Presentations -

A Study on Estimating Pedestrian Crossing Intentions Using First-Token Representations of VLM

横山 航大, Daisuke Deguchi, Seigo Ito, Hiroshi Murase

IEICE General Conference  2026.3.10 

　More details

Event date： 2026

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：九州産業大学  

Pedestrians' Gaze Object Estimation in Traffic Scene Considering Relationships Among Multiple Pedestrians International conference

Hiroyuki Tatsumi, Daisuke Deguchi, Seigo Ito, Hiroshi Murase

International Workshop on Advanced Image Technology (IWAIT) 2026  2026.1.12 

　More details

Event date： 2026

Language：English   Presentation type：Oral presentation (general)  

Venue：高雄福華ホテル，台湾  

Instance Segmentation in Densely Packed Environments

坂口 駿哉, Daisuke Deguchi, Hiroshi Murase, Seigo Ito

IEICE General Conference  2026.3.9 

　More details

Event date： 2026

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：九州産業大学（福岡市）  

A study on Frame Alignment in Train Front-View Videos via Local Spatial Embeddings

関剛志, Daisuke Deguchi, Seigo Ito, Hiroshi Murase, Hiroki Mukoujima, Nozomi Nagamine

IEICE General Conference  2026.3.9 

　More details

Event date： 2026

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：九州産業大学  

3D Pose Estimation from Human Silhouette Images

長江 和馬, Daisuke Deguchi, Hiroshi Murase, Seigo Ito

IEICE General Conference  2026.3.9 

　More details

Event date： 2026

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：九州産業大学  

講義スライドのコンテンツ解析に基づく講義動画の自動生成に関する予備検討

水上 皓太, 出口 大輔, 久徳 遙矢, 峰松 翼, 村瀬 洋

教育学習支援情報システム研究会(CLE)  2025.3.21 

　More details

Event date： 2025

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：群馬大学  

Multi-group Vision Semantic Centroid for Semantic Segmentation International conference

Jialei Chen, Daisuke Deguchi, Chenkai Zhang, Zhenzhen Quan, Seigo Ito, Hiroshi Murase

Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2025)  2025.2.18 

　More details

Event date： 2025

Language：English   Presentation type：Oral presentation (general)  

Venue：Sogang University, Seoul, Korea  

Multi-media processing has achieved great success based on
semantic segmentation. Semantic segmentation can be viewed as pixel-
clustering based on semantic prototypes. However, existing methods fo-
cus more on consistent semantics while ignoring the consistency in vi-
sion, making this task challenging. Motivated by the success of discrete
visual representation learning, we propose Multi-group Visual Semantic
Centroid (MVSC) to better cluster the pixels while maintaining consis-
tent semantics of the dense features for any image encoder. Specifically,
we randomly initialize multiple groups of prototypes as multi-groups in
visual space. The visual features are also randomly split into the same
groups and forced to be aligned with the corresponding prototypes. Then
these visual prototypes are projected into the semantic space and super-
vised by the same classifier as the dense features. Compared with existing
methods, MVSC further considers the visual space and thus facilitates
the task. Experimental results on COCO-Stu! show great improvements
compared with previous methods.

A Cross-Modal Knowledge Distillation Approach for RGB-to-Infrared Video Action Recognition International conference

Zhenzhen Quan, Daisuke Deguchi, Jialei Chen, Chenkai Zhang, Yujun Li, Seigo Ito, Hiroshi Murase

Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2025)  2025.2.18 

　More details

Event date： 2025

Language：English   Presentation type：Oral presentation (general)  

Object Detection using In-Vehicle Camera Images with Object Attributes Constraints

星谷那月, Daisuke Deguchi, Jialei Chen, Hiroshi Murase, 伊藤誠悟

IEICE Technical Report (MVE)  2025.3.5 

　More details

Event date： 2025

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：沖縄県市町村自治会館  

複数歩行者間のインタラクション理解に向けた 気づき認識データセットの構築

辰己弘征, 出口 大輔, 村瀬 洋, 伊藤誠悟

メディアエクスペリエンス・バーチャル環境基礎研究会(MVE)  2025.3.5 

　More details

Event date： 2025

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：沖縄県市町村自治会館  

学習活動ログと講義スライドの併用による早期At-risk 検出

尾﨑 優也, 出口 大輔, 久徳 遙矢, 村瀬 洋

教育学習支援情報システム研究会(CLE)  2025.3.20 

　More details

Event date： 2025

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：群馬大学  

Rethinking Multimodal Semantic Segmentation: Maximizing the Contribution of Each Modality

Jialei Chen, Daisuke Deguchi, Seigo Ito, Hiroshi Murase

28th Meeting on Image Recognition and Understanding (MIRU2025)  2025.7.29 

　More details

Event date： 2025

Language：Japanese   Presentation type：Poster presentation  

Venue：国立京都国際会館  

Pyramid Window Attention for Open-Vocabulary Semantic Segmentation Inference

Jialei Chen, Daisuke Deguchi, Seigo Ito, Hiroshi Murase

28th Meeting on Image Recognition and Understanding (MIRU2025)  2025.7.29 

　More details

Event date： 2025

Language：English   Presentation type：Oral presentation (general)  

Venue：国立京都国際会館  

講義スライドのコンテンツ解析に基づく ハイライト表示付き講義動画の自動生成に関する検討

水上 皓太, 出口 大輔, 久徳 遙矢, 峰松 翼, 村瀬 洋

画像の認識・理解シンポジウム(MIRU)  2025.8.7 

　More details

Event date： 2025

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：国立京都国際会館  

Landmark-guided Contextual Queries for Robust Visual Place Recognition

Dongyue Li, Daisuke Deguchi, Hiroshi Murase

28th Meeting on Image Recognition and Understanding (MIRU2025)  2025.8.1 

　More details

Event date： 2025

Language：Japanese   Presentation type：Poster presentation  

Venue：国立京都国際会館  

複数歩行者間の関係性を考慮した注視対象物推定の全体最適化に関する検討

辰己 弘征, 出口 大輔, 村瀬 洋, 伊藤 誠悟

画像の認識・理解シンポジウム(MIRU)  2025.8.7 

　More details

Event date： 2025

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：国立京都国際会館  

AIとは？

出口 大輔

日本鋳造工学会東海支部2025年度鋳物技術講演会  2025.10.24 

　More details

Event date： 2025

Language：Japanese   Presentation type：Oral presentation (invited, special)  

Venue：刈谷市  

Leveraging Global Semantics from Captions for Referring Image Segmentation

CHONG YI, Daisuke Deguchi, Seigo Ito, Hiroshi Murase

28th Meeting on Image Recognition and Understanding (MIRU2025)  2025.8.8 

　More details

Event date： 2025

Language：English   Presentation type：Poster presentation  

Venue：国立京都国際会館  

Split Matching for Inductive Zero-shot Semantic Segmentation International conference

Jialei Chen, Xu Zheng, Dongyue Li, CHONG YI, Seigo Ito, Danda Pani Paudel, Luc Van Gool, Hiroshi Murase, Daisuke Deguchi

British Machine Vision Conference (BMVC 2025)  2025.12.5 

　More details

Event date： 2025

Language：English   Presentation type：Poster presentation  

Venue：Cutlers’ Hall, Sheffield  

Semantic-driven Distillation for Semantic Segmentation with Unknown Classes International conference

Jialei Chen, Dongyue Li, CHONG YI, Xu Zheng, Seigo Ito, Hiroshi Murase, Daisuke Deguchi

2025 IEEE Conference on Intelligent Transportation Systems (ITSC2025)  2025.11.18 

　More details

Event date： 2025

Language：English   Presentation type：Oral presentation (general)  

Venue：Star Grand, Broadbeach, Gold Coast