Contents Science Lab

Dr. Takahiro Komamizu

Associate Professor （Center for Artificial Intelligence, Mathematical and Data Science）

E-Mail: taka-coma ( a t ) acm.org

Personal website: https://taka-coma.pro

Recent publications

Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning

Junan Chen, Trung Thanh Nguyen, Takahiro Komamizu, Ichiro Ide
ACM International Conference on Multimedia in Asia, pp.1-10, To be published in December 2025.

Hierarchical Global-Local Fusion for One-stage Open-vocabulary Temporal Action Detection

Trung Thanh Nguyen, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
ACM Transactions on Multimedia Computing, Communications, and Applications, October 2025.

IntentVC 2025: The ACM Multimedia Grand Challenge on Intention-Oriented Controllable Video Captioning

Takahiro Komamizu, Marc A. Kastner, Yasutomo Kawanishi, Trung Thanh Nguyen, Junan Chen
ACM International Conference on Multimedia (ACMMM), pp.1-2, October 2025.

Exploring Unknown Image Generation for Zero Shot Learning via Diffusion Models

Lei Xiang, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS3-079, August 2025.

Exploring Unknown Image Generation for Zero Shot Learning via Diffusion Models

Lei Xiang, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS3-079, August 2025.

Exploring Unknown Image Generation for Zero Shot Learning via Diffusion Models

Lei Xiang, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS3-079, August 2025.

Investigating conceptual blending of a diffusion model for improving nonword-to-image generation (ACMMM2024)

松平 茅隼, カストナー マークアウレル, Takahiro Komamizu, 平山 高嗣, 井手 一郎
第28回画像の認識・理解シンポジウム(MIRU2025), IT3-06, August 2025.

Investigating conceptual blending of a diffusion model for improving nonword-to-image generation (ACMMM2024)

松平 茅隼, カストナー マークアウレル, Takahiro Komamizu, 平山 高嗣, 井手 一郎
第28回画像の認識・理解シンポジウム(MIRU2025) 論文集, IT3-06, August 2025.

Multi-proposal collaboration and multi-task training for weakly-supervised video moment retrieval

Bolin Zhang, Chao Yang, Bin Jiang, Takahiro Komamizu, Ichiro Ide
International Journal of Machine Learning and Cybernetics, Vol.16, 7-8, pp.4509-4524, August 2025.

Multi-proposal collaboration and multi-task training for weakly-supervised video moment retrieval

Bolin Zhang, Chao Yang, Bin Jiang, Takahiro Komamizu, Ichiro Ide
International Journal of Machine Learning and Cybernetics, Vol.16, 7-8, pp.4509-4524, August 2025.

MultiSensor-Home: Benchmark for Multi-modal Multi-view Action Recognition in Home Environments

Trung Thanh Nguyen, Yasutomo Kawanishi, Vijay John, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS3-038, August 2025.

MultiSensor-Home: Benchmark for Multi-modal Multi-view Action Recognition in Home Environments

Trung Thanh Nguyen, Yasutomo Kawanishi, Vijay John, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS3-038, August 2025.

Visual Adapter for Extracting Textually-related Features for Video Captioning

Junan Chen, Trung Thanh Nguyen, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS3-148, August 2025.

Visual Adapter for Extracting Textually-related Features for Video Captioning

Junan Chen, Trung Thanh Nguyen, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS3-148, August 2025.

Image Retrieval based on Editable Scene Graph with Contrastive Representation Learning

PHAM Dinh Duy, Itthisak PHUEAKSRI, Marc A. Kastner, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
Unknown Journal, July 2025.

MLLM-based Dataset Construction for Hazard-aware Guidance for the Visually Impaired

Peiyuan ZHU, Marc A. Kastner, Hirotaka Kato, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS2-140, July 2025.

MLLM-based Dataset Construction for Hazard-aware Guidance for the Visually Impaired

Peiyuan ZHU, Marc A. Kastner, Hirotaka Kato, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS2-140, July 2025.

MLLM-based Dataset Construction for Hazard-aware Guidance for the Visually Impaired

Peiyuan ZHU, Marc A. Kastner, Hirotaka Kato, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide
Unknown Journal, IS2-140, July 2025.

画像特徴のクラスタリングによる形容詞の視覚的な多様性の分析

田中優衣, カストナー マークアウレル, 川西 康友, 駒水孝裕, 井手 一郎
第28回画像の認識・理解シンポジウム(MIRU2025) 論文集, IS1-145, July 2025.

画像特徴のクラスタリングによる形容詞の視覚的な多様性の分析

田中優衣, カストナー マークアウレル, 川西 康友, 駒水孝裕, 井手 一郎
第28回画像の認識・理解シンポジウム(MIRU2025) 論文集, IS1-145, July 2025.

画像特徴のクラスタリングによる形容詞の視覚的な多様性の分析

田中優衣, カストナー マークアウレル, 川西 康友, 駒水孝裕, 井手 一郎
第28回画像の認識・理解シンポジウム(MIRU2025) 論文集, IS1-145, July 2025.

折り図の自動生成のための折り線推定とその評価

加藤 眸, 加藤 大貴, 平山 高嗣, 駒水孝裕, 井手 一郎
第28回画像の認識・理解シンポジウム(MIRU2025) 論文集, July 2025.

折り図の自動生成のための折り線推定とその評価

加藤 眸, 加藤 大貴, 平山 高嗣, 駒水孝裕, 井手 一郎
第28回画像の認識・理解シンポジウム(MIRU2025) 論文集, July 2025.

折り図の自動生成のための折り線推定とその評価

加藤 眸, 加藤 大貴, 平山 高嗣, 駒水孝裕, 井手 一郎
第28回画像の認識・理解シンポジウム(MIRU2025) 論文集, July 2025.

Analysis and prediction of attractive fonts on title-overlaid food images

Nanami Takagi, Haruya Kyutoku, Keisuke Doman, Takahiro Komamizu, Ichiro Ide
Proceedings of the 19th Int. Conf. on Machine Vision Applications (MVA2025), July 2025.

Analysis and prediction of attractive fonts on title-overlaid food images

Nanami Takagi, Haruya Kyutoku, Keisuke Doman, Takahiro Komamizu, Ichiro Ide
Proceedings of the 19th Int. Conf. on Machine Vision Applications (MVA2025), July 2025.

Front matter

Takahiro Komamizu, Marc A. Kastner, Minh-Son Dao
ICDAR ‘25: Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and Retrieval, June 2025.

ICDAR 25: Intelligent Cross-Data Analysis and Retrieval

Takahiro Komamizu, Marc A. Kastner, Minh-Son Dao, Michael Alexander Riegler, Duc-Tien Dang-Nguyen, Son Tran
ICMR ‘25: Proceedings of the 2025 International Conference on Multimedia Retrieval, June 2025.

ICDAR'25 -Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and Retrieval-

Takahiro Komamizu, Marc A. Kastner, Minh-Son Dao
ACM Proceedings, June 2025.

Action Selection Learning for Weakly Labeled Multi-modal Multi-view Action Recognition

Trung Thanh Nguyen, Yasutomo Kawanishi, Vijay John, Takahiro Komamizu, Ichiro Ide
ACM Transactions on Multimedia Computing, Communications, and Applications, June 2025.