• Publications
  • Influence
Generating images with recurrent adversarial networks
Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual quality. We show thatExpand
  • 156
  • 12
  • Open Access
AudioCaps: Generating Captions for Audios in The Wild
We explore the problem of audio captioning1: generating natural language description for any kind of audio in the wild, which has been surprisingly unexplored in previous research. We contribute aExpand
  • 10
  • 3
  • Open Access
Generative Adversarial Parallelization
Generative Adversarial Networks (GAN) have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable ofExpand
  • 20
  • 1
  • Open Access
Generative Adversarial Metric
  • 8
  • 1
Product-Service Systems (PSS) Design Process and Design Support Systems
This paper presents a new PSS design process and associated design support systems being developed by the PSS Design Project Consortium sponsored by the Korean Ministry of Knowledge Economy. SixExpand
  • 8
  • 1
Variational Laplace Autoencoders
Variational autoencoders (Kingma & Welling, 2014) employ an amortized inference model to approximate the posterior of latent variables. However, such amortized variational inference faces twoExpand
  • 3
  • Open Access
Video Question Answering with Spatio-Temporal Reasoning
Vision and language understanding has emerged as a subject undergoing intense study in Artificial Intelligence. Among many tasks in this line of research, visual question answering (VQA) has been oneExpand
  • 1
Imbalanced Continual Learning with Partitioning Reservoir Sampling
Continual learning from a sequential stream of data is a crucial challenge for machine learning research. Most studies have been conducted on this topic under the single-label classification settingExpand