IEICE Technical Report

Online edition: ISSN 2432-6380

Pattern Recognition and Media Understanding

Workshop Date : 2025-11-06 - 2025-11-07 / Issue Date : 2025-10-30

PRMU2025-7
Generation of Ponzo Illusion Images Using Controllable Diffusion Models
Yuki Miyamoto, Satoshi Iizuka, Kazuhiro Fukui (Tukuba Univ.)
pp. 1 - 6

PRMU2025-8
Musical Performance Video Generation Method Robust to Increasing Number of Instruments Using CLAP Features
Yusaku Nakanose, Katsufumi Inoue, Michifumi Yoshioka (Osaka Metropolitan Univ.)
pp. 7 - 12

PRMU2025-9
(See Japanese page.)
pp. 13 - 18

PRMU2025-10
(See Japanese page.)
pp. 19 - 24

PRMU2025-11
Development of a CNN Model that Identifies Small Areas with Elevated Traffic Accident Risk from Satellite Images
Kota Shigemi, Yuki Ono, Tsuyoshi Migita, Norikazu Takahashi (Okayama Univ.)
pp. 25 - 30

PRMU2025-12
Detection of Trees in Real Images Using YOLOv5 Trained on CG Images
Haruki Yoshida, Takahiro Kobayashi, Tsuyoshi Migita, Norikazu Takahashi (Okayama Univ.)
pp. 31 - 36

PRMU2025-13
Automatic Pitch Scene Detection from Monocular Amateur Baseball Videos -- A Two-Stage Framework with ROI Detection and Temporal Modeling --
Genki Hibiya, Kohei Torimi, Yoshimitsu Aoki (Keio Univ.)
pp. 37 - 42

PRMU2025-14
Laplacian Pyramid-Based Fewer-Shot Self-Supervised Image Recoloring for Deutan Color Vision Deficiency
Onhi Kato, Akira Kubota (Chuo Univ.)
pp. 43 - 48

PRMU2025-15
Feature Selection Methods for Stroke Scale
Soma Tabata (TDU), Junichi Kono (Hyogo Medical Univ.), Eisaku Maeda (TDU)
pp. 49 - 54

PRMU2025-16
[Short Paper] Development of a Benchmark for Evaluating Dimension Reduction Methods for Visualization
Masaya Ohga, Hitoshi Sakano (Shimane Univ)
pp. 55 - 56

PRMU2025-17
[Short Paper] Incorporating Self-Supervised Video Features and Word Distribution Matching into LLM-based Sign Language Translation
Yoshitaka Ando, Rei Kawakami (Science Tokyo)
pp. 57 - 61

PRMU2025-18
Proposal of a hand correction method by applying step-specified additional learning in image generation AI
Yuki Ryu, Kubota Akira (Chuo Univ.)
pp. 62 - 67

PRMU2025-19
(See Japanese page.)
pp. 68 - 73

PRMU2025-20
Individual Recognition Based on Motion Habit Analysis Using Skeletal Coordinates
Daiki Nishimura, Kunio Matsui (KIT)
pp. 74 - 78

PRMU2025-21
Investigating Line-symmetrical Sample k-means Algorithm for Skeleton-Based Clustering
Hiroto Miyabe, Shunsuke Yoneda, Michiko Inoue, Masashi Nishiyama (Tottori Univ.)
pp. 79 - 84

PRMU2025-22
Estimation and analysis of concentration level by analyzing gaze data
Keisuke Shigeno, Kunio Matsui (KIT)
pp. 85 - 90

PRMU2025-23
A study on improving class discriminability in scatter plots by maximizing perceptual color differences between neighboring points
Haruki Katsurada (Ryukoku Univ.), Jun Fujiki (Fukuoka Univ.), Yoshiaki Ueda (Ryukoku Univ.)
pp. 91 - 96

PRMU2025-24
Research on Adversarial Attack Strategies for Inducing Misclassification in Traffic Sign Recognition
Sena Takahashi (Shimane Univ), Xuping Huang (Shimane Univ/Tohoku Univ), Akinori Ito (Tohoku Univ)
pp. 97 - 101

Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan