Zobrazeno 1 - 10
of 147
pro vyhledávání: '"Winston H. Hsu"'
Publikováno v:
IEEE Transactions on Multimedia. 24:61-72
Deep learning-based blind image deblurring plays an essential role in solving image blur since all existing kernels are limited in modeling the real world blur. Thus far, researchers focus on powerful models to handle the deblurring problem and achie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db6357c7ffc59bbfe45bbd44a5038320
https://doi.org/10.1109/tmm.2020.3045303
https://doi.org/10.1109/tmm.2020.3045303
The large amount of data collected by LiDAR sensors brings the issue of LiDAR point cloud compression (PCC). Previous works on LiDAR PCC have used range image representations and followed the predictive coding paradigm to create a basic prototype of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e90021e91cc46cb5a32ca9dce3068117
Autor:
Yu-Sheng Lin, Winston H. Hsu, Yi-Rong Chen, Yu-An Chen, Yu-Siang Wang, Zhe Yu Liu, Hsin-Ying Lee, Ya-Liang Chang
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 17:1-16
We study the XAI (explainable AI) on the face recognition task, particularly the face verification. Face verification has become a crucial task in recent days and it has been deployed to plenty of applications, such as access control, surveillance, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7b74926329ff60c12be7a25e7748167
https://doi.org/10.1145/3469288
https://doi.org/10.1145/3469288
Publikováno v:
2022 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::26b8a94c4e9caf7ec144fc63a61d8b8a
https://doi.org/10.1109/icip46576.2022.9897561
https://doi.org/10.1109/icip46576.2022.9897561
Autor:
Tsung-Han Wu, Yi-Syuan Liou, Shao-Ji Yuan, Hsin-Ying Lee, Tung-I Chen, Kuan-Chih Huang, Winston H. Hsu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198175
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8609a7c8863416e12d7c1db80e3d539a
https://doi.org/10.1007/978-3-031-19818-2_26
https://doi.org/10.1007/978-3-031-19818-2_26
Object detection in low-light conditions remains a challenging but important problem with many practical implications. Some recent works show that, in low-light conditions, object detectors using raw image data are more robust than detectors using im
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c0777a4163d43367aabdcea6c6a836be
Publikováno v:
CIKM
Spatial-temporal prediction is a critical problem for intelligent transportation, which is helpful for tasks such as traffic control and accident prevention. Previous studies rely on large-scale traffic data collected from sensors. However, it is unl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d1c87587c58b8b410a2f624ec541403
http://arxiv.org/abs/2108.08307
http://arxiv.org/abs/2108.08307
Publikováno v:
CIKM
Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boosted performance on various tasks using visual cues, deep cognition to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f17548d41b563fe1803f9aa3cb083988
http://arxiv.org/abs/2108.04542
http://arxiv.org/abs/2108.04542
Publikováno v:
ICASSP
Multi-party dialogue question answering (MPDQA) is an emerging topic in speech and language processing where the goal is to answer the questions according to the multiparty conversations. Different from conventional QA, which assumes a single speaker
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ce6f33778122714c5ce0b30d456a9a5
https://doi.org/10.1109/icassp39728.2021.9414980
https://doi.org/10.1109/icassp39728.2021.9414980
Autor:
Tsung-Lin Tsou, Hung-Ting Su, Yu-An Wang, Tsung-Han Wu, Winston H. Hsu, Yueh-Cheng Liu, Yu-Kai Huang, Yu-Cheng Chang
Publikováno v:
CVPR
Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g., LiDAR and Radar, has been leveraged as guidance for enhancing dense depth estimation, the improvem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2fec40a956e12cc73db254a08983a3eb
https://doi.org/10.1109/cvpr46437.2021.01643
https://doi.org/10.1109/cvpr46437.2021.01643