Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Shang-Ta Yang"'
Face anti-spoofing (FAS) plays a critical role in securing face recognition systems from different presentation attacks. Previous works leverage auxiliary pixel-level supervision and domain generalization approaches to address unseen spoof types. How
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1ca0b73786e5596b95da680acc6de8e
http://arxiv.org/abs/2203.14325
http://arxiv.org/abs/2203.14325
Autor:
Juan-Ting Lin, Min Sun, Meng-Li Shih, Hung-Kuo Chu, Hou-Ning Hu, Hsien-Tzu Cheng, Fu-En Wang, Shang-Ta Yang
Publikováno v:
Computer Vision – ACCV 2018 ISBN: 9783030208721
ACCV (5)
ACCV (5)
As 360\(^{\circ }\) cameras become prevalent in many autonomous systems (e.g., self-driving cars and drones), efficient 360\(^{\circ }\) perception becomes more and more important. We propose a novel self-supervised learning approach for predicting t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::08578b3618842497cfdd8bdb407b426d
https://doi.org/10.1007/978-3-030-20873-8_4
https://doi.org/10.1007/978-3-030-20873-8_4
Publikováno v:
SIGGRAPH ASIA Posters
We present PanoAnnotator, a semi-automatic system that facilitates the annotation of 2D indoor panoramas to obtain high-quality 3D room layouts. Observing that fully-automatic methods are often restricted to a subset of indoor panoramas and generate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bc2d6139e36f442135cc3570ec6311e2
https://doi.org/10.1145/3283289.3283304
https://doi.org/10.1145/3283289.3283304
Publikováno v:
CVPR
We present a deep learning framework, called DuLa-Net, to predict Manhattan-world 3D room layouts from a single RGB panorama. To achieve better prediction accuracy, our method leverages two projections of the panorama at once, namely the equirectangu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf515db417a29bf2c23970eb2d960977