Search Results 1-20 of 268

  • Intention Detection Based on Siamese Neural Network With Triplet Loss

    Ren Fuji , Xue Siyuan

    … In this paper, we propose a triplet training framework based on the multiclass classification approach to conduct the training for the intention detection task. … Precisely, we utilize a Siamese neural network architecture with metric learning to construct a robust and discriminative utterance feature embedding model. …

    IEEE Access (8), 82242-82254, 2020-04-30

    IR 

  • Deep Metric Learning with Triplet-Margin-Center Loss for Sketch Face Recognition

    FENG Yujian , WU Fei , JI Yimu , JING Xiao-Yuan , YU Jian

    … The main challenge of sketch face recognition is learning discriminative feature representations to ensure intra-class compactness and inter-class separability. … It aims to effectively select hard samples to avoid unstable training phase and slow converges. …

    IEICE Transactions on Information and Systems E103.D(11), 2394-2397, 2020

    J-STAGE 

  • Training protocol for touchscreen-based visual discrimination in mice

    GOTO KAZUHIRO , HATAJI YUYA

    … In this report, we described a training protocol, developed in our laboratory, for mice acquiring a simultaneous discrimination performance using visual stimuli. … C57BL/6N mice were first given magazine training. … All mice successfully went through all training stages, confirming that this training protocol is promising for shaping appropriate discriminative behaviors in mice.</p> …

    Japanese Journal of Animal Psychology 70(1), 1-13, 2020

    J-STAGE  Ichushi Web 

  • Scope-aware Code Completion with Discriminative Modeling

    Sheng Hu , Chuan Xiao , Yoshiharu Ishikawa

    … In this paper, we propose a novel method to improve the quality of code completion by incorporating the users' acronym-like input conventions and the APIs' scope context into a discriminative model. … The users' input conventions are learned using a logistic regression model by extracting features from collected training data. … The weights in the discriminative model are learned using a support vector machine (SVM). …

    情報処理学会論文誌 60(8), 2019-08-15

    IPSJ 

  • Medical Education in Private Schools in Chosen During the Japanese Colonial Period : A Comparative Educational History of Severance Union Medical College  [in Japanese]

    松本 麻人 , MATSUMOTO Asato

    … Under a discriminative colonial education policy, schools in Chosen were evaluated as lower level schools as compared to Japanese schools. … In conclusion, we suggest that under the strict regulations for private schools during the colonial period, Severance Union Medical College maintained an advanced medical education for Korean students that contributed importantly to the training of Korean doctors and the development of medical research. …

    名古屋大学大学院教育発達科学研究科紀要. 教育科学 65(2), 29-41, 2019-03-31

    IR  DOI 

  • Improved C-COT based on feature channels confidence for visual tracking

    SHEN Shuwei , TIAN Shengjing , WANG Leyuan , SHEN Aihong , LIU Xiuping

    … <p>In the field of visual tracking, the methods of Discriminative Correlation Filters (DCF) have showed excellent performance, which rely heavily on the choice of feature descriptors. … Therefore, in order to reduce the redundancy of the online training sample and avoid similar background interference, we adopts the method of Peak Side Lobe Ratio (PSLR) to update the model. …

    Journal of Advanced Mechanical Design, Systems, and Manufacturing 13(5), JAMDSM0096-JAMDSM0096, 2019

    J-STAGE 

  • Occupational Natural Radiation Exposure at the Uranium Deposit of Kitongo, Cameroon

    Oumar Bobbo Modibo , Saïdou , Ndjana Nkoulou Ii Joseph Emmanuel , Suzuki Takahito , Kudo Hiromi , Hosoda Masahiro , Owono Owono Luc Calvin , Tokonami Shinji

    … <sup>222</sup>Rn-<sup>220</sup>Rn discriminative measurements were performed using passive type monitors. …

    RADIOISOTOPES 68(9), 621-630, 2019

    J-STAGE  Ichushi Web 

  • Scope-aware Code Completion with Discriminative Modeling

    Hu Sheng , Xiao Chuan , Ishikawa Yoshiharu

    … scope context into a discriminative model. … input conventions are learned using a logistic regression model by extracting features from collected training data. … The weights in the discriminative model are learned using a support vector machine (SVM). …

    Journal of Information Processing 27(0), 469-478, 2019

    J-STAGE 

  • Multi-View Synthesis and Analysis Dictionaries Learning for Classification

    WU Fei , DONG Xiwei , HAN Lu , JING Xiao-Yuan , JI Yi-mu

    … or <i>l</i><sub>1</sub>-norm sparsity constraint on the representation coefficients, which makes the training and testing phases time-consuming. … MSADL utilizes synthesis dictionaries to achieve class-specific reconstruction and uses analysis dictionaries to generate discriminative code coefficients by linear projection. …

    IEICE Transactions on Information and Systems E102.D(3), 659-662, 2019

    J-STAGE 

  • Development and Experimental Ealuation of Large Geometric Margin Minimum Classification Error Training for Classification of Variable-length Time Series Patterns  [in Japanese]

    松廣 達也 , 橋本 哲也 , 北岡 見生代 , ア デイビッド , 落合 翼 , 渡辺 秀行 , 片桐 滋 , 大崎 美穂

    最近,識別学習法の1つ,最小分類誤り(MCE: Minimum Classification Error)学習法が,大幾何マージン最小分類誤り(LGM-MCE: Large Geometric Margin Minimum Classification Error)学習法に拡張された.LGM-MCE法は,利用可能な学習用標本上の分類誤り数損失の最小化と,標本空間における幾何マージンの最大化とを同時 …

    情報処理学会論文誌 59(4), 1295-1308, 2018-04-15

    IPSJ 

  • Generalization tests using different dosing routes from those of drug discrimination training in rats

    Fujiwara Atsushi , Shimosawa Miki , Iino Masahiko , Sasaki Mikio , Sato Shin-ichi , Shimoi Akihito

    … <p>The purpose of this study was to investigate the discriminative stimulus properties of morphine and codeine using different administration routes to that used at drug discrimination training. … Generalization of morphine by the subcutaneous and the oral routes, and codeine by the intraperitoneal and the oral routes to the discriminative stimulus properties of the morphine training dose were investigated. …

    The Journal of Toxicological Sciences 43(7), 451-458, 2018

    J-STAGE  Ichushi Web 

  • Deep Attention Residual Hashing

    LI Yang , MIAO Zhuang , HE Ming , ZHANG Yafei , LI Hang

    … Compared to previous methods, our method does not need to generate all possible pairwise or triplet labels from the training dataset. … In addition, we embedded the attention layer into the residual network to simultaneously learn discriminative image features and hash codes in an end-to-end manner. …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E101.A(3), 654-657, 2018

    J-STAGE 

  • Learning Deep Relationship for Object Detection

    XU Nuo , HUO Chunlei

    … In recent years, training a model from labeled images using machine learning technique becomes popular. … However, the relationship between training samples is usually ignored by existing approaches. … To address this problem, a novel approach is proposed, which trains Siamese convolutional neural network on feature pairs and finely tunes the network driven by a small amount of training samples. …

    IEICE Transactions on Information and Systems E101.D(1), 273-276, 2018

    J-STAGE 

  • Prior-based Binary Masking and Discriminative Methods for Reverberant and Noisy Speech Recognition Using Distant Stereo Microphones

    Yuuki Tachioka , Shinji Watanabe , Jonathan Le Roux , John R. Hershey

    … This paper also validates state-of-the-art ASR techniques that include various discriminative training and feature transformation methods. … Furthermore, we develop an efficient method to combine discriminative language modeling and minimum Bayes risk decoding in the ASR post-processing stage. …

    情報処理学会論文誌 58(6), 2017-06-15

    IPSJ 

  • The Formation of Referential Function of Word as Receptive Language for Severely Child with Intellectual Disabilities  [in Japanese]

    大城 英名 , OSHIRO Eimei

    … The purpose of this study was to examine the effects of language training in a formation of referential function of word as receptive language for severely child with intellectual disabilities. … The subject who was 10 year-old boy with intellectual disabilities, was given six language training tasks for a year and half to form referential function of word. …

    秋田大学教育文化学部研究紀要 教育科学 = MEMOIRS OF FACULTY OF EDUCATION AND HUMAN STUDIES AKITA UNIVERSITY EDUCATIONAL SCIENCES (72), 1-10, 2017-03-01

    IR 

  • Improving Feature-space Discriminative Training and Adaptation Using Regularization Process  [in Japanese]

    福田 隆 , 市川 治 , 立花 隆輝

    GMM/HMMシステムにおいては,音響モデルを新たな音響環境に適応するため,MAP法などのモデル空間適応がさかんに利用されている.一方で,近年の音声認識システムは特徴空間上の識別学習を行っているものの,識別的特徴変換行列が環境適応の対象になることは少ない.しかし,識別的特徴変換行列は大規模データから統計的に学習されるため,音響モデルと並んで識別的変換行列も対象ドメインに適応することが望ましい.本論 …

    情報処理学会論文誌 58(1), 288-296, 2017-01-15

    IPSJ 

  • Differential Reinforcement of Absolute and Relative Discriminative Behaviors in Pigeons Using Conditional Discrimination Procedures  [in Japanese]

    KUBO NAOYA

    <p><b>研究の目的</b> 条件性弁別手続きを用いた絶対的弁別行動と相対的弁別行動の分化強化を施すことにより、同一個体内に2種の弁別行動を同時的に分化させることが可能か、ハトを対象に検討することを目的とした。<b>研究計画</b> 視覚的な図形を対象に、大きさの絶対的弁別行動と相対的弁別行動を分化強化する条件性弁別訓練を実施した後、新 …

    Japanese Journal of Behavior Analysis 32(1), 21-35, 2017

    J-STAGE 

  • Prior-based Binary Masking and Discriminative Methods for Reverberant and Noisy Speech Recognition Using Distant Stereo Microphones

    Tachioka Yuuki , Watanabe Shinji , Roux Jonathan Le , Hershey John R.

    … This paper also validates state-of-the-art ASR techniques that include various discriminative training and feature transformation methods. … Furthermore, we develop an efficient method to combine discriminative language modeling and minimum Bayes risk decoding in the ASR post-processing stage. …

    Journal of Information Processing 25(0), 407-416, 2017

    J-STAGE 

  • Deep Metric Learning for Video-Based Person Re-Identification  [in Japanese]

    KATO Naoki , HAKOZAKI Kohei , TANABIKI Masamoto , SATO Yuji , FURUYAMA Junko , AOKI Yoshimitsu

    … This simple change of parameter updating method significantly improves network training, enabling the embeddings to be further discriminative. …

    Journal of the Japan Society for Precision Engineering 83(12), 1117-1124, 2017

    J-STAGE 

  • Deep Discriminative Supervised Hashing via Siamese Network

    LI Yang , MIAO Zhuang , WANG Jiabao , ZHANG Yafei , LI Hang

    … However, generating all possible pairwise or triplet labels from the training dataset can quickly become intractable, where the majority of those samples may produce small costs, resulting in slow convergence. … In this letter, we propose a novel deep discriminative supervised hashing method, called DDSH, which directly learns hash codes based on a new combined loss function. …

    IEICE Transactions on Information and Systems E100.D(12), 3036-3040, 2017

    J-STAGE 

Page Top