Takahiro Shindo

AI Engineer at SONY.

Research Topic : Artificial Intelligence & Signal Processing

Biography

I am an AI Engineer at SONY, specializing in AI development for SONY α.
Prior to this, I worked as a Research Assistant under Prof. Hiroshi Watanabe, focusing on Image Coding for Machines.
My research has been presented at international conferences such as ICIP, MMSP and CCNC.

I earned my B.E. and M.E. degrees from Waseda University, Tokyo, Japan, in 2023 and 2025, respectively.
In recognition of my academic achievements, I was honored with both the Department Award and the Major Award upon receiving each degree.
Additionally, as the top-ranked student in research achievements, I served as the departmental representative for diploma reception at the completion ceremony.

Main Project

Image Coding for Humans and Machines
[ project page ]

Experience

AI Engineer at SONY (Apr. 2025 - )

Diploma Recipient Representative (Mar. 2025)

NICT commissioned research (Sep. 2022 - Mar. 2025)

Internship: AI Researcher at SONY (Feb. 2024 - Mar. 2024)

Internship: AI Engineer at SONY (Aug. 2023 - Sep. 2023)

IEEE VCIP reviewer

IEEE ICME reviewer

Publication (International Conference)

1st author

Image Coding for Object Recognition Tasks Based on Contour Feature Learning with Flexible Object Selection
[ under review ]

Guided Diffusion for the Extension of Machine Vision to Human Visual Perception
[ under review ] arXiv

Delta-ICM: Entropy Modeling with Delta Function for Learned Image Compression
[ IEEE ICCE 2025 ] IEEE Xplore arXiv

Image Coding for Machines with Edge Information Learning Using Segment Anything
[ IEEE ICIP 2024 ] IEEE Xplore arXiv

Scalable Image Coding for Humans and Machines Using Feature Fusion Network
[ IEEE MMSP 2024 ] IEEE Xplore arXiv

Refining Coded Image in Human Vision Layer Using CNN-Based Post-Processing
[ IEEE GCCE 2024 ] IEEE Xplore arXiv

Object Detection Method for Drone Videos Using Optical Flow
[ IEVC 2024 ]

Image Coding for Machines with Object Region Learning
[ IEEE CCNC 2024 ] IEEE Xplore arXiv

VVC Extension Scheme for Object Detection Using Contrast Reduction
[ IEEE GCCE 2023 ] IEEE Xplore arXiv

Accuracy Improvement of Object Detection in VVC Coded Video Using YOLO-v7 Features
[ IEEE IICAIET 2023 ] IEEE Xplore arXiv

Super Resolution for QR Code Images
[ IEEE GCCE 2022 ] IEEE Xplore

2nd author

Neural Video Representation for Redundancy Reduction and Consistency Preservation
[ IEEE ICCE 2025 ] IEEE Xplore arXiv

Data Augmentation with 3D-rendered Models for Livestock Recognition Using Drone Footage
[ IEVC 2024 ]

Future Object Detection Using Frame Prediction
[ IEEE GCCE 2023 ] IEEE Xplore

Accuracy Consistency of Object Detection With Contrast Reduction by Pixel Value Limitation
[ IEEE GCCE 2023 ] IEEE Xplore

Novel CNN approach for video prediction based on FitVid
[ IWAIT 2023 ]

others

Classification in Japanese Sign Language Based on Dynamic Facial Expressions
[ IEEE GCCE 2024 ]

Integrating QR Code Characteristics Into Super-Resolution Method
[ IEEE GCCE 2024 ]

Publication (Domestic Conference, Japan)

1st author

Evaluation of Face Recognition Accuracy in Decoded Images for Machines vision
[ IPSJ national conv. 2025 ]

Assessing the Effectiveness of ICM Method for Privacy Protection
[ PCSJ 2024 ]

Video Representaion Based on Dynamic Shifts in Pixel Values
[ ITE annual conv. 2024 ]

Video Coding Scheme for YOLO-v7 Combining VVC and CNN
[ IEICE general conf. 2023 ]

A Method for Improving Object Detection Accuracy in Coding Noise Environment
[ PCSJ 2022 ]

2nd author

Video Frame Interpolation Using Pretrained Diffusion Model
[ IPSJ national conv. 2025 ]

A Study of Spatially and Temporally Consistent Video Representation
[ PCSJ 2024 ]

Scalable Image Coding for Humans and Machines Using Feature Differences
[ PCSJ 2024 ]

A Method for Video Frame Interpolation Using Cross-Frame Attention
[ ITE annual conv. 2024 ]

A Study on Future Object Detection Using YOLOV
[ IEICE general conf. 2023 ]

Education

Asano High School (Apr. 2015 - Mar. 2018)

Waseda University, Department of Communications and Computer Engineering (Apr. 2019 - Mar. 2023)

Waseda University, Department of Computer Science and Communications Engineeringy (Apr. 2023 - Mar. 2025)

Award

Waseda University, Department of Computer Science and Communications Engineeringy Award (Mar. 2025)

PCSJ 2024 Best Poster Award (Dec. 2024)

IEEE GCCE 2024 Presentation Award (Nov. 2024)

Waseda University, Department of Communications and Computer Engineering Award (Mar. 2023)

Acknowledgment

Research Funding

NICT (National Institute of Information and Communications Technology)
[ Commissioned research on information and communication technology ] number 05101

IISF (International Information Science Foundation)
[ 2024 Visiting Researcher Support Program ]

Waseda University (Center for Science and Engineering)
[ 2024 Overseas Research Travel Grant Program ]