E
Eiichi Matsumoto
Researcher at University of Tokyo
Publications - 46
Citations - 1257
Eiichi Matsumoto is an academic researcher from University of Tokyo. The author has contributed to research in topics: Robot & Robot control. The author has an hindex of 13, co-authored 42 publications receiving 944 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.
Posted Content
Learning Discrete Representations via Information Maximizing Self-Augmented Training
TL;DR: The Information Maximizing Self-Augmented Training (IMSAT) method as mentioned in this paper uses data augmentation to impose the invariance on discrete representations and maximize the information-theoretic dependency between data and their predicted discrete representations.
Proceedings Article
Learning discrete representations via information maximizing self-augmented training
TL;DR: In IMSAT, data augmentation is used to impose the invari-ance on discrete representations and the predicted representations of augmented data points to be close to those of the original data points in an end-to-end fashion to maximize the information-theoretic dependency between data and their predicted discrete representations.
Proceedings ArticleDOI
Decomposing NeRF for Editing via Feature Field Distillation
TL;DR: The authors propose to distill the knowledge of off-the-shelf, self-supervised 2D image feature extractors such as CLIP-LSeg or DINO into a 3D feature field optimized in parallel to the radiance field.
Patent
Internal combustion engine with crankcase ventilation system
Eiichi Matsumoto,Tatsuo Aruga +1 more
TL;DR: An internal combustion engine with a crankcase ventilation system is shown in this paper, where a crankshaft is rotatably held in the crankcase and including a counterweight.