Search Results 1-20 of 4338

  • Sports Field Recognition Using Deep Multi-task Learning

    Shuhei Tarashima

    … To address these issues, we propose to train our regressor in combination with semantic segmentation in a multi-task learning framework. … Thisarticle should be cited as: Journal of Information Processing Vol.29(2021) (online)DOI http://dx.doi.org/10.2197/ipsjjip.29.328------------------------------In this paper we propose a novel approach to build a single shot regressor, called SFLNet, that directly predicts a parameter set relating a sports field seen in an input frame to its metric model. …

    情報処理学会論文誌 62(4), 2021-04-15

    IPSJ 

  • Dynamic meaning and truth-conditions  [in Japanese]

    天本 貴之

    特集 : 岡田光弘教授 退職記念号原著研究論文

    哲學 (146), 39-82, 2021-03

    IR 

  • Teaching Activities of Nursing Faculty that Support Problem Solving by Nursing Students Themselves During Nursing Clinical Practicum  [in Japanese]

    佐藤 和也 , 松田 安弘 , 山下 暢子 , 服部 美香 , 金谷 悦子

    目的:実習中の学生の問題を知覚し,学生自身によって問題解決できるように支援する教員の教授活動を明らかにし,その特徴を考察する.方法:Berelson,B. の方法論を参考にした看護教育学における内容分析を適用した.全国の看護基礎教育機関に所属し,実習を担当している教員974 名を対象に,郵送法による質問紙を配布し,262 名(回収率26.9%)から回答を得た.このうち,自由回答式質問に回答した25 …

    群馬県立県民健康科学大学紀要 16, 81-96, 2021-03

    IR 

  • Sports Field Recognition Using Deep Multi-task Learning

    Tarashima Shuhei

    … To address these issues, we propose to train our regressor in combination with semantic segmentation in a multi-task learning framework. …

    Journal of Information Processing 29(0), 328-335, 2021

    J-STAGE 

  • False recognition/misidentification of unfamiliar person in a patient after cerebral infarction  [in Japanese]

    Sugahara Yumiko , Iizuka Chiaki , Doi Kazuya , Matsuzaki Kenichiro , Nagaoka Masanori

    <p>【要旨】 症例は84歳男性で、心原性脳梗塞後に繰り返し他人を自分の家族・友人と誤認した。視力・聴力は正常、視野障害や半側空間無視を認めなかったが、担当のリハビリテーション職員の顔を覚えられず、他患者の面会者やリハビリテーション職員を自分の家族・友人と繰り返し誤認し、その誤りに気付かなかった。長谷川式認知症スケールは25/30点。視覚による物体失認を認めず相貌認知では、家族や有名人 …

    Japanese Journal of Cognitive Neuroscience 22(2), 88-97, 2021

    J-STAGE 

  • Recognition of aquatic plants and lake surface environment using deep neural network for visual navigation of robot boat.  [in Japanese]

    KUMA Keishiro , KAIZU Yutaka , SHIMADA Tetsuro , TAKAHASHI Yusuke , FURUHASHI Kenichi , IMOU Kenji

    <p>本研究では水草刈払いロボットの視覚センサとして,ディープラーニングによるセマンティックセグメンテーションにより,湖沼の水上の風景を自動的に分類するシステムの開発を行った.セマンティックセグメンテーシ ョンによるクラス分類に関しては今回実験を行った場所で刈り取り対象であるハスと希少種であるアサザを約 90%の正解率で分類することができた.ディープラーニングでは画像中の色や形状,位置 …

    Ecology and Civil Engineering 23(2), 369-376, 2021

    J-STAGE 

  • Cognitive Semantic Analysis of the Polysemous Word Spirit  [in Japanese]

    Uehara Hoshina , Shimizu Hiroko

    <p>本研究は,認知意味論の理論的枠組みにおいて,記述的に英語の"spirit"という言葉のもつ内容や情報量を検討し,"spirit"の意味体系を明らかにすることを目的とする.</p><p>研究方法は,3種類の中型英語辞典から英語の"spirit"の意味を抽出し,カテゴリー分類を行い,語義に定義づけを行った.また,皆島が作成した多義語放射状カテゴリーモデルの形態 …

    Nursing Journal of Kagawa University 25(1), 23-32, 2021

    IR  J-STAGE 

  • Sketch Face Recognition via Cascaded Transformation Generation Network

    CAO Lin , HUO Xibao , GUO Yanan , DU Kangning

    … The generation module aims to generate a high quality cross-modality image, the cascaded feature transformation module extracts high-level semantic features for generation and recognition simultaneously, the classifier module is used to complete sketch face recognition. …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2021

    J-STAGE 

  • Working Memory Trumps Language Aptitude in Learning Semantic-Based Linguistic Category Rules

    Dardon Diego Elisandro , Jeong Hyeonjeong

    … Previous studies have focused on grammatical rules that rely on form, but there are no studies investigating WM and LAA's contribution comparatively to learning linguistic rules that require the generalization of semantic information. … The aim of this study was to determine the contributions of WM and LAA in learning semantic noun classes, grammatical structures whose rules rely on the ability to generalize and categorize based on conceptual knowledge. …

    Studies in Language Sciences 19(0), 77-84, 2021

    J-STAGE 

  • A case suspected of Alzheimer type dementia showing multimodal (face and voice) person recognition disorder from face and voice  [in Japanese]

    M.D. Ishihara Kenji , S.T. Kaneko Sayaka , M.D. Takahashi Nobuyoshi , M.D. Asahi Toshiomi

    <p>相貌および声を介した人物同定障害を呈した90歳,女性例を報告した.全般的な認知機能低下を認めたが,相貌以外の視覚性認知機能は保持.人物同定障害の内容として家族など親密度の高い人物は相貌,声による同定可能,有名人の相貌,声は同定困難であったが,既知感はあり名前の記憶は保持されていた.新規の人物は相貌,声ともに同定できなかった.画像検査では右優位の両側側頭葉前部萎縮と右側頭極を中心と …

    Rinsho Shinkeigaku 61(3), 182-187, 2021

    J-STAGE 

  • Opposite Information Annotation on 'Word List by Semantic Principles'  [in Japanese]

    Kato Sachi , Asahara Masayuki , Moriyama Nanami , Ogiwara Asami , Yamazaki Makoto

    <p>本論文ではシソーラス『分類語彙表』に対する反対語情報付与作業について示す.分類語彙表上では反対語対に対しても同じ分類番号が付与されている.この同じ分類番号が付与されている単語群から反対語対を抽出し,分類作業を行った.まず,人手により反対語候補となる単語対を網羅的に収集した.次に,一般的な日本語話者が反対語と感じるかをクラウドソーシングにより収集し,50% 以上の方が反対語とみなし …

    Journal of Natural Language Processing 28(1), 60-81, 2021

    IR  J-STAGE 

  • Effect of posture as contextual information for recognition of facial expressions of emotion  [in Japanese]

    Watanabe Nobuyuki , Shintaku Yukino

    … They rated the pictures using a semantic differential technique. …

    Emotion Studies 6(1), 50-56, 2021

    J-STAGE 

  • Self-Learning pLSA Model for Abnormal Behavior Detection in Crowded Scenes

    LIU Shuoyan , YANG Enze , FANG Kai

    … This paper proposes a self-learning probabilistic Latent Semantic Analysis, which aims at taking full advantage of the high-level abnormal information to solve problems. …

    IEICE Transactions on Information and Systems E104.D(3), 473-476, 2021

    J-STAGE 

  • TRIAL OF MANIFESTATION OF RINSHO-NO-CHI THROUGH REFLECTION OF PRACTICE WITH PICTORIAL AND VERBAL EXPRESSION ASSOCIATED WITH THE PRACTICE  [in Japanese]

    FUJII Haruyuki , HIRATA Sadayo , SHINOZAKI Ken-ichi

    … This paper describes the characteristics of the process of co-creating verbal expression of the judgement skill.</p><p> Seven types of the verbal expressions, which are made to evaluate the workmanship of the coral stone fences on the basis of visual information of the coral stone fences shown in the pictures, are extracted from the conversations to discuss about the workmanship as follows;</p><p> 1. …

    Journal of Architecture and Planning (Transactions of AIJ) 86(779), 345-355, 2021

    J-STAGE 

  • Error Recovery Action Planning for Robots Based on Deep Semantic Information of Failures  [in Japanese]

    MATSUOKA Satoru , SAWARAGI Tetsuo , MAEKAWA Kiyoshi

    … In this paper, we propose a recovery action planning system by considering semantic information behind the detected error information. …

    Transactions of the Society of Instrument and Control Engineers 57(1), 25-36, 2021

    J-STAGE 

  • Face-Image Anonymization as an Application of Multidimensional Data k-anonymizer

    Nakamura Taichi , Sakuma Yuiko , Nishi Hiroaki

    … For solving this privacy problem, researchers have been developing anonymization technologies that are used to preserve privacy by deleting the private information from the original data. … This is attributed to the fact that conventional anonymization techniques do not consider the complex relationships between dimensions and the semantic loss of data. … Both machine learning and anonymization share the common idea in their bases to abstract statistical information from a given dataset . …

    International Journal of Networking and Computing 11(1), 102-119, 2021

    J-STAGE 

  • [Paper] User-selectable Event Summarization in Unedited Raw Soccer Video via Multimodal Bidirectional LSTM

    Haruyama Tomoki , Takahashi Sho , Ogawa Takahiro , Haseyama Miki

    <p>A new method that generates user-selectable event summaries from unedited raw soccer videos is presented in this paper. Since there are more unedited raw soccer videos than broadcasted/distri …

    ITE Transactions on Media Technology and Applications 9(1), 42-53, 2021

    J-STAGE 

  • Context-aware Music Recommender System Based on Implicit Feedback

    Takama Yasufumi , Zhang Jing-cheng , Shibata Hiroki

    … Context and content features are used as auxiliary information to compensate for implicit feedback. … This paper focuses on two challenges specific to music recommender systems: the difficulty of obtaining explicit feedback such as ratings, and the importance of making use of context information. …

    Transactions of the Japanese Society for Artificial Intelligence 36(1), WI2-D_1-10, 2021

    J-STAGE 

  • An Ontology-based Approach for Semantic Interoperability in Air Traffic Information Management  [in Japanese]

    Egami Shusaku , Lu Xiaodong , Koga Tadashi , Sumiya Yasuto

    … <p>With the advancement of information and communication technologies, to improve the interoperability between heterogeneous information systems by regularizing the syntax for information exchange is essential to achieve global seamless air traffic management operation. … However, the current point-to-point aviation related information exchange among different systems and operators cannot satisfy the requirement for interoperability. …

    Transactions of the Japanese Society for Artificial Intelligence 36(1), WI2-F_1-12, 2021

    J-STAGE 

  • Target-Oriented Deformation of Visual-Semantic Embedding Space

    MATSUBARA Takashi

    … However, because entities in different modalities exhibit different abstraction levels and modality-specific information, it is insufficient to embed related entities close to each other. …

    IEICE Transactions on Information and Systems E104.D(1), 24-33, 2021

    J-STAGE 

Page Top