Výsledky vyhledávání - "Shimada, Nobutaka"

Report

Vision + Language Applications: A Survey

Text-to-image generation has attracted significant interest from researchers and practitioners in recent years due to its widespread and diverse applications across various industries. Despite the progress made in the domain of vision and language re

Externí odkaz: http://arxiv.org/abs/2305.14598

Zobrazit plný text záznamu

Report

Construction of Latent Descriptor Space and Inference Model of Hand-Object Interactions

Autor: Matsuo, Tadashi, Shimada, Nobutaka

Publikováno v: IEICE Trans. on Info. and Sys., Vol.E100-D, No.6, pp.1350-1359, 2017

Appearance-based generic object recognition is a challenging problem because all possible appearances of objects cannot be registered, especially as new objects are produced every day. Function of objects, however, has a comparatively small number of

Externí odkaz: http://arxiv.org/abs/1709.03739

Zobrazit plný text záznamu

Report

Transform Invariant Auto-encoder

Autor: Matsuo, Tadashi, Fukuhara, Hiroya, Shimada, Nobutaka

The auto-encoder method is a type of dimensionality reduction method. A mapping from a vector to a descriptor that represents essential information can be automatically generated from a set of vectors without any supervising information. However, an

Externí odkaz: http://arxiv.org/abs/1709.03754

Zobrazit plný text záznamu