Tomokazu Sato
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tomokazu Sato has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Naokazu Yokoya
Graduate School of Information Science, Nara Instiutute of Science and Technology, 8916-5 Takayama, Ikoma, Nara, Japan
4 shared publications- Yuta Nakashima
Osaka University
3 shared publications - Antonio Tejero-De-Pablos
The University of Tokyo
1 shared publication - Esa Rahtu
Tampere University
1 shared publication - Fumio Okura
The University of Osaka
1 shared publication Marko Linna
Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland
1 shared publication
Latest Publications
- 1 August 2018
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 55, 56-66
Iterative applications of image completion with CNN-based failure detection
- 1 August 2018
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 55, 56-66
Iterative applications of image completion with CNN-based failure detection
- 15 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 20 (8) , 2000-2011
Summarization of User-Generated Sports Video by Using Deep Action Recognition Features
Automatically generating a summary of a sports video poses the challenge of detecting interesting moments, or highlights, of a game. Traditional sports video summarization methods leverage editing conventions of broadcast sports video that facilitate the extraction of high-level semantics. However, user-generated videos are not edited and, thus, traditional methods are not suitable to generate a summary. In order to solve this problem, this paper proposes a novel video summarization method that uses players' actions as a cue to determine the highlights of the original video. A deep neural-network-based approach is used to extract two types of action-related features and to classify video segments into interesting or uninteresting parts. The proposed method can be applied to any sports in which games consist of a succession of actions. Especially, this paper considers the case of Kendo (Japanese fencing) as an example of a sport to evaluate the proposed method. The method is trained using Kendo videos with ground truth labels that indicate the video highlights. The labels are provided by annotators possessing a different experience with respect to Kendo to demonstrate how the proposed method adapts to different needs. The performance of the proposed method is compared with several combinations of different features, and the results show that it outperforms previous summarization methods.
- 15 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 20 (8) , 2000-2011
Summarization of User-Generated Sports Video by Using Deep Action Recognition Features
Automatically generating a summary of a sports video poses the challenge of detecting interesting moments, or highlights, of a game. Traditional sports video summarization methods leverage editing conventions of broadcast sports video that facilitate the extraction of high-level semantics. However, user-generated videos are not edited and, thus, traditional methods are not suitable to generate a summary. In order to solve this problem, this paper proposes a novel video summarization method that uses players' actions as a cue to determine the highlights of the original video. A deep neural-network-based approach is used to extract two types of action-related features and to classify video segments into interesting or uninteresting parts. The proposed method can be applied to any sports in which games consist of a succession of actions. Especially, this paper considers the case of Kendo (Japanese fencing) as an example of a sport to evaluate the proposed method. The method is trained using Kendo videos with ground truth labels that indicate the video highlights. The labels are provided by annotators possessing a different experience with respect to Kendo to demonstrate how the proposed method adapts to different needs. The performance of the proposed method is compared with several combinations of different features, and the results show that it outperforms previous summarization methods.
- 28 October 2016
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 76 (9) , 12097-12115
Video summarization using textual descriptions for authoring video blogs
- 28 October 2016
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 76 (9) , 12097-12115
Video summarization using textual descriptions for authoring video blogs
- Open Access
- 1 January 2014
- Published by Institute of Image Information and Television Engineers in ITE Transactions on Media Technology and Applications
- Vol. 2 (1) , 82-93
[Paper] Free-viewpoint Mobile Robot Teleoperation Interface Using View-dependent Geometry and Texture
This paper proposes a free-viewpoint interface for mobile-robot teleoperation, which provides viewpoints that are freely configurable by the human operator head pose. The viewpoints are acquired by a head tracker equipped on a head mounted display. A real-time free-viewpoint image generation method based on view-dependent geometry and texture is employed by the interface to synthesize the scene presented to the operator. In addition, a computer graphics model of the robot is superimposed on the free-viewpoint images using an augmented reality technique. We developed a prototype system based on the proposed interface using an omnidirectional camera and depth cameras for experiments. The experiments under both virtual and physical environments demonstrated that the proposed interface can improve the accuracy of the robot operation compared with first- and third-person view interfaces, while the quality of the free-viewpoint images generated by the prototype system was satisfactory for expressing the potential advantages on operational accuracy
- 1 January 2014
- Published by Institute of Image Information and Television Engineers in ITE Transactions on Media Technology and Applications
- Vol. 2 (1) , 82-93
Open Access[Paper] Free-viewpoint Mobile Robot Teleoperation Interface Using View-dependent Geometry and Texture
This paper proposes a free-viewpoint interface for mobile-robot teleoperation, which provides viewpoints that are freely configurable by the human operator head pose. The viewpoints are acquired by a head tracker equipped on a head mounted display. A real-time free-viewpoint image generation method based on view-dependent geometry and texture is employed by the interface to synthesize the scene presented to the operator. In addition, a computer graphics model of the robot is superimposed on the free-viewpoint images using an augmented reality technique. We developed a prototype system based on the proposed interface using an omnidirectional camera and depth cameras for experiments. The experiments under both virtual and physical environments demonstrated that the proposed interface can improve the accuracy of the robot operation compared with first- and third-person view interfaces, while the quality of the free-viewpoint images generated by the prototype system was satisfactory for expressing the potential advantages on operational accuracy