Publishing type：Research paper (scientific journal)  

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr2109.html#abs-2109-04307

Publishing type：Research paper (international conference proceedings)   Publisher：PMLR  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/corl/2020

Publishing type：Research paper (scientific journal)  

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr2011.html#abs-2011-00155

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/IROS45743.2020.9341620

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/iros/iros2020.html#OtaSJYK20

Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3444685.3446257

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/mmasia/mmasia2020.html#KonnoAK20

Publishing type：Research paper (scientific journal)  

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr2003.html#abs-2003-01641

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1109/TIP.2020.3011269

Web of Science

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr2007.html#abs-2007-09990

Publishing type：Research paper (scientific journal)  

DOI： 10.1109/LRA.2020.2967677

researchmap

Publishing type：Research paper (scientific journal)  

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr2009.html#abs-2009-07476

Publishing type：Research paper (scientific journal)  

DOI： 10.1109/TIP.2020.3011269

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels for training, our method treats the viewpoint labels as latent variables, which are learned in an unsupervised manner during the training using an unaligned object dataset. RotationNet uses only a partial set of multi-view images for inference, and this property makes it useful in practical scenarios where only partial views are available. Moreover, our pose alignment strategy enables one to obtain view-specific feature representations shared across classes, which is important to maintain high accuracy in both object categorization and pose estimation. Effectiveness of RotationNet is demonstrated by its superior performance to the state-of-the-art methods of 3D object classification on 10- and 40-class ModelNet datasets. We also show that RotationNet, even trained without known poses, achieves comparable performance to the state-of-the-art methods on an object pose estimation dataset. Furthermore, our object ranking method based on classification by RotationNet achieved the first prize in two tracks of the 3D Shape Retrieval Contest (SHREC) 2017. Finally, we demonstrate the performance of real-world applications of RotationNet trained with our newly created multi-view image dataset using a moving USB camera.

DOI： 10.1109/TPAMI.2019.2922640

PubMed

researchmap

Language：English   Publishing type：Part of collection (book)   Publisher：Elsevier  

DOI： 10.1016/B978-0-12-817358-9.00008-1

Scopus

researchmap

Language：Japanese   Publisher：The Japan Society of Mechanical Engineers  

<p>The paper proposes a motion planning algorithm using deep reinforced learning algorithm; Asynchronous Actor-Critic Agents(A3C)．For mobile robot navigation tasks in crowded situations, existingpath planning based approaches are limited because the surrounding environment is changing dynamically. The correct motion in such a dynamic environment is underspecified, and reinforced learning approach is suitable to generate applicable motion. We propose A3C based motion planning method to acquire mobile robot motion going through crowds of people situation. The proposed method is evaluated in simulated crowds of pedestrians. The experiment section shows the basic performance depending on training parameters and some generated motion examples in the simulator.</p>

DOI： 10.1299/jsmermd.2019.2P2-B03

CiNii Research

researchmap

Publishing type：Research paper (scientific journal)  

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr1902.html#abs-1902-10993

Language：Japanese   Publisher：The Japan Society of Mechanical Engineers  

<p>Recently, it has been required to automate the task of displaying products in convenience stores by robots. In this paper, we use a deep learning-based method to recognize pose and category of product. However, when an object is photographed by a camera, the recognition rate of objects with few features in color and shape is low. Therefore, we made a hypothesis that the recognition rate is improved by adding some features to the product. Two types of color markers were developed and those recognition rates were examined by using AlexNet. As a result, the proposed markers were able to improve the category recognition rate and pose recognition rate of the products.</p>

DOI： 10.1299/jsmermd.2019.2P1-Q01

CiNii Research

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/SMC.2019.8914201

Web of Science

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/smc/smc2019.html#SasakiMKT19

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/ICASSP.2019.8682522

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/icassp/icassp2019.html#ImamogluDFKKN19

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1109/LRA.2017.2783400

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1007/s11760-017-1159-7

Web of Science

Scopus

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/sivp/sivp12.html#ImamogluSZFKYN18

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

<p>We propose a semi-supervised method for estimating the number and locations of products in pictures. Many existing approaches can estimate objects locations in images by supervised learning which needs images annotated with objects locations. On the other hand, our method needs only numbers of objects in images. The experiment shows effectiveness of our method.</p>

DOI： 10.11517/pjsai.JSAI2018.0_4M204

CiNii Research

J-GLOBAL

researchmap

Publishing type：Research paper (scientific journal)  

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr1807.html#abs-1807-01532

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/CVPR.2018.00526

Web of Science

researchmap

Other Link： https://dblp.uni-trier.de/conf/cvpr/2018

Publishing type：Research paper (international conference proceedings)   Publisher：SciTePress  

DOI： 10.5220/0006691303610368

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/csedu/csedu2018-2.html#OonoNKKY18

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ICASSP.2018.8462533

Web of Science

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/icassp/icassp2018.html#Kanezaki18

Publishing type：Research paper (international conference proceedings)   Publisher：Eurographics Association  

DOI： 10.2312/3dor.20171048

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/3dor/3dor2017.html#HuaTTPKLCH0LJTA17

Publishing type：Research paper (scientific journal)  

The paper gives futuristic challenges disscussed in the cvpaper.challenge. In<br />
2015 and 2016, we thoroughly study 1,600+ papers in several<br />
conferences/journals such as CVPR/ICCV/ECCV/NIPS/PAMI/IJCV.

arXiv

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr1707.html#KataokaSHUSAKMY17

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Eurographics Association  

DOI： 10.2312/3dor.20171050

Scopus

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/3dor/3dor2017.html#SavvaYSKFOZYBBA17

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ICCVW.2017.54

Web of Science

Scopus

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/iccvw/iccvw2017.html#KugaKSSM17

Language：Japanese  

J-GLOBAL

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ICME.2016.7552915

Web of Science

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/icmcs/icme2016.html#SaitoKH16

Publishing type：Research paper (scientific journal)  

researchmap

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr1603.html#Kanezaki16

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/CVPR.2016.338

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/CVPR.2016.338

Web of Science

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/cvpr/cvpr2016.html#OhnishiKKH16

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electrical and Electronics Engineers Inc.  

DOI： 10.1109/3DV.2014.61

Scopus

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1145/2733373.2806299

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/IROS.2015.7353358

Web of Science

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

We propose an optimization method for estimating parameters in graph-theoretical formulations of the matching problem for object detection. Unlike several methods which optimize parameters for graph matching in a way to promote correct correspondences and to restrict wrong ones, our approach aims at improving performance in the more general task of object detection. In our formulation, similarity functions are adjusted so as to increase the overall similarity among a reference model and the observed target, and at the same time reduce the similarity among reference and "non-target" objects. We evaluate the proposed method in two challenging scenarios, demonstrating substantial improvements in both settings.

CiNii Books

CiNii Research

J-GLOBAL

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1007/s10846-013-0011-8

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ICRA.2014.6907300

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1145/2647868.2655009

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1145/2647868.2655021

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ICIP.2014.7025319

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1145/2502081.2502159

Scopus

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

We propose an efficient method to train multiple object detectors simultaneously using a large-scale image dataset. The one-vs-all approach that optimizes the boundary between positive samples from a target class and negative samples from the others has been the most standard approach for object detection. However, because this approach trains each object detector independently, the likelihoods are not balanced between object classes. The proposed method combines ideas derived from both detection and classification in order to balance the scores across all object classes. We optimized the boundary between target classes and their hard-negative samples, just as in detection, while simultaneously balancing the detector likelihoods across obj ect classes, as done in multi-class classification. We evaluated the performances on multi-class object detection using a subset of the ImageNet Large Scale Visual Recognition Challenge(ILSVRC) 2011 dataset and showed our method outperformed a de facto standard method.

CiNii Books

CiNii Research

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

We propose an efficient method to train multiple object detectors simultaneously using a large-scale image dataset. The one-vs-all approach that optimizes the boundary between positive samples from a target class and negative samples from the others has been the most standard approach for object detection. However, because this approach trains each object detector independently, the likelihoods are not balanced between object classes. The proposed method combines ideas derived from both detection and classification in order to balance the scores across all object classes. We optimized the boundary between target classes and their hard-negative samples, just as in detection, while simultaneously balancing the detector likelihoods across object classes, as done in multi-class classification. We evaluated the performances on multi-class object detection using a subset of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2011 dataset and showed our method outperformed a de facto standard method.

CiNii Books

researchmap

Language：Japanese   Publisher：Information Processing Society of Japan (IPSJ)  

We propose an efficient method to train multiple object detectors simultaneously using a large-scale image dataset.The one-vs-all approach that optimizes the boundary between positive samples from a target class and negative samples from the others has been the most standard approach for object detection. However, because this approach trains each object detector independently, the likelihoods are not balanced between object classes. The proposed method combines ideas derived from both detection and classification in order to balance the scores across all object classes. We optimized the boundary between target classes and their hard-negative samples, just as in detection, while simultaneously balancing the detector likelihoods across object classes, as done in multi-class classification. We evaluated the performances on multi-class object detection using a subset of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2011 dataset and showed our method outperformed a de facto standard method.

CiNii Books

CiNii Research

researchmap

Language：Japanese   Publisher：一般社団法人情報処理学会  

We propose an efficient method to train multiple object detectors simultaneously using a large-scale image dataset.The one-vs-all approach that optimizes the boundary between positive samples from a target class and negative samples from the others has been the most standard approach for object detection. However, because this approach trains each object detector independently, the likelihoods are not balanced between object classes. The proposed method combines ideas derived from both detection and classification in order to balance the scores across all object classes. We optimized the boundary between target classes and their hard-negative samples, just as in detection, while simultaneously balancing the detector likelihoods across object classes, as done in multi-class classification. We evaluated the performances on multi-class object detection using a subset of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2011 dataset and showed our method outperformed a de facto standard method.

J-GLOBAL

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ICCVW.2011.6130300

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ICRA.2011.5980129

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1007/s00371-010-0521-3

Web of Science

Scopus

CiNii Research

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ROBOT.2010.5509271

Web of Science

Scopus

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

As a previous work, we proposed a method of high-speed 3D object recognition using linear subspace method and our 3D features. This method enables matching of 3D models in a database and partial models with any size in any posture in a 3D scene, with highly short computation time. In this paper, we experiment on the performance of our method using real 3D models and 3D scenes, which are measured in a day-to-day human environment. In the experiments we compare our method with conventional methods using Spin-Images and Textured Spin-Images. Moreover, we demonstrate and discuss the performance of our method on searching for objects in a real 3D scene.

CiNii Books

CiNii Research

J-GLOBAL

researchmap

Language：Japanese   Publisher：The Robotics Society of Japan  

We present a new feature &ldquo;Color Cubic Higher-order Auto-Correlation (Color CHLAC) features&rdquo; to recognize objects in the real world versatilely and robustly. The new features satisfy the necessary functions for the exploration of objects in a three-dimensional map. In order to search and retrieve objects in a three-dimensional map, the features should have the co-occurrence of textures and shapes, robustness for partial observations and noise, ability to adapt a widespread environment, scalability, and invariance for many transformations. We studied experiments both in a simulation and a real environment for recognition of objects, which have many kinds of shapes and textures, and then we showed that our proposed features obtain high recognition accuracy in both situations.

DOI： 10.7210/jrsj.27.749

CiNii Books

CiNii Research

J-GLOBAL

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.2312/3DOR/3DOR09/009-012

Scopus

researchmap

Language：Japanese   Publisher：The Robotics Society of Japan  

We present a new feature “Color Cubic Higher-order Auto-Correlation (Color CHLAC) features” to recognize objects in the real world versatilely and robustly. The new features satisfy the necessary functions for the exploration of objects in a three-dimensional map. In order to search and retrieve objects in a three-dimensional map, the features should have the co-occurrence of textures and shapes, robustness for partial observations and noise, ability to adapt a widespread environment, scalability, and invariance for many transformations. We studied experiments both in a simulation and a real environment for recognition of objects, which have many kinds of shapes and textures, and then we showed that our proposed features obtain high recognition accuracy in both situations.

DOI： 10.7210/jrsj.27.749

CiNii Books

CiNii Research

J-GLOBAL

researchmap

Language：Japanese   Publisher：一般社団法人電子情報通信学会  

DOI： 10.1587/ieiceissjournal.21.4_16

CiNii Research

researchmap

CiNii Research

researchmap