Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Rikio Onai"'
Publikováno v:
IEEE Access, Vol 6, Pp 49040-49055 (2018)
Human action recognition is a challenging problem, especially in the presence of multiple actors in the scene and/or viewpoint variations. In this paper, three modalities, namely, 3-D skeletons, body part images, and motion history image (MHI), are i
Externí odkaz:
https://doaj.org/article/713ae66707a6456f9744bc0fff2ada98
Publikováno v:
IEEE Access, Vol 6, Pp 49040-49055 (2018)
Human action recognition is a challenging problem, especially in the presence of multiple actors in the scene and/or viewpoint variations. In this paper, three modalities, namely, 3-D skeletons, body part images, and motion history image (MHI), are i
Publikováno v:
ACM Transactions on Graphics. 34:1-10
We propose a method of three-dimensional (3D) modeling of volumetric fluid phenomena from sparse multi-view images (e.g., only a single-view input or a pair of front- and side-view inputs). The volume determined from such sparse inputs using previous
Autor:
Makoto Okabe, Emi Anzai, Kazuhiko Yamashita, Kanako Nakajima, Yumi Iwakami, Rikio Onai, Kazuya Imaizumi
Publikováno v:
IEEJ Transactions on Electronics, Information and Systems. 135:505-512
Autor:
Takahiro Hayashi, Rikio Onai
Publikováno v:
Transactions of the Japanese Society for Artificial Intelligence. 30:102-111
Publikováno v:
BigMM
Recently, many people have begun to take pictures of meals and food either at home or in restaurants. These pictures are then uploaded to social networking services (SNS) where they are shared with friends. People want to take pictures of food that l
Publikováno v:
Computer Graphics Forum. 30:1973-1982
We present a method for synthesizing fluid animation from a single image, using a fluid video database. The user inputs a target painting or photograph of a fluid scene along with its alpha matte that extracts the fluid region of interest in the scen
Autor:
Takahiro Hayashi, Rikio Onai
Publikováno v:
IEEJ Transactions on Sensors and Micromachines. 129:173-180
This paper presents a support system for motion training for dances, sports, gestures, etc. In our previous study, we developed a prototype system for supporting motion training using motion caputure, i.e., marker tracking using a DV camera. The prot
Publikováno v:
Journal of Advanced Computational Intelligence and Intelligent Informatics. 11:61-70
This paper reports a new method for retrieving landscape images using a sketch and icons as a query. Based on the proposal, first, a user sketches lines expressing contours of landscape elements such as mountains and forests and attaches icons expres
Publikováno v:
SIGGRAPH Asia Mobile Graphics and Interactive Applications
Recently, many people take a picture of foods at home or in restaurants, and upload the picture to a social networking service (SNS) to share it with friends. People want to take a delicious-looking picture of foods, but it is often difficult, becaus