Search Results for author: Shu Nakamura

Found 2 papers, 0 papers with code

DeePoint: Visual Pointing Recognition and Direction Estimation

no code implementations ICCV 2023 Shu Nakamura, Yasutomo Kawanishi, Shohei Nobuhara, Ko Nishino

The first is the introduction of a first-of-its-kind large-scale dataset for pointing recognition and direction estimation, which we refer to as the DP Dataset.

Quantization optimized with respect to the Haar basis

no code implementations9 Jan 2021 Shu Nakamura

We propose a method of data quantization of finite discrete-time signals which optimizes the error estimate of low frequency Haar coefficients.

Quantization

Cannot find the paper you are looking for? You can Submit a new open access paper.