Takatsugu HIRAYAMA

Attribute-Aware Loss Function for Accurate Semantic Segmentation Considering the Pedestrian Orientations
Mahmud Dwi SULISTIYO Yasutomo KAWANISHI Daisuke DEGUCHI Ichiro IDE Takatsugu HIRAYAMA Jiang-Yu ZHENG Hiroshi MURASE 
Publication:   
Publication Date: 2020/01/01
Vol. E103-A  No. 1  pp. 231-242
Type of Manuscript:  Special Section PAPER (Special Section on Intelligent Transport Systems)
Category: 
Keyword: 
semantic segmentation, attribute-aware, pedestrian orientation, deep neural network, 
 Summary | Full Text:PDF
Estimation of the Attractiveness of Food Photography Based on Image Features
Kazuma TAKAHASHI Tatsumi HATTORI Keisuke DOMAN Yasutomo KAWANISHI Takatsugu HIRAYAMA Ichiro IDE Daisuke DEGUCHI Hiroshi MURASE 
Publication:   
Publication Date: 2019/08/01
Vol. E102-D  No. 8  pp. 1590-1593
Type of Manuscript:  LETTER
Category: Human-computer Interaction
Keyword: 
food photography, attractiveness, photographic framing, 
 Summary | Full Text:PDF
Pedestrian Detectability Estimation Considering Visual Adaptation to Drastic Illumination Change
Yuki IMAEDA Takatsugu HIRAYAMA Yasutomo KAWANISHI Daisuke DEGUCHI Ichiro IDE Hiroshi MURASE 
Publication:   
Publication Date: 2018/05/01
Vol. E101-D  No. 5  pp. 1457-1461
Type of Manuscript:  LETTER
Category: Image Recognition, Computer Vision
Keyword: 
ITS, driving assistance, pedestrian detectability, illumination change, visual adaptation, 
 Summary | Full Text:PDF
Personal Viewpoint Navigation Based on Object Trajectory Distribution for Multi-View Videos
Xueting WANG Kensho HARA Yu ENOKIBORI Takatsugu HIRAYAMA Kenji MASE 
Publication:   
Publication Date: 2018/01/01
Vol. E101-D  No. 1  pp. 193-204
Type of Manuscript:  PAPER
Category: Human-computer Interaction
Keyword: 
multi-view video navigation, user preference, Gaussian mixture model, 
 Summary | Full Text:PDF
Vote Distribution Model for Hough-Based Action Detection
Kensho HARA Takatsugu HIRAYAMA Kenji MASE 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/11/01
Vol. E99-D  No. 11  pp. 2796-2808
Type of Manuscript:  PAPER
Category: Image Recognition, Computer Vision
Keyword: 
action detection, Hough transform, Hough forests, 
 Summary | Full Text:PDF
Top-Down Visual Attention Estimation Using Spatially Localized Activation Based on Linear Separability of Visual Features
Takatsugu HIRAYAMA Toshiya OHIRA Kenji MASE 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/12/01
Vol. E98-D  No. 12  pp. 2308-2316
Type of Manuscript:  PAPER
Category: Image Recognition, Computer Vision
Keyword: 
human visual attention, visual search, saliency map, activation map, linear separability, 
 Summary | Full Text:PDF
Computational Models of Human Visual Attention and Their Implementations: A Survey
Akisato KIMURA Ryo YONETANI Takatsugu HIRAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2013/03/01
Vol. E96-D  No. 3  pp. 562-578
Type of Manuscript:  INVITED SURVEY PAPER
Category: 
Keyword: 
human visual attention, computational model, saliency, bottom-up, top-down, 
 Summary | Full Text:PDF
Estimates of User Interest Using Timing Structures between Proactive Content-Display Updates and Eye Movements
Takatsugu HIRAYAMA Jean-Baptiste DODANE Hiroaki KAWASHIMA Takashi MATSUYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/06/01
Vol. E93-D  No. 6  pp. 1470-1478
Type of Manuscript:  Special Section PAPER (Special Section on Info-Plosion)
Category: Human-computer Interaction
Keyword: 
proactive interaction, Mind Probing, interest estimation, gaze behavior, time-delay feature, 
 Summary | Full Text:PDF