6 accepted papers
In this paper, we propose a novel graph convolutional network architecture, Graph Stacked Hourglass Networks, for 2D-to-3D human pose estimation tasks. The proposed architecture consists of repeated encoder-decoder, in which graph-structured features are processed across three different scales of hu…
This article describes a novel approach to classification of whole-body motions from estimated human postures in 2D camera images and subsequent generation of their relevant descriptions. The motions are encoded into stochastic motion models referred to as motion primitives. Words are connected to t
Humans perceive continuous high-dimensional information by dividing it into significant segments such as words and units of motion. We believe that such unsupervised segmentation is also important for robots to learn topics such as language and motion. To this end, we previously proposed a hierarchi…
In this paper, we investigate the relationship between the depth perception and an approaching motion toward an object. We propose the depth perception dependency test, which is the combination of tests of a motion and depth perception based on the situation that an object is placed on the human’s p…
This paper discusses video motion capture, namely, 3D reconstruction of human motion from multi-camera images. After the Part Confidence Maps are computed from each camera image, the proposed spatiotemporal filter is applied to deliver the human motion data with accuracy and smoothness for human mot…
Gesture recognition is used for many practical applications such as human-robot interaction, medical rehabilitation and sign language. In this paper, we apply a hybrid generative-discriminative approach by using the Fisher Vector to improve the recognition performance. The strategy is to merge the g…