Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Jayakorn Vongkulbhisal"'
Publikováno v:
IEEE Access, Vol 9, Pp 56140-56151 (2021)
Trajectory prediction has gained great attention and significant progress has been made in recent years. However, most works rely on a key assumption that each video is successfully preprocessed by detection and tracking algorithms and the complete o
Externí odkaz:
https://doaj.org/article/a45f63693d9043ef8c6a18418daaab63
Autor:
Masaki Kuribayashi, Seita Kayukawa, Jayakorn Vongkulbhisal, Chieko Asakawa, Daisuke Sato, Hironobu Takagi, Shigeo Morishima
Publikováno v:
Proceedings of the ACM on Human-Computer Interaction. 6:1-22
Navigating in an indoor corridor can be challenging for blind people as they have to be aware of obstacles while also having to recognize the intersections that lead to the destination. To aid blind people in such tasks, we propose Corridor-Walker, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c5cf196284441ef75ea1bc577493ec7
https://doi.org/10.1145/3546714
https://doi.org/10.1145/3546714
Autor:
Masaki Kuribayashi, Tatsuya Ishihara, Daisuke Sato, Jayakorn Vongkulbhisal, Karnik Ram, Seita Kayukawa, Hironobu Takagi, Shigeo Morishima, Chieko Asakawa
Publikováno v:
Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23fd517c0ab4b8e1fd00d2fcd21e7040
https://doi.org/10.1145/3544548.3580687
https://doi.org/10.1145/3544548.3580687
Publikováno v:
IEEE Access, Vol 9, Pp 56140-56151 (2021)
Trajectory prediction has gained great attention and significant progress has been made in recent years. However, most works rely on a key assumption that each video is successfully preprocessed by detection and tracking algorithms and the complete o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e59d23c39b58de4d16908a9a42709f0
http://arxiv.org/abs/2203.07098
http://arxiv.org/abs/2203.07098
Autor:
Ryuki Tachibana, Guillaume Le Moing, Jayakorn Vongkulbhisal, Tadanobu Inoue, Don Joven Agravante, Phongtharin Vinayavekhin, Asim Munawar
Publikováno v:
ICASSP
Deep neural networks have recently led to promising results for the task of multiple sound source localization. Yet, they require a lot of training data to cover a variety of acoustic conditions and microphone array layouts. One can leverage acoustic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e8e0d58875a425af8a785efa6fcb916
https://doi.org/10.1109/icassp39728.2021.9413695
https://doi.org/10.1109/icassp39728.2021.9413695
Publikováno v:
CVPR
The focal loss has demonstrated its effectiveness in many real-world applications such as object detection and image classification, but its theoretical understanding has been limited so far. In this paper, we first prove that the focal loss is class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c4f503b5d98a5ee26689fab29f05654
https://doi.org/10.1109/cvpr46437.2021.00516
https://doi.org/10.1109/cvpr46437.2021.00516
Autor:
Jayakorn Vongkulbhisal, Ryuki Tachibana, Tadanobu Inoue, Don Joven Agravante, Guillaume Le Moing, Phongtharin Vinayavekhin, Asim Munawar
Publikováno v:
MMSP
In this paper, we propose novel deep learning based algorithms for multiple sound source localization. Specifically, we aim to find the 2D Cartesian coordinates of multiple sound sources in an enclosed environment by using multiple microphone arrays.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f06a403e696680c7b1a73f49841b9176
http://arxiv.org/abs/2012.05515
http://arxiv.org/abs/2012.05515
Publikováno v:
CVPR
Rigid Point Cloud Registration (PCReg) refers to the problem of finding the rigid transformation between two sets of point clouds. This problem is particularly important due to the advances in new 3D sensing hardware, and it is challenging because ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b9010207394b8e93fa134eea6118176
https://doi.org/10.1109/cvpr.2018.00316
https://doi.org/10.1109/cvpr.2018.00316
Autor:
Jayakorn Vongkulbhisal
Many computer vision problems are formulated as the optimization of a cost function. This approach faces two main challenges: (i) designing a cost function with a local optimum at an acceptable solution, and (ii) developing an efficient numerical met
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6adf2b6194a0542c6b7a85e1bb850aef
Publikováno v:
CVPR
Many computer vision problems are formulated as the optimization of a cost function. This approach faces two main challenges: (1) designing a cost function with a local optimum at an acceptable solution, and (2) developing an efficient numerical meth
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af875b455fdc552fde4fe606e318a365
https://doi.org/10.1109/cvpr.2017.423
https://doi.org/10.1109/cvpr.2017.423