M
Masaki Saito
Researcher at Tohoku University
Publications - 15
Citations - 726
Masaki Saito is an academic researcher from Tohoku University. The author has contributed to research in topics: Deep learning & Belief propagation. The author has an hindex of 10, co-authored 15 publications receiving 515 citations.
Papers
More filters
Proceedings ArticleDOI
Temporal Generative Adversarial Nets with Singular Value Clipping
TL;DR: A generative model which can learn a semantic representation of unlabeled videos, and is capable of generating videos, is proposed, and a novel method to train it stably in an end-to-end manner is proposed.
Journal ArticleDOI
Train Sparsely, Generate Densely: Memory-Efficient Unsupervised Training of High-Resolution Temporal GAN
TL;DR: This study presents a novel memory efficient method of unsupervised learning of high-resolution video dataset whose computational cost scales only linearly with the resolution.
Proceedings ArticleDOI
ChainerCV: a Library for Deep Learning in Computer Vision
TL;DR: ChainerCV as mentioned in this paper is a software library that supports numerous neural network models as well as software components needed to conduct research in computer vision, including object detection and semantic segmentation.
Proceedings ArticleDOI
Illustration2Vec: a semantic vector representation of illustrations
Masaki Saito,Yusuke Matsui +1 more
TL;DR: A semantic morphing algorithm that searches the intermediate illustrations that gradually connect two queries is proposed, so users can efficiently search for references with similar attributes from a large image collection.
Posted Content
TGANv2: Efficient Training of Large Models for Video Generation with Multiple Subsampling Layers
Masaki Saito,Shunta Saito +1 more
TL;DR: A novel method to efficiently train a Generative Adversarial Network (GAN) on high dimensional samples by introducing a differentiable subsampling layer which appropriately reduces the dimensionality of intermediate feature maps in the generator during training.