Papers - SUGIURA, Komei

Flare Transformer: 磁場画像と物理特徴量を用いた太陽フレア予測

兼田寛大， 飯田紡， 西塚直人， 久保勇樹， 杉浦孔明

人工知能学会全国大会論文集 第 36 回 (2022), 2D6GS201-2D6GS201 (The Japanese Society for Artificial Intelligence)  JSAI2022 ( 0 ) 2D6GS201 - 2D6GS201 2022

　View Summary

<p>The prediction of solar flares is essential for reducing the potential damage to social infrastructures that are vital to society. However, predicting solar flares accurately is a very challenging task. In this paper, we propose a solar flare prediction model, Flare Transformer, which handles both images and physical features through the Magnetogram Module and the Sunspot Feature Module. We introduce the transformer attention mechanism to model the temporal relationships. We also introduce a new differentiable loss function to balance the two major metrics of the Gandin-Murphy-Gerrity score and Brier skill score. Comparative experiments using Gandin-Murphy-Gerrity score and true skill statistics as metrics showed that the proposed method achieves better performance than baseline methods and human experts.</p>

• Access to Document (DOI)
• CiNii Research

Relational Future Captioning Model for Explaining Likely Collisions in Daily Tasks.

Motonari Kambara, Komei Sugiura

ICIP    2601 - 2605 2022

• Access to Document (DOI)

Moment-based Adversarial Training for Embodied Language Comprehension.

Shintaro Ishikawa, Komei Sugiura

ICPR    4139 - 4145 2022

• Access to Document (DOI)

Flare Transformer: Solar Flare Prediction Using Magnetograms and Sunspot Physical Features.

Kanta Kaneda, Yuiga Wada, Tsumugi Iida, Naoto Nishizuka, Yûki Kubo, Komei Sugiura

ACCV (2)    442 - 457 2022

• Access to Document (DOI)

Operational solar flare prediction model using Deep Flare Net

N Nishizuka, Y Kubo, K Sugiura, M Den, M Ishii

Earth, Planets and Space 73 (1), 1-12  2021

Predicting and attending to damaging collisions for placing everyday objects in photo-realistic simulations

A Magassouba, K Sugiura, A Nakayama, T Hirakawa, T Yamashita, ...

Advanced Robotics, 1-13 abs/2102.06507 2021

Case Relation Transformer に基づく対象物体及び目標領域の参照表現を含む物体操作指示文生成

神原元就， 杉浦孔明

人工知能学会全国大会論文集 第 35 回全国大会 (2021), 4J1GS6d05-4J1GS6d05 (The Japanese Society for Artificial Intelligence)  2021 ( 0 ) 4J1GS6d05 - 4J1GS6d05 2021

　View Summary

<p>The purpose of this paper is to extend the dataset based on a cross-modal generative language generation model. We propose a Case Relation Transformer (CRT) that generates a fetching instruction sentence from an image, such as ``Move the blue flip-flop to the lower left box.'' Unlike existing methods, CRT uses Transformer to capture the visual and geometric features of objects in an image. The Case Relation Block allows the CRT to process the object. We conducted comparative experiments and human evaluations. Experimental results showed that CRT outperformed the baseline methods.</p>

• Access to Document (DOI)
• CiNii Research

生活支援ロボットによる物体配置タスクにおける Transformer PonNet に基づく危険性予測および可視化

植田有咲， 平川翼， 山下隆義， 藤吉弘亘， 杉浦孔明

人工知能学会全国大会論文集 第 35 回全国大会 (2021), 2J1GS8a03-2J1GS8a03 (The Japanese Society for Artificial Intelligence)  2021 ( 0 ) 2J1GS8a03 - 2J1GS8a03 2021

　View Summary

<p>Placing everyday objects in designated areas, such as placing a glass on a table, is a crucial task for Domestic service robots (DSRs). In this paper, we propose a physical reasoning method about collisions in placement tasks. The proposed method, Transformer PonNet, predicts the probability of a possible collision and visualizes areas involved in the collision. Unlike existing methods, Transformer PonNet can be applied to objects whose models are unavailable. We propose a novel Transformer Perception Branch that handles relationships among features more complex than simple self-attention. We built simulation and physical datasets using a DSR, and validated our method on the datasets. We obtained an accuracy of 82.5% for the physical dataset.</p>

• Access to Document (DOI)
• CiNii Research

Target-dependent UNITER に基づく対象物体に関する参照表現を含む物体操作指示理解

石川慎太朗， 杉浦孔明

人工知能学会全国大会論文集 第 35 回全国大会 (2021), 4I2GS7c04-4I2GS7c04 (The Japanese Society for Artificial Intelligence)  2021 ( 0 ) 4I2GS7c04 - 4I2GS7c04 2021

　View Summary

<p>Currently, domestic service robots have an insufficient ability to interact naturally through language. This is because understanding human instructions is complicated by a variety of ambiguities and missing information. Existing methods are insufficient to model reference expressions that specify relationships between objects. In this paper, we propose Target-dependent UNITER, which learns directly the relationship between the target object and other objects by focusing on the relevant regions within an image, instead of the whole image. Our model is validated on two standard datasets, and the results show that Target-dependent UNITER outperforms the baseline method in terms of classification accuracy.</p>

• Access to Document (DOI)
• CiNii Research

Unified questioner transformer for descriptive question generation in goal-oriented visual dialogue

S Matsumori, K Shingyouchi, Y Abe, Y Fukuchi, K Sugiura, M Imai

Proceedings of the IEEE/CVF International Conference on Computer Vision … abs/2106.15550 2021

Target-Dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots

S Ishikawa, K Sugiura

IEEE Robotics and Automation Letters 6 (4), 8401-8408  2021

CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation.

Aly Magassouba, Komei Sugiura, Hisashi Kawai

IEEE Robotics Autom. Lett. 6 ( 4 ) 6258 - 6265 2021

Research paper (scientific journal), Joint Work, Accepted

• Access to Document (DOI)

Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions

M Kambara, K Sugiura

IEEE Robotics and Automation Letters 6 (4), 8371-8378  2021

Bilingual Case Relation Transformerに基づく複数言語による物体操作指示文生成

兼田寛大, 神原元就, 杉浦孔明

日本ロボット学会学術講演会予稿集(CD-ROM) 39th 2021

Deep Neural Networks Applied to Predictions of 4-Class Solar Flares and Eruptions

N Nishizuka, M Den, M Ishii, Y Kubo, K Sugiura

43rd COSPAR Scientific Assembly. Held 28 January-4 February 43, 1037  2021

LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation

S Matsumori, Y Abe, K Shingyouchi, K Sugiura, M Imai

IEEE Access 9, 160521-160532  2021

配置物体を考慮したAttention機構マルチモーダルネットワークによる衝突予測

河合竹彦, 平川翼, 山下隆義, 藤吉弘亘, 杉浦孔明

日本ロボット学会学術講演会予稿集(CD-ROM) 39th 2021

生活支援ロボットによる物体配置タスクにおける危険性予測および視覚的説明生成

畑中駿平, 上田雄斗, 植田有咲, 平川翼, 山下隆義, 藤吉弘亘, 杉浦孔明

日本ロボット学会学術講演会予稿集(CD-ROM) 39th 2021

物体指示理解タスクにおけるクロスモーダル言語生成に基づくデータ拡張

飯田紡, 九曜克之, 石川慎太朗, 杉浦孔明

日本ロボット学会学術講演会予稿集(CD-ROM) 39th 2021

深層学習を用いた太陽フレア予測モデルによる予報運用評価

西塚直人, 久保勇樹, 杉浦孔明, 田光江, 石井守

日本天文学会年会講演予稿集 2021 2021

ISSN  1347-0639