Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Daiheng Gao"'
Manipulating latent code in generative adversarial networks (GANs) for facial image synthesis mainly focuses on continuous attribute synthesis (e.g., age, pose and emotion), while discrete attribute synthesis (like face mask and eyeglasses) receives
Externí odkaz:
http://arxiv.org/abs/2207.05300
Publikováno v:
International Journal of Computer Vision.
This paper studies compositional 3D-aware image synthesis for both single-object and multi-object scenes. We observe that two challenges remain in this field: existing approaches (1) lack geometry constraints and thus compromise the multi-view consis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be0a39e6cbaed8666c71a31b7c8779b4
https://doi.org/10.1007/s11263-023-01805-x
https://doi.org/10.1007/s11263-023-01805-x
Publikováno v:
Pattern Recognition. 141:109628
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb41442765742ce64133393cde56300d
https://doi.org/10.1016/j.patcog.2023.109628
https://doi.org/10.1016/j.patcog.2023.109628
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::08ed50f69237e1fcf062d7f4c1c4a9da
https://doi.org/10.1145/3503161.3547828
https://doi.org/10.1145/3503161.3547828
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view consistent i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7c535bcc4efbdaa597cb60ef674df5f
https://doi.org/10.1109/cvpr52688.2022.01790
https://doi.org/10.1109/cvpr52688.2022.01790
Autor:
Qi Wang, Yinghui Xu, Li Hu, Haiming Zhao, Peng Zhang, Daiheng Gao, Jian Cao, Lian Zhuo, Bang Zhang, Jinwei Qi, Pan Pan, Xiaoduan Feng
Publikováno v:
ACM Multimedia
Virtual character has been widely adopted in many areas, such as virtual assistant, virtual customer service, robotics and etc. In this paper, we focus on its application in e-commerce live streaming. Particularly, we propose a virtual character gene
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ab38542b7d5d780a5e0900dc30f5e9c
https://doi.org/10.1145/3474085.3481547
https://doi.org/10.1145/3474085.3481547
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61afd789f75d73aa9f4450d679fce1c8
https://doi.org/10.1109/iccvw54120.2021.00256
https://doi.org/10.1109/iccvw54120.2021.00256
Publikováno v:
Human Brain and Artificial Intelligence ISBN: 9789811612879
Spiking neural networks (SNNs), stem from neuroscience, are promising for energy-efficient information processing due to the “event-driven” characteristic, whereas, they are inferior to artificial neural networks (ANNs) in real complicated tasks.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d6f19cb6db8cd5f01f8b34233a224f4
https://doi.org/10.1007/978-981-16-1288-6_1
https://doi.org/10.1007/978-981-16-1288-6_1
Publikováno v:
ICIP
Pedestrian attribute analysis, which is a vital component in the intelligent video surveillance area, can facilitate person retrieval, searching and indexing. However, the resolution of the surveillance video is relatively low. The ability of neural
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02fe0be73b16b8be0289882e4075489e
https://doi.org/10.1109/icip.2019.8803069
https://doi.org/10.1109/icip.2019.8803069