| Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
| IEICE-ITS, IEICE-IE, ME, AIT, MMS [detail] |
2024-02-19
10:45 |
Hokkaido |
Hokkaido Univ. |
A Note on Text to Image Generation Based on Stable Diffusion Using Brain Activity Data While Gazing on Image
-- Introduction of Controllable Mechanism with Brain Activity Data in Latent Space --
Ryo Shichida, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2024-3 ME2024-19 AIT2024-3
pp.13-17 |
| IEICE-ITS, IEICE-IE, ME, AIT, MMS [detail] |
2024-02-19
11:00 |
Hokkaido |
Hokkaido Univ. |
A Note on Improvement of Zero-shot Video Retrieval using LLM Description based on Multiple Image Captioning Models
Haoyang Wang, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Uni) |
[more] |
MMS2024-4 ME2024-20 AIT2024-4
pp.18-21 |
| IEICE-ITS, IEICE-IE, ME, AIT, MMS [detail] |
2024-02-19
13:30 |
Hokkaido |
Hokkaido Univ. |
A Note on Domain Adaptation by Setting Features of Interest in Visual Language Models
Hiroki Okamura, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
In this paper, we present a domain adaptation method for image classification using a visual-language model (VLM). Recen... [more] |
MMS2024-8 ME2024-24 AIT2024-8
pp.39-43 |
| IEICE-ITS, IEICE-IE, ME, AIT, MMS [detail] |
2024-02-20
11:00 |
Hokkaido |
Hokkaido Univ. |
[Special Talk]
Research for Next-generation Infrastructure Maintenance and Activity of Collaboration Agreement with Hokkaido Regional Development Bureau
Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2024-23 ME2024-39 AIT2024-23
pp.114-119 |
| IEICE-ITS, IEICE-IE, ME, AIT, MMS [detail] |
2024-02-20
11:15 |
Hokkaido |
Hokkaido Univ. |
[Special Talk]
Damage Detection Using Drone Videos of Road Attachments Based on Vision Transformer
Koshi Watanabe, Naoki Ogawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2024-24 ME2024-40 AIT2024-24
pp.120-123 |
| IEICE-ITS, IEICE-IE, ME, AIT, MMS [detail] |
2024-02-20
11:25 |
Hokkaido |
Hokkaido Univ. |
[Special Talk]
Technology of Findings Generation Based on Generative AI for Efficient Bridge Inspection
Yuto Watanabe, Naoki Ogawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2024-25 ME2024-41 AIT2024-25
pp.124-127 |
| IEICE-ITS, IEICE-IE, ME, AIT, MMS [detail] |
2024-02-20
11:35 |
Hokkaido |
Hokkaido Univ. |
[Special Talk]
Prediction of Event Locations from Urgent Call Using Speech Recognition and Generative AI
Masaki Yoshida, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido University) |
Operators handling road-related urgent calls are required to pinpoint the event location from information verbally commu... [more] |
MMS2024-26 ME2024-42 AIT2024-26
pp.128-131 |
| IEICE-ITS, IEICE-IE, ME, AIT, MMS [detail] |
2024-02-20
13:30 |
Hokkaido |
Hokkaido Univ. |
A Note on Action Estimation with Event Stream Data of Soccer Player Based on Bidirectional Transformer
Ryota Goka, Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2024-28 ME2024-44 AIT2024-28
pp.137-141 |
| MMS, ME, AIT, IEICE-IE, IEICE-ITS [detail] |
2023-02-21
10:30 |
Hokkaido |
Hokkaido Univ. |
A Note on Traffic Sign Recognition Based on Vision Transformer Adapter Using Visual Feature Matching
Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Traffic sign recognition is a real-world task that involves many constraints and complications. Traffic sign recognition... [more] |
MMS2023-1 ME2023-21 AIT2023-1
pp.1-4 |
| MMS, ME, AIT, IEICE-IE, IEICE-ITS [detail] |
2023-02-21
10:45 |
Hokkaido |
Hokkaido Univ. |
A Note on Multi-label Image Classification in Animation Illustration Considering Hierarchical Relationships of Attributes
Ziwen Lan, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
This paper presents a multi-label classification of animated illustrations considering the hierarchical relationships of... [more] |
MMS2023-2 ME2023-22 AIT2023-2
pp.5-9 |
| MMS, ME, AIT, IEICE-IE, IEICE-ITS [detail] |
2023-02-21
11:30 |
Hokkaido |
Hokkaido Univ. |
A Note on Accurate Shoot Prediction Considering Players' Spatio-temporal Relations in Soccer Videos
-- Introduction of Complete Bipartite Graph Based on Players' Team Information --
Ryota Goka, Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
This paper presents the introduction of a complete bipartite graph based on the team information of players for improvin... [more] |
MMS2023-5 ME2023-25 AIT2023-5
pp.23-28 |
| MMS, ME, AIT, IEICE-IE, IEICE-ITS [detail] |
2023-02-21
11:45 |
Hokkaido |
Hokkaido Univ. |
A Note on Improvement of Supervised Latent Variable Model with Graph-Encoded Class Information
Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Supervised latent variable models aim to estimate a manifold from original data and supervised information, such as clas... [more] |
MMS2023-6 ME2023-26 AIT2023-6
pp.29-33 |
| MMS, ME, AIT, IEICE-IE, IEICE-ITS [detail] |
2023-02-21
15:00 |
Hokkaido |
Hokkaido Univ. |
A Note on Specific Object Removal in Urban Scene Using Video Inpainting Approach
Jiahuan Zhang, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido University) |
[more] |
MMS2023-14 ME2023-34 AIT2023-14
pp.71-74 |
| MMS, ME, AIT, IEICE-IE, IEICE-ITS [detail] |
2023-02-21
16:00 |
Hokkaido |
Hokkaido Univ. |
A note on gaze-dependent image re-ranking for content-based image retrieval
Yuhu Feng, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2023-18 ME2023-38 AIT2023-18
pp.89-93 |
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-21
13:15 |
Online |
online |
A Note on Improvement of Accuracy in Classification of Distress Images for Efficient Inspection of Road Structures
-- Introduction of Ratio of Similar Cases Based on Text Data --
Taisei Hirakawa, Naoki Ogawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
In this paper, we propose a method for correcting the results of distress image classification using text data recorded ... [more] |
MMS2022-8 ME2022-33 AIT2022-8
pp.43-48 |
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-21
16:15 |
Online |
online |
A Note on Realizing Adversarial Defense Based on Regularization of Multi-stage Squeeze-and-Excitation Features
Jiahuan Zhang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Regularizing deep features is a common adversarial defense method. However, the existing methods do not further explore ... [more] |
MMS2022-17 ME2022-42 AIT2022-17
pp.87-90 |
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-21
17:00 |
Online |
online |
A Note on Interest level Estimation Using Users' Behavior Information
-- Validating the Effectiveness of Feature Integration with Multiple Users --
Kyohei Kamikawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
In this paper, we verify the effectiveness of feature integration with multi-user behavior information for interest leve... [more] |
MMS2022-20 ME2022-45 AIT2022-20
pp.103-107 |
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-21
13:55 |
Online |
online |
A Note on Multi-label Image Recognition in Anime Illustration Based on Graph Convolutional Networks Using Captioning Features
Ziwen Lan, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
[more] |
MMS2022-22 ME2022-47 AIT2022-22
pp.161-165 |
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-21
14:25 |
Online |
online |
A Note on Visual Sentiment Prediction Based on Few-shot Learning using Knowledge Distillation
Yingrui Ye, Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
The prediction of visual sentiment can be useful to understand users' behaviors. Emotion theories underlying the sentime... [more] |
MMS2022-24 ME2022-49 AIT2022-24
pp.171-175 |
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-21
14:40 |
Online |
online |
A Note on Inspection Action Classification Using First and Third Person Video of Engineers Inspecting Bridges
Tsuyoshi Masuda, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
In this paper, we propose an inspection action classification method using first and third person videos of engineers in... [more] |
MMS2022-25 ME2022-50 AIT2022-25
pp.177-180 |