Source Code Available