論文 - 馬場口　登

Speech-driven Face Reenactment for a Video Sequence 査読

Y. Nakashima, T. Yasui, L. Nguyen, N. Babaguchi

ITE Transactions on Media Technology and Applications   8 ( 1 )   60 - 68   2020年1月

　詳細を見る

Online ISSN : 2186-7364

［招待講演］メディアクローン攻撃 招待

馬場口登

大阪大学工学研究科テクノアリーナ いきもの - AI共創工学、大阪大学吹田キャンパス   2019年12月

Anonymization of Gait Silhouette Video by Perturbing Its Phase and Shape Components 査読

Y. Hirose, K. Nakamura, N. Nitta, N. Babaguchi

Proc.of Asia-Pacific Signal and Processing Association Annual Summit and Conference (APSIPA ASC 2019)   2019年11月

Discrimination between Handwritten and Computer-Generated Texts using a Distribution of Patch-Wise Font Features 査読

N. Hamasaki, K. Nakamura, N. Nitta, N. Babaguchi

Proc. of Asia-Pacific Signal and Processing Association Annual Summit and Conference (APSIPA ASC 2019)   2019年11月

Generating Spoofing Tweets considering Points of Interest of Target User 査読

J. Lim, N. Nitta, K. Nakamura, N. Babaguchi

Proc. of Asia-Pacific Signal and Processing Association Annual Summit and Conference (APSIPA ASC 2019)   2019年11月

Discrimination between Genuine and Cloned Gait Silhouette Videos via Autoencoder-based Training Data Generation 査読

Y. Hirose, K. Nakamura, N. Nitta, N. Babaguchi

IEICE Transactions on Information and Systems   E102.D ( 12 )   2535 - 2546   2019年9月

［解説］認識サービスの運用：認識器クローンに対する防御法 招待

中村和晃, 新田直子, 馬場口登

MEDICAL IMAGING TECHNOLOGY   37 ( 4 )   188 - 193   2019年9月

［解説］内心プライバシー情報の流出を防ぐ画像認識フレームワークの開発 招待

中村和晃, 新田直子, 馬場口登

画像ラボ   30 ( 6 )   12 - 19   2019年6月

Constructing Geographic Dictionary from Streaming Geotagged Tweets 査読

J. Lim, N. Nitta, K. Nakamura, N. Babaguchi

ISPRS International Journal on Geo-Information   8 ( 5 )   Article No. 216 - 24 pages   2019年5月

Encryption-Free Framework of Privacy-Preserving Image Recognition for Photo-Based Information Services 査読

K. Nakamura, N. Nitta, N. Babaguchi

IEEE Transactions on Information Forensics and Security   14 ( 5 )   1264 - 1279   2019年5月

A logical consideration on deceived person's thinking 査読

S. Myojin, N. Babaguchi

ARTIFICIAL LIFE AND ROBOTICS   24 ( 1 )   114 - 118   2019年3月

　詳細を見る

The problem that old people are sometimes deceived by means of remittance fraud has become a great concern in our society. In this paper, we consider deceived person's thinking using Barwise-Seligman's framework, which is a logic for representing distributed systems among people or artifacts. The framework has been used to consider the conversation with comical misconception. We think that it is similar to remittance fraud because in telephone conversation, a criminal of the fraud uses victim's misconception so that the criminal can impersonate somebody. In this paper, we consider a logical system to describe the communication of a typical remittance fraud, and discuss the representative ability of the formulas to express the situation where a person is deceived or not deceived. The formulas have indicated that a person may be deceived as a result of handling exceptions in terms of logic. This paper contributes to providing a novel viewpoint to consider why people are deceived.

Semiotic and Logical Approach for Analysis of Augmented World 査読

S. Myojin, N. Babaguchi

Proc. of 12th Asia Pacific Workshop on Mixed and Augmented Reality (APMAR2019)   2019年3月

Modeling deceptive communication based on information flow 査読

S. Myojin, N. Babaguchi

Proc. of International Symposium on Artificial Life and Robotics, AROB 24th 2019   2019年1月

A Comic-Style Chat System with Japanese Expression Techniques for More Expressive Communication. 査読

J. Itou, K. Matsumura, J. Munemori, N. Babaguchi

Collaboration Technologies and Social Computing - 25th International Conference(CRIWG/CollabTech)   172 - 187   2019年

TRAINING-FREE METHOD FOR GENERATING MOTION VIDEO CLONES FROM A STILL IMAGE CONSIDERING SELF-OCCLUSION OF HUMAN BODY 査読

T. Tsutsumi, K. Nakamura, S. Myojin, N. Nitta, N. Babaguchi

2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)   509 - 513   2019年

　詳細を見る

In this paper, we propose a method for generating photorealistic video in which a person virtually performs a motion that is not performed in the real world. we refer to such video as motion video clones (MVCs). The proposed method requires only two kinds of source information as input data: a reference video, in which a person A performs some motion, and a target image, which includes the whole body of another person B. Using these data, our method generates a MVC in which the person A's motion is re-enacted by the person B's body. Since our method does not need 3D human body model nor any training phase, it is suitable to MVC-based entertainment systems. To handle the self-occlusion of the human body in the reference video, we employ a part-based approach. For each part such as the right arm and the left leg, we first extract its skeleton from the target image and move it so that the motion represented by the reference video is re-enacted. Next, we compute a 2D affine transform between the original and moved positions of the skeleton. This transform is used to map the texture of the target image onto each frame of a resultant MVC. Finally, we extend the part-wise affine transforms to pixel-wise ones by computing their linear combination for each pixel, whose combination weights are computed according to the geodesic distance between the pixel and the center of each part. This allows us to avoid unnatural appearance around the joints of the body parts. In our experiments, the proposed method generated much visually-natural MVCs than existing methods.

Passive Video Forgery Detection Considering Spatio-Temporal Consistency 査読

K. Kono, T. Yoshida, S. Ohshiro, N. Babaguchi

Proceedings of 14th International Conference on Information Assurance and Security   2018年12月

［招待講演］メディアクローンによるサイバー／フィジカル攻撃－情報トラストの新しい道－ 招待

馬場口登

2018年12月

　詳細を見る

紫翠会第９３３回例会，関西電力本店

Initial Consideration on Human Factor in Security Incident 査読

S. Myojin, N. Babaguchi

Proc. of The 13th International Workshop on Security   2018年9月

Generating Handwritten Character Clones from an Incomplete Seed Character Set using Collaborative Filtering 査読

K. Nakamura, E. Miyazaki, N. Nitta, N. Babaguchi

Proc. of International Conference on Frontiers in Handwriting Recognition   68 - 73   2018年8月

マイクロブログからの関連実世界観測情報の抽出 査読

新田直子, 吉武真人, 中村和晃, 馬場口登

日本データベース学会和文論文誌   vol.16-J   Article No. 22 - 8 pages   2018年3月

　詳細を見る

8 pages