5 citations · 8 across the 5 of their papers we have counts for
5 papers
Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation
Takahiko Furuya, Zhoujie Chen, Ryutarou Ohbuchi +1
Invariance against rotations of 3D objects is an important property in analyzing 3D point set data. Conventional 3D point set DNNs having rotation invariance typically obtain accur…
DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold
Takahiko Furuya, Ryutarou Ohbuchi
Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recent…
Vanishing of the Hochschild cohomology for some self-injective special biserial algebra of rank four
Takahiko Furuya, Takao Hayami
In this paper, we determine the dimensions of the Hochschild cohomology groups of some self-injective special biserial algebra whose Grothendieck group is of rank . This result…
Hochschild cohomology for a class of some self-injective special biserial algebras of rank four
Takahiko Furuya
In this paper, we construct an explicit minimal projective bimodule resolution of a self-injective special biserial algebra () whose Grothendieck group is of rank $…
Support varieties for modules over stacked monomial algebras
Takahiko Furuya, Nicole Snashall
In this paper we give necessary and sufficient conditions for the variety of a simple module over a (D,A)-stacked monomial algebra to be nontrivial. This class of algebras was intr…