Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Yasheng Sun"'
Publikováno v:
IEEE Access, Vol 12, Pp 57288-57301 (2024)
While considerable progress has been made in achieving accurate lip synchronization for 3D speech-driven talking face generation, the task of incorporating expressive facial detail synthesis aligned with the speaker’s speaking status remains challe
Externí odkaz:
https://doaj.org/article/2de39d95a4964ebbbb868fca10a6dfda
Publikováno v:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cdb75fc6624af024f11ec9bf757345fd
https://doi.org/10.1109/wacv56688.2023.00606
https://doi.org/10.1109/wacv56688.2023.00606
Autor:
Yasheng Sun, Hang Zhou, Kaisiyuan Wang, Qianyi Wu, Zhibin Hong, Jingtuo Liu, Errui Ding, Jingdong Wang, Ziwei Liu, Koike Hideki
Previous studies have explored generating accurately lip-synced talking faces for arbitrary targets given audio conditions. However, most of them deform or generate the whole facial area, leading to non-realistic results. In this work, we delve into
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::631468666a304f3aefefe2ffbfbda892
Publikováno v:
IJCAI
What can we picture solely from a clip of speech? Previous research has shown the possibility of directly inferring the appearance of a person's face by listening to a voice. However, within human speech lies not only the biometric identity signal bu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::efec2e6b452eeb74e678a28c88822276
https://doi.org/10.24963/ijcai.2021/141
https://doi.org/10.24963/ijcai.2021/141
Publikováno v:
CVPR
While accurate lip synchronization has been achieved for arbitrary-subject audio-driven talking face generation, the problem of how to efficiently drive the head pose remains. Previous methods rely on pre-estimated structural information such as land
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::670ea49bef63f852b0dd3ee8bbb183cd
Publikováno v:
ICIP
In this paper, we introduce an approach for visual tracking in videos that predicts the bounding box location of a target object at every frame. This tracking problem is formulated as a sequential decision-making process where both historical and cur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::99077729d1f502f0c3182839a8af267c
https://doi.org/10.1109/icip40778.2020.9191145
https://doi.org/10.1109/icip40778.2020.9191145
Publikováno v:
2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC).
Learning to understand human behaviors and predict their trajectories is a prerequisite for an automated car to navigate through the crowd safely and efficiently. This problem is particularly challenging as it requires the car to jointly reason about
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d23b13fb055a8835dab5eeed2949332
https://doi.org/10.1109/itnec.2019.8729387
https://doi.org/10.1109/itnec.2019.8729387
Publikováno v:
2019 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA).
Learning to understand human behaviors and forecast their motions is a prerequisite for an automated car to navigate in urban traffic safely and efficiently. When pedestrians interact with a vehicle, they follow specific motion patterns based on thei
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b103a1354e2ff8ccf6195a94d948cc17
https://doi.org/10.1109/icaica.2019.8873455
https://doi.org/10.1109/icaica.2019.8873455
Publikováno v:
Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP).
We investigate a Plug-and-Play framework for microscopy image reconstruction under Poisson noise, by unfolding the reconstruction into a Newton iteration and a denoising-based algorithm. This method can flexibly embed various denoising priors into re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3d2678fc2c1da4d373c61f419bf92b9
https://doi.org/10.1364/cosi.2019.jw2a.5
https://doi.org/10.1364/cosi.2019.jw2a.5
Publikováno v:
Journal of Electronic Imaging. 28:1
Poisson image deconvolution remains an ill-posed research problem consisting of a nonquadratic data-fidelity term and an implicit regularization function. Recently, the plug-and-play (PnP) framework has provided a new method to reformulate the regula
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a605e0c4bb38ca5d208169448bddcb9
https://doi.org/10.1117/1.jei.28.4.043020
https://doi.org/10.1117/1.jei.28.4.043020