Details of a Researcher - SUGIURA, Komei

Papers - SUGIURA, Komei

Division display 1 - 20 of about 211 ／ All the affair displays >>

Mobile Manipulation Instruction Generation From Multiple Images With Automatic Metric Enhancement

K Katsumata, M Kambara, D Yashima, R Korekata, K Sugiura

IEEE Robotics and Automation Letters 2025

DM2RM: dual-mode multimodal ranking for target objects and receptacles based on open-vocabulary instructions

R Korekata, K Kaneda, S Nagashima, Y Imai, K Sugiura

Advanced Robotics, 1-16 abs/2408.07910 2025

Access to Document (DOI)

Pre-Manipulation Alignment Prediction for Open-Vocabulary Object Manipulation Based on End-Effector Trajectories

M Kambara, K Sugiura

2025 19th International Conference on Machine Vision and Applications (MVA), 1-5 1 - 5 2025

Access to Document (DOI)

NaiLIA: 緩和損失に基づくネイルデザインのマルチモーダル検索

雨宮佳音，小松拓実，八島大地，是方諒介，勝又圭，杉浦孔明

人工知能学会全国大会論文集第 39 回 (2025), 2Win555-2Win555 (The Japanese Society for Artificial Intelligence) JSAI2025 ( 0 ) 2Win555 - 2Win555 2025

<p>We focus on the task of retrieving nail design images based on dense intent descriptions, which represent long and multi-layered user intent for nail designs. This is challenging because such descriptions specify flexibly created paintings and pre-manufactured embellishments, as well as visual characteristics, spatial relationships, higher-order themes, and overall impressions. Existing vision-and-language foundation models often struggle to capture the interplay between paintings and embellishments, failing to incorporate multi-layered intent descriptions. To address this, we propose NaiLIA, a method that enables the retrieval of nail design images that comprehensively align with descriptions with dense user intent. Our approach estimates confidence scores for images that align with a given description and can be considered as positive examples but are not explicitly labeled (unlabeled positives), and incorporates this score into the loss function. To evaluate NaiLIA, we constructed a benchmark consisting of 10,625 images collected from people with diverse cultural backgrounds. The images were annotated with long and dense intent descriptions given by over 200 annotators. Experimental results demonstrate that the proposed method outperforms standard methods by 20.9 points in terms of recall@10.</p>

Interactive robot action replanning using multimodal llm trained from human demonstration videos

C Hori, M Kambara, K Sugiura, K Ota, S Khurana, S Jain, R Corcodel, ...

ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and … 1 - 5 2025

Access to Document (DOI)

Deep Space Weather Model: Long-Range Solar Flare Prediction from Multi-Wavelength Images

S Nagashima, K Sugiura

Proceedings of the IEEE/CVF International Conference on Computer Vision … abs/2508.07847 2025

Access to Document (DOI)

Crosslingual Visual Prompt に基づくテキスト付き画像からの日常物体検索

戸倉健登，是方諒介，小松拓実，今井悠人，杉浦孔明

人工知能学会全国大会論文集第 39 回 (2025), 1Win452-1Win452 (The Japanese Society for Artificial Intelligence) JSAI2025 ( 0 ) 1Win452 - 1Win452 2025

<p>This study explores a task where a robot searches for images containing target objects based on user language queries from a large set of images captured in diverse indoor and outdoor environments. Both images with and without scene text are considered. For example, when searching with the query, "Pass me the red container of Sun-Maid raisins on the kitchen counter," the model ranks images containing a container labeled "Sun-Maid raisins" on the kitchen counter higher. However, linking visual semantics with scene text is challenging. Additionally, multimodal search requires large-scale, high-speed inference, making it impractical to rely solely on a multimodal large language model (MLLM). To address this, we introduce a Scene Text Visual Encoder, integrating an Aligned Representation with a narrative representation obtained using an MLLM based on Crosslingual Visual Prompting. Incorporating OCR results into the prompt further reduces hallucination. Experiments show that the proposed method outperforms multimodal foundation models across multiple benchmarks in standard evaluation metrics for ranking-based learning.</p>

Pre-manipulation alignment prediction with parallel deep state-space and transformer models

M Kambara, K Sugiura

Advanced Robotics 39 (13), 806-816 2025

Object Segmentation from Open-Vocabulary Manipulation Instructions Based on Optimal Transport Polygon Matching with Multimodal Foundation Models.

Takayuki Nishimura, Katsuyuki Kuyo, Motonari Kambara, Komei Sugiura

IROS 9549 - 9556 2024