Papers - IDE, Ichiro
-
Investigating conceptual blending of a diffusion model for improving nonword-to-image generation Reviewed
Chihaya Matsuhira, Marc Aurel Kastner, Takahiro Komamizu, Takatsugu Hirayama, Ichiro Ide
Proc. 32nd ACM Int. Multimedia Conf. (ACMMM2024) page： 7307-7315 2024.10
-
広域多視点マルチモーダル行動認識のためのセンサ統合手法とMultiSensor-Homeデータセットの提案
Trung Thanh Nguyen，川西康友，Vijay John，駒水孝裕，井手一郎
電子情報通信学会パターン認識・メディア理解研究会 ( PRMU2024-XXX ) 2025.3
-
A study on quantifying visual variety of adjectives (in Japanese)
Yui Tanaka, Marc A. Kastner, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
IEICE 2025 Annual Convention ( D-12-52 ) 2025.3
-
タイトル重畳料理画像における魅力的なフォントの分析と推定
高木七海，久徳遙矢，道満恵介，駒水孝裕，井手一郎
第17回データ工学と情報マネジメントに関するフォーラム（DEIM2025） ( 6E-05/Z4-06 ) 2025.3
-
HashtagMeta: Fake news mitigation for hashtag recommendation
Jialiang Shi, Takahiro Komamizu, Ichiro Ide
17th Forum on Data Engineering and Information Management (DEIM2025) ( 1K-05/X2-11 ) 2025.3
-
Leveraging data-free pruning through gradient analysis towards lightweight maize disease detection
Carlos Padeiro, Tse-Wei Chen, Takahiro Komamizu, Ichiro Ide
IEICE Tech. Rep. Image Engineering ( IE2024-118 ) 2025.3
-
Crease estimation from Origami pictures for automatic folding diagrams generation (in Japanese)
Hitomi Kato, Hirotaka Kato, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide
IEICE Tech. Rep. Media Experience and Virtual Environment ( MVE2024-98 ) 2025.3
-
Towards visual storytelling by understanding narrative context through scene-graphs Reviewed
Itthisak Phueaksri, Marc Aurel Kastner, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
Proc. 31st Int. Conf. on Multimedia Modeling (MMM2025) Vol. 4 page： 226-239 2025.1
-
Quantifying image-adjective associations by leveraging large-scale pretrained models Reviewed
Chihaya Matsuhira, Marc Aurel Kastner, Takahiro Komamizu, Takatsugu Hirayama, Ichiro Ide
Proc. 31st Int. Conf. on Multimedia Modeling (MMM2025) Vol. 4 page： 428-441 2025.1
-
Cross-modal recipe retrieval based on unified text encoder with fine-grained contrastive learning Reviewed International coauthorship
Bolin Zhang, Haruya Kyutoku, Keisuke Doman, Takahiro Komamizu, Ichiro Ide, Jiangbo Qian
Knowledge-Based Systems Vol. 305 ( 112641 ) page： 1-15 2024.12
-
Action selection learning for multi-label multi-view action recognition Reviewed
Trung Thanh Nguyen, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
Proc. ACM Multimedia Asia 2024 Conf. ( 50 ) page： 1-8 2024.12
-
Can an LLM reproduce emotional associations to nonsense words by humans? (in Japanese)
Yui Miyakawa, Chihaya Matsuhira, Hirotaka Kato, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide
21st Text Analytics Symposium 2024.9
-
Do LLMs agree with humans on emotional associations to nonsense words? Reviewed
Yui Miyakawa, Chihaya Matsuhira, Hirotaka Kato, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide
Proc. 13th Workshop on Cognitive Modeling and Computational Linguistics (CMCL2024) in conjunction with ACL2024 page： 81-85 2024.8
-
R-DiP: Re-ranking based Diffusion Pre-computation for image retrieval Reviewed
Tatsuya Kato, Takahiro Komamizu, Ichiro Ide
Proc. 35th Int. Conf. on Database and Expert Systems Applications (DEXA2024) Vol. 2 page： 233-247 2024.8
-
Toward visual storytelling using scene-graph contexts
Itthisak Phueaksri, Marc Aurel Kastner, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
Meeting on Image Recognition and Understanding (MIRU) 2024 ( IS2-99 ) 2024.8
-
Leveraging similarity-preserving post-training quantization for lightweight crop disease detection
Carlos Victorino Padeiro, Tse-Wei Chen, Takahiro Komamizu, Ichiro Ide
Meeting on Image Recognition and Understanding (MIRU) 2024 ( IS2-12 ) 2024.8
-
語感の定量化に向けた画像に写る概念に対する視覚的印象の推定
松平茅隼，カストナーマークアウレル，駒水孝裕，平山高嗣，井手一郎
画像の認識・理解シンポジウム（MIRU）2024 ( IS2-134 ) 2024.8
-
歌唱時の口唇形状の類似性を考慮した歌詞の自動翻訳の検討
池田昂太郎，松平茅隼，加藤大貴，カストナーマークアウレル，平山高嗣，駒水孝裕，井手一郎
画像の認識・理解シンポジウム（MIRU）2024 ( IS2-138 ) 2024.8
-
Lightweight maize disease detection through post-training quantization with similarity preservation Reviewed
Carlos Victorino Padeiro, Tse-Wei Chen, Takahiro Komamizu, Ichiro Ide
Proc. 20th Embedded Vision Workshop (EVW2024) in conjunction with CVPR2024 page： 2111-2120 2024.6
-
One-stage open-vocabulary temporal action detection leveraging temporal multi-scale and action label features Reviewed
Trung Thanh Nguyen, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide
Proc. 18th IEEE Int. Conf. on Automatic Face and Gesture Recognition (FG2024) ( P2-13 ) page： 1-10 2024.5