Publications 2025

Journals

1. Jialei Chen, Daisuke Deguchi, Dongyue Li, Xu Zheng, Seigo Ito, Hiroshi Murase, Qi Fan: "Semantic-Centric Alignment for Zero-shot Panoptic Segmentation with Limited Data,"International Journal of Computer Vision, 134(122), 2026/02/16 doi

2. Jialei Chen, Zhenzhen Quan, Chenkai Zhang, Xu Zheng, Daisuke Deguchi, Hiroshi Murase: "CLIP-to-Seg Distillation for Zero-shot Semantic Segmentation,"IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025/09/28 doi

3. Zhenzhen Quan, Jialei Chen, Daisuke Deguchi, Jie Sun, Chenkai Zhang, Yujun Li, Hiroshi Murase: "Semantic matters: A constrained approach for zero-shot video action recognition,"Pattern Recognition, Vol.162, p.111402, 2025/06/01 doi

International Conferences

1. Hiroyuki Tatsumi, Daisuke Deguchi, Seigo Ito, Hiroshi Murase: "Pedestrians' Gaze Object Estimation in Traffic Scene Considering Relationships Among Multiple Pedestrians,"Proceedings of International Workshop on Advanced Image Technology (IWAIT) 2026, 2026/01/12 doi

2. Jialei Chen, Xu Zheng, Dongyue Li, CHONG YI, Seigo Ito, Danda Pani Paudel, Luc Van Gool, Hiroshi Murase, Daisuke Deguchi: "Split Matching for Inductive Zero-shot Semantic Segmentation,"Proceedings of British Machine Vision Conference (BMVC 2025), 2025/12/05

3. Jialei Chen, Dongyue Li, CHONG YI, Xu Zheng, Seigo Ito, Hiroshi Murase, Daisuke Deguchi: "Semantic-driven Distillation for Semantic Segmentation with Unknown Classes,"Proceedings of 2025 IEEE Conference on Intelligent Transportation Systems (ITSC2025), 2025/11/18

4. Kota Mizukami, Daisuke Deguchi, Haruya Kyutoku, Tsubasa Minematsu, Tomoki Toda, Hiroshi Murase: "Study on automatic generation of lecture videos based on content analysis of lecture slides,"Proceedings of the 22nd International Conference on Cognition and Exploratory Learning in Digital Age, p.353, 2025/11/03

5. Dongyue Li, Jialei Chen, Seigo Ito, Hiroshi Murase, Daisuke Deguchi: "CQVPR: Landmark-aware Contextual Queries for Visual Place Recognition,"Proceedings of 2025 IEEE Conference on Intelligent Transportation Systems (ITSC2025), 2025/10/21

Domestic Conferences

1. Nazuna Matsuo, Daisuke Deguchi, Hiroshi Murase, Seigo Ito, Haruya Kyutoku: "Automatic Generation of Lecture Videos with Semantically Meaningful Gestures from Lecture Slides,"IEICE Technical Report (MVE), 125(411), pp.61-62, 2026/03/15

2. Kota Mizukami, Daisuke Deguchi, 久徳遥矢, Atsushi Shimada, Tsubasa Minematsu, Hiroshi Murase: "マルチモーダルLLMを用いた講義スライド解析に基づくハイライト付き講義動画の自動生成の検討,"IEICE General Conference, 2026/03/12

3. 横山 航大, Daisuke Deguchi, Seigo Ito, Hiroshi Murase: "A Study on Estimating Pedestrian Crossing Intentions Using First-Token Representations of VLM,"IEICE General Conference, 2026/03/10

4. 長江 和馬, Daisuke Deguchi, Hiroshi Murase, Seigo Ito: "3D Pose Estimation from Human Silhouette Images,"IEICE General Conference, 2026/03/09

5. 関剛志, Daisuke Deguchi, Seigo Ito, Hiroshi Murase, Hiroki Mukoujima, Nozomi Nagamine: "A study on Frame Alignment in Train Front-View Videos via Local Spatial Embeddings,"IEICE General Conference, 2026/03/09

6. 坂口 駿哉, Daisuke Deguchi, Hiroshi Murase, Seigo Ito: "Instance Segmentation in Densely Packed Environments,"IEICE General Conference, 2026/03/09

Domestic Symposiums

1. Hiroyuki Tatsumi, Daisuke Deguchi, Seigo Ito, Hiroshi Murase: "複数歩行者間の関係性を考慮した各歩行者の注視対象物の同時推定,"IEICE Technical Report (MVE), 125(411), pp.49-54, 2026/03/16

2. CHONG YI, Daisuke Deguchi, Seigo Ito, Hiroshi Murase: "Leveraging Global Semantics from Captions for Referring Image Segmentation,"Proceedings of 28th Meeting on Image Recognition and Understanding (MIRU2025), 2025/08/08

3. Hiroyuki Tatsumi, Daisuke Deguchi, Hiroshi Murase, Seigo Ito: "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,"Proceedings of 28th Meeting on Image Recognition and Understanding (MIRU2025), 2025/08/07

4. Kota Mizukami, Daisuke Deguchi, Haruya Kyutoku, Tsubasa Minematsu, Hiroshi Murase: "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,"Proceedings of 28th Meeting on Image Recognition and Understanding (MIRU2025), 2025/08/07

5. Dongyue Li, Daisuke Deguchi, Hiroshi Murase: "Landmark-guided Contextual Queries for Robust Visual Place Recognition,"Proceedings of 28th Meeting on Image Recognition and Understanding (MIRU2025), 2025/08/01

6. Jialei Chen, Daisuke Deguchi, Seigo Ito, Hiroshi Murase: "Pyramid Window Attention for Open-Vocabulary Semantic Segmentation Inference,"Proceedings of 28th Meeting on Image Recognition and Understanding (MIRU2025), 2025/07/29

7. Jialei Chen, Daisuke Deguchi, Seigo Ito, Hiroshi Murase: "Rethinking Multimodal Semantic Segmentation: Maximizing the Contribution of Each Modality,"Proceedings of 28th Meeting on Image Recognition and Understanding (MIRU2025), 2025/07/29

Lectures & Panels

1. Daisuke Deguchi: "AIとは?,"Unknown Journal, 2025/10/24

Awards

1. Hiroyuki Tatsumi, Daisuke Deguchi, Seigo Ito, Hiroshi Murase: "Pedestrians' Gaze Object Estimation in Traffic Scene Considering Relationships Among Multiple Pedestrians,"Best Paper Award, 2026/01/12

2. Jialei Chen: "Pyramid Window Attention for Open-Vocabulary Semantic Segmentation Inference,"MIRU学⽣奨励賞, 2025/08/01

Theses

1. Kota Mizukami: "Automatic Generation of Visually Highlighted Lecture Videos Based on Multimodal LLM-Driven Lecture Slide Analysis,"Master thesis, 2026/02/05

We research on various themes using video and images.

Please feel free to contact us if you are interested.

Contact Information

Furo-cho, Chikusa-ku, Nagoya, Japan
IB Building South #457
Phone: 052-789-3310
Fax: 052-789-3807