IEICE Technical Report

Online edition: ISSN 2432-6380

Pattern Recognition and Media Understanding

Workshop Date : 2026-03-24 - 2026-03-25 / Issue Date : 2026-03-17

PRMU2025-41
[Short Paper] Frequency-Aware Linear-Time Sequence Model for Image Super-Resolution
Reo Kanazawa, Naoshi Kaneko (Tokyo Denki Univ.)
pp. 1 - 4

PRMU2025-42
Sigmoid Functions and Their Binarization for Self-Attention in Image Classification
June Miwa (Univ. Tsukuba), Masaki Onishi (AIST)
pp. 5 - 10

PRMU2025-43

Adorno Leonardo, Minoru Mori (KAIT)
pp. 11 - 16

PRMU2025-44
Background Music Generation depending on Game Situation using Text-to-Music model
Tougo Fujisawa, Makoto Murakami (Toyo Univ.)
pp. 17 - 21

PRMU2025-45
(See Japanese page.)
pp. 22 - 27

PRMU2025-46
[Short Paper] Manpu-Guided Facial Emotion Recognition for Manga Characters
Toma Kusano, Naoshi Kaneko (Tokyo Denki Univ.)
pp. 28 - 31

PRMU2025-47
Improving the Accuracy of Material Identification of Joruri Puppet Head Using Correction of Identification Results by U-NET
Hiroyuki Ukida, Kazuma Hirata, Masahide Tominaga (Tokushima Univ.), Tomoyo Sasao (Reitaku Univ.), Kenji Terada (Tokushima Univ.)
pp. 32 - 37

PRMU2025-48
[Invited Talk] Social Signal Processing Bridging Cognition, Psychology, and Behavior -- From Pattern Recognition to Human Understanding, and Beyond to Social Understanding --
Shogo Okada (JAIST)
pp. 38 - 39

PRMU2025-49
Investigation of Worker Tracking Methods Using Omnidirectional Camera Images
Shozo Sato, Yusaku Asai (IPUT Nagoya)
pp. 40 - 45

PRMU2025-50
View-consistency Learning for Partially Overlapping Multi-view Action Recognition
Trung Thanh Nguyen (Nagoya Univ.), Yasutomo Kawanishi (RIKEN), Takahiro Komamizu, Ichiro Ide (Nagoya Univ.)
pp. 46 - 51

PRMU2025-51
Statistical Verification of Detection-Loss Precursors and Causal Hierarchy Analysis in Automatic Tracking for Formula Kite in Open-Water Environments -- Event-Based Operational Log Analysis in Formula Kite --
Koki Goto (Mie HS)
pp. 52 - 56

PRMU2025-52
Generating Consistent and High-Fidelity Visual Guides from Text Manuals using Video Diffusion Models
Shun Okamoto, Satoshi Iizuka, Kazuhiro Fukui (Tsukuba Univ.)
pp. 57 - 62

PRMU2025-53
Automatic Scoring of Answers using a Digital Compass for Geometric Construction Problems
Thanh-Nghia Truong, Hung Tuan Nguyen, Nam Tuan Ly (TUAT), Yoichi Tsuchida, Hiroshi Miyazawa, Tomo Asakura, Masamitsu Ito (WACOM), Toshihiko Horie (Ratta Global), Fumiko Yasuno (NIEPR), Masaki Nakagawa (TUAT)
pp. 63 - 67

PRMU2025-54
Building a pose estimation model based on the hierarchical structure using the transformer decoder
Kong Huijing, Makoto Murakami (Toyo univ)
pp. 68 - 72

PRMU2025-55
(See Japanese page.)
pp. 73 - 78

PRMU2025-56
Analysis of the Visual Capabilities of a Deep Neural Network Trained via Reinforcement Learning for Autonomous Behavior in a Virtual Environment
Naoko Kaneda, Sena Sato, Makoto murakami (Toyo univ)
pp. 79 - 83

PRMU2025-57
Local Structure-based Sample Selection for Active Learning under Class Imbalance and Open World Conditions
Toshihiro Takahashi, Shuhei Noda (Toshiba)
pp. 84 - 89

PRMU2025-58
Contrastive Learning Network for Zero-Shot Automatic Scoring of Very Short Answers
Tuan Nam Ly, Hung Tuan Nguyen, Thanh-Nghia Truong, Masaki Nakagawa (TUAT)
pp. 90 - 95

PRMU2025-59
A Preliminary Study on Coded Aperture Imaging for Mitigating Adversarial Attack
Yasura Yokogawa (Kagoshima Univ.), Hiroshi Kawasaki (Kyushu Univ.), Hajime Nagahara (Osaka Univ.), Satoshi Ono (Kagoshima Univ.)
pp. 96 - 101

PRMU2025-60
Investigating Factors Behind Accuracy Variations in Age and Gender Recognition: Effects of Methods, Datasets, and Class Imbalance
Takumi Ozaki, Masashi Nishiyama (Tottori Univ.)
pp. 102 - 107

PRMU2025-61
Evaluating Speaker-Specific Transcription in Multi-Speaker Conversation Videos Using LLMs with Temporal Facial Features
Yuta Kudo, Yilin Wen, Yusuke Sugano (U Tokyo)
pp. 108 - 113

PRMU2025-62
Egocentric Gaze Estimation via Neck-Mounted Camera
Haoyu Huang, Yoichi Sato (UTokyo)
pp. 114 - 119

PRMU2025-63
Surgical Suturing Skill Estimation Based on Suture Geometry and Video Data
Reo Tanaka, Yota Koshimoto, Hiroki Kajita, Mariko Isogawa (Keio Univ.)
pp. 120 - 125

PRMU2025-64
A Study of Point Cloud Segmentation Using Multi-View Stereo
Hikaru Saito, Shintaro Ito, Koichi Ito, Takafumi Aoki (Tohoku Univ.)
pp. 126 - 131

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