Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EMM |
2022-03-07 15:55 |
Online |
(Primary: Online, Secondary: On-site) (Primary: Online, Secondary: On-site) |
[Poster Presentation]
Video Forgery Detection Using a Robust Hashing Algorithm Shoko Niwa, Miki Tanaka, Hitoshi Kiya (Tokyo Metro. Univ.) EMM2021-102 |
In this paper, we propose a method to detect the editing of video signals using a robust hashing algorithm. The assumed ... [more] |
EMM2021-102 pp.58-63 |
EMM |
2022-03-07 16:35 |
Online |
(Primary: Online, Secondary: On-site) (Primary: Online, Secondary: On-site) |
Access Control of Vision Transformer models without performance degradation Ryota Iijima, Yuma Kinoshita, Hitoshi Kiya (Tokyo Metro. Univ.) EMM2021-104 |
In this paper, we propose a novel access control method to protect trained models from unauthorized access. Conventional... [more] |
EMM2021-104 pp.70-75 |
EMM |
2022-03-07 17:00 |
Online |
(Primary: Online, Secondary: On-site) (Primary: Online, Secondary: On-site) |
Extention of robust image classification system with Adversarial Example Detectors Miki Tanaka, Takayuki Osakabe, Hitoshi Kiya (Tokyo Metro. Univ.) EMM2021-105 |
In image classification with deep learning, there is a risk that an attacker can intentionally manipulate the prediction... [more] |
EMM2021-105 pp.76-80 |
EMM |
2022-03-08 10:25 |
Online |
(Primary: Online, Secondary: On-site) (Primary: Online, Secondary: On-site) |
[Poster Presentation]
Influence of Data Hiding in Etc-Image Classification with SVM Kosuke Abe, Shoko Imaizumi (Chiba Univ.), Hitoshi Kiya (Tokyo Metropolitan Univ.) EMM2021-112 |
Classification accuracy for Encryption-then-Comperssion (EtC) images by support vector machine(SVM) is comparable to tha... [more] |
EMM2021-112 pp.107-111 |
EA, SIP, SP, IPSJ-SLP [detail] |
2022-03-02 12:00 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Evaluating the robustness of signal processing-based pseudonymization using parameter optimization against inversion attack. Hiroto Kai (Tokyo Metro. Univ.), Shinnosuke Takamichi (The Univ. of Tokyo), Sayaka Shiota, Hitoshi Kiya (Tokyo Metro. Univ.) EA2021-82 SIP2021-109 SP2021-67 |
[more] |
EA2021-82 SIP2021-109 SP2021-67 pp.114-119 |
EA, SIP, SP, IPSJ-SLP [detail] |
2022-03-02 13:25 |
Okinawa |
(Primary: On-site, Secondary: Online) |
[Poster Presentation]
Multi-channel missing signals recovery using autoencoder for acoustic scene classification Yuki Shiroma, Yuma Kinoshita (Tokyo Metro. Univ.), Keisuke Imoto (Doshisha Univ.), Sayaka Shiota, Nobutaka Ono, Hitoshi Kiya (Tokyo Metro. Univ.) EA2021-86 SIP2021-113 SP2021-71 |
[more] |
EA2021-86 SIP2021-113 SP2021-71 pp.140-145 |
EMM |
2022-01-27 13:00 |
Online |
Online |
Enhancing robustness of image classification system with Adversarial Example Detector Takayuki Osakabe, Maungmaung Aprilpyone, Hitoshi Kiya (TMU) EMM2021-84 |
[more] |
EMM2021-84 pp.1-6 |
EMM |
2022-01-27 13:25 |
Online |
Online |
Access Control Using Feature Map Transformation With Secret Key for Object Detection Models Teru Nagamori, Hiroki Ito, MaungMaung AprilPyone, Hitoshi Kiya (Tokyo Metro. Univ.) EMM2021-85 |
In this paper, we propose an access control method for object detection models.
The use of transformed images or transf... [more] |
EMM2021-85 pp.7-12 |
EMM, EA, ASJ-H |
2021-11-15 09:00 |
Online |
Online |
[Poster Presentation]
A consideration of training datasets for universal detectors of CNN-generated images Miki Tanaka, Hitoshi Kiya (Tokyo Metro. Univ.) EA2021-32 EMM2021-59 |
Recent rapid advances in convolutional neural networks (CNNs) have made manipulating and generating images easy, so synt... [more] |
EA2021-32 EMM2021-59 pp.31-36 |
SIS, ITE-BCT |
2021-10-07 14:25 |
Online |
Online |
Block-wise Transformation with Secret Key for Adversary Robust Defence of SVM model Ryota Iijima, MaungMaung AprilPyone, Hitoshi Kiya (TMU) SIS2021-13 |
In this paper, we propose a method for implementing support vector machine (SVM) models that are robust against adversar... [more] |
SIS2021-13 pp.17-22 |
SP, IPSJ-SLP, IPSJ-MUS |
2021-06-19 15:00 |
Online |
Online |
Investigation on fine-tuning with image classification networks for deep neural network-based musical instrument classification Yuki Shiroma, Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya (TMU) SP2021-17 |
In this paper, we investigate abilities of channel conversion methods for fine-tuning with image classification networks... [more] |
SP2021-17 pp.75-79 |
EMM, IT |
2021-05-20 14:35 |
Online |
Online |
A universal detector of CNN-generated images based on properties of checkerboard artifacts Miki Tanaka, Hitoshi Kiya (Metro Univ.) IT2021-3 EMM2021-3 |
We propose a universal detector of images generated by using any CNNs to detect CNN-generated images.
We consider prope... [more] |
IT2021-3 EMM2021-3 pp.13-18 |
EMM, IT |
2021-05-21 14:00 |
Online |
Online |
An MSB Prediction-Based Method with Less Prediction Errors for Reversible Data Hiding in Encrypted Images Kotaro Yamamura, Shoko Imaizumi (Chiba Univ.), Hitoshi Kiya (Tokyo Metropolitan Univ.) IT2021-13 EMM2021-13 |
In this paper, we propose an MSB prediction-based reversible data hiding method in encrypted images. The proposed method... [more] |
IT2021-13 EMM2021-13 pp.72-77 |
EMM, IT |
2021-05-21 14:25 |
Online |
Online |
A reversible data hiding method with high flexibility in compressive encrypted images Ryota Motomura, Shoko Imaizumi (Chiba Univ.), Hitoshi Kiya (Tokyo Metropolitan Univ.) IT2021-14 EMM2021-14 |
In this paper, we propose a reversible data hiding method in encrypted images, where both the com-pression efficiency an... [more] |
IT2021-14 EMM2021-14 pp.78-83 |
EMM |
2021-03-05 09:30 |
Online |
Online |
An MSB Prediction-Based Method Using Linear Regression for Reversible Data Hiding in Encrypted Images Kotaro Yamamura, Ryoichi Hirasawa, Shoko Imaizumi (Chiba Univ.), Hitoshi Kiya (Tokyo Metropolitan Univ.) EMM2020-75 |
In this paper, we propose an MSB prediction-based reversible data hiding method using linear regression in encrypted dom... [more] |
EMM2020-75 pp.46-51 |
EMM |
2021-01-28 15:15 |
Online |
Online |
An Extension of MSB Prediction-Based Method for Reversible Data Hiding in Encrypted Images Ryoichi Hirasawa, Shoko Imaizumi (Chiba Univ.), Hitoshi Kiya (Tokyo Metropolitan Univ.) EMM2020-65 |
In this paper, we propose a high capacity MSB prediction-based method with sufficient reversibility for data hiding in e... [more] |
EMM2020-65 pp.25-30 |
SIS, ITE-BCT |
2020-10-01 10:50 |
Online |
Online |
Target-color correction method based on multi-color balance Teruaki Akazawa, Yuma Kinoshita, Hitoshi Kiya (Tokyo Metro. Univ.) SIS2020-12 |
In this paper, we propose a target-color correction method for reducing color changes caused by the different of lightin... [more] |
SIS2020-12 pp.11-16 |
SIS, ITE-BCT |
2020-10-01 13:00 |
Online |
Online |
Evaluation of linear dimensionality reduction methods considering visual information protection for privacy-preserving machine learning Masaki Kitayama, Nobutaka Ono, Hitoshi Kiya (Tokyo Metro. Univ.) SIS2020-13 |
In this paper, linear dimensionality reduction methods are evaluated in terms of difficulty in estimating the visual inf... [more] |
SIS2020-13 pp.17-22 |
SIS, ITE-BCT |
2020-10-01 13:20 |
Online |
Online |
Robustness Evaluation of Detectinon methods for Image manipulation with GANs Miki Tanaka, Hitoshi Kiya (Tokyo Metropolitan Univ.) SIS2020-14 |
Recent rapid advances in image manipulation tools and deep image synthesis techniques, such as Generative Adversarial Ne... [more] |
SIS2020-14 pp.23-28 |
SIS, IPSJ-AVM, ITE-3DMT [detail] |
2020-06-03 13:00 |
Online |
Online |
Luminance-Independent Hue Image Generation Method Based on CIELAB Color Space Yuma Kinoshita, Hitoshi Kiya (Tokyo Metro. Univ.) SIS2020-1 |
In this paper, we propose luminance-independent hue-image generation method based on the CIELAB color space, from RAW im... [more] |
SIS2020-1 pp.1-6 |