Myungsub Choi myungsub

Vision & Language

Ask Your Neurons: A Neural-Based Approach to Answering Questions About Images
- Mateusz Malinowski, Marcus Rohrbach, Mario Fritz
Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books
- Yukun Zhu, Ryan Kiros, Rich Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler
Learning Query and Image Similarities With Ranking Canonical Correlation Analysis
Wah Ngo

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [Paper]

Shaoqing Ren, USTC; Kaiming He*, Microsoft Research Asia; Ross Girshick, Microsoft Research; Jian Sun, Microsoft Research Asia

Ke SUN*, University of Geneva; Jun Wang, Expedia, Geneva; Alexandros Kalousis, ; Stephane Marchand-Maillet, University of Geneva

Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning

J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, “The german traffic sign recognition benchmark: A multi-class classification competition,” in Proc. IJCNN, 2011, pp. 1453–1460. [Online]
J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, "Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition,” Neural Netw., vol. 32, pp. 323–332, Aug. 2012. [Online]

** Recognition **

Sermanet, P. and LeCun, Y. (2011). Traffic sign recognition with multi-scale convolutional networks. In Proceedings of the IEEE International Joint Conference on Neural Networks, pages 2809–2813. IEEE Press.
Ciresan, D. C., Meier, U., Masci, J., and Schmidhuber, J. (2011). A committee of neural networks for traffic sign classification. In Proceedings of the IEEE Internationa

$$ E = mc^2 $$ I want this equation $ \alpha = \beta + \gamma $ to render correctly

Self-Transfer Learning for Fully Weakly Supervised Object Localization
- by Sangheum Hwang and Hyo-Eun Kim (both from Lunit)
- Arxiv:1602, MICCAI 2016
- Datasets used: KIT(training), Shenzhen(test), MC set(test)
  - Localization annotation is obtained by human clinicians
LEARNING TO DIAGNOSE FROM SCRATCH BY EXPLOITING DEPENDENCIES AMONG LABELS [paper]
- Li Yao, Eric Poblenz, Dmitry Dagunts, Ben Covington, Devon Bernard, Kevin Lyman
- Arxiv:1710
Learning to detect chest radiographs containing lung nodules using visual attention networks [paper]
Emanuele Pesce, Petros-Pavlos Ypsilantis, Samuel Withey, Robert Bakewell, Vicky Goh, Giovanni Montana

NIPS 2017

Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks
Prototypical Networks for Few-shot Learning
Good Semi-supervised Learning That Requires a Bad GAN
Neural Discrete Representation Learning
Learning Disentangled Representations with Semi-Supervised Deep Generative Models

	cjson = require 'cjson'
	f = io.open(filename, 'r')
	text = f:read()
	info = cjson.decode(text)

	-- 'info' is a table containing everything
	-- info.all_losses
	-- info.iter
	-- info.loss_history
	-- info.results_history

	# Jupyter Notebook Tutorial
	https://www.digitalocean.com/community/tutorials/how-to-set-up-a-jupyter-notebook-to-run-ipython-on-ubuntu-16-04