| Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-19
13:15 |
Hokkaido |
|
Improving Visual–Knowledge Integration in MLLMs via Hidden-State Editing Guided by Output Token Probabilities
Masaya Sato, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-19
13:30 |
Hokkaido |
|
A Note on Improving Training of a Bridge-Inspection-Specific MLLM
-- Accuracy Gains via Data Augmentation and Loss Redesign --
Masaya Sato, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-19
14:30 |
Hokkaido |
|
A Note on Object-Aware Dataset Distillation with Adaptive Patch Selection
Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-19
14:45 |
Hokkaido |
|
A Note on Active Learning Combining Noisy Label Learning and Coreset Selection in the Presence of Label Noise
Masaki Kashiwagi, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-19
15:45 |
Hokkaido |
|
A Note on Automated Dataset Construction for Composed Video Retrieval in Soccer
-- Improvement of MLLM-based Dataset Evaluation via Prompt Tuning --
Riku Yoshida, Ryota Goka, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
09:10 |
Hokkaido |
|
[Special Talk]
Development and operation of Hokkaido University's Digital Reskilling Program
-- Review of phase 2 and current progress in phase 3 --
Hisashi Ukawa, Takahiro Ogawa, Keisuke Maeda, Keigo Sakurai, Yusuke Mizutani, Katsutoshi Kondo, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
09:25 |
Hokkaido |
|
[Special Talk]
Activities of the Regional Problem-Solving Course within Hokkaido University's Digital Reskilling Program
Keisuke Maeda, Guang Li, Takahiro Ogawa, Katsutoshi Kondo, Hisashi Ukawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
10:30 |
Hokkaido |
|
[Special Talk]
Anomaly Detection Using Semantic Segmentation Model and Large Vision-Language Model for Efficient Daily Inspection on Highways
Ren Tasai, Xiang Li, Ryota Goka, Naoki Saito, Keisuke Maeda (Hokkaido Univ.), Fumiyuki Kamada (Nexco-Engineering Hokkaido), Ryushi Kubo (NEXCO-East Engineering), Yuji Kawasaki (East Nippon Expressway Kanto Regional Head Office), Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
10:40 |
Hokkaido |
|
[Special Talk]
Crack Detection Technology from High-Speed Camera Images for Efficient Daily Inspection on Highways
Ziwen Lan, Keisuke Maeda, Naoki Saito (Hokkaido Univ.), Fumiyuki Kamada (Nexco-Engineering Hokkaido), Ryushi Kubo (NEXCO-East Engineering), Yuji Kawasaki (East Nippon Expressway Kanto Regional Head Office), Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
10:50 |
Hokkaido |
|
[Special Talk]
Introduction of a Depth Estimation–Based Position Control Mechanism Toward Realizing an Autonomous UAV for Efficient Roadside Object Inspection
Tasuku Nakajima, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
11:00 |
Hokkaido |
|
[Special Talk]
Extending Finding Generation AI Based on In-context Learning for Adaptation to the 2024 Bridge Inspection Guidelines
Masaya Sato, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
11:10 |
Hokkaido |
|
[Special Talk]
A Note on Motion Recognition for Tire Inspection Based on Motion Caption Generation for Local Regions in Video
Kyohei Kamikawa, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
11:20 |
Hokkaido |
|
[Special Talk]
A Note on Analyzing Relationships among Variables through Causal Discovery in Rubber Material Production Processes
Huaying Zhang, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(To be available after the conference date) [more] |
|
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-20
14:45 |
Hokkaido |
|
A Note on an Object-Centric Metric for 3D Scenes Based on Open-Vocabulary Object Detection Models
Yuiko Uchida, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
|
| ME, AIT, MMS, IEICE-IE, IEICE-ITS, SIP [detail] |
2025-02-18
10:30 |
Hokkaido |
Hokkaido Univ. |
A Note on Performance Improvement of Visual Emotion Classification via Multimodal LLM Introducing Text Prompt Optimization
Ryo Takahashi, Naoki Saito, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2025-3 ME2025-3 AIT2025-3 SIP2025-3
pp.13-17 |
| ME, AIT, MMS, IEICE-IE, IEICE-ITS, SIP [detail] |
2025-02-18
10:45 |
Hokkaido |
Hokkaido Univ. |
A Note on Image-to-music Generation via Musical Caption Based on In-context Learning
Shilin Liu, Kyohei Kamikawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2025-4 ME2025-4 AIT2025-4 SIP2025-4
pp.18-22 |
| ME, AIT, MMS, IEICE-IE, IEICE-ITS, SIP [detail] |
2025-02-18
12:50 |
Hokkaido |
Hokkaido Univ. |
A Note on Interpretability of Visual Language Model by Few-shot Learning based on the Linear Representation Hypothesis
Hiroki Okamura, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Visual language models (VLMs), pre-trained on vast amounts of web-based images and text, have demonstrated impressive ze... [more] |
MMS2025-7 ME2025-7 AIT2025-7 SIP2025-7
pp.34-39 |
| ME, AIT, MMS, IEICE-IE, IEICE-ITS, SIP [detail] |
2025-02-18
13:35 |
Hokkaido |
Hokkaido Univ. |
Effectiveness Verification of Introducing Model Merging in Federated Learning
-- Investigation from Multi-domain Image Classification Tasks --
Kenta Kubota, Reb Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
In this paper, we evaluate the effectiveness of model merging methods for federated learning, which continuously update ... [more] |
MMS2025-10 ME2025-10 AIT2025-10 SIP2025-10
pp.52-56 |
| ME, AIT, MMS, IEICE-IE, IEICE-ITS, SIP [detail] |
2025-02-18
15:40 |
Hokkaido |
Hokkaido Univ. |
A Note on Sensitivity Evaluation of Novel View Synthesis Metrics in 3D Scenes with Limited Conditions
Haoyang Wang, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2025-17 ME2025-17 AIT2025-17 SIP2025-17
pp.86-90 |
| ME, AIT, MMS, IEICE-IE, IEICE-ITS, SIP [detail] |
2025-02-18
15:55 |
Hokkaido |
Hokkaido Univ. |
A Note on Personalized Anomaly Detection Based on Vision Language Model Using Image Prompt
Haruka Matsuda, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
This paper presents a personalized anomaly detection method based on the Vision Language Model (VLM) that utilizes image... [more] |
MMS2025-18 ME2025-18 AIT2025-18 SIP2025-18
pp.91-95 |
|