Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Wing-Yin Yu"'
Publikováno v:
IEEE Access, Vol 11, Pp 72295-72305 (2023)
This paper presents CLIP Driven Few-shot Panoptic Segmentation (CLIP-FPS), a novel few-shot panoptic segmentation model that leverages the knowledge of Contrastive Language-Image Pre-training (CLIP) model. The proposed method builds upon a center ind
Externí odkaz:
https://doaj.org/article/5e676431ba6a4ff3bce3235bf1dbc7c0
Publikováno v:
Sensors, Vol 24, Iss 5, p 1411 (2024)
In this paper, we introduce a novel panoptic segmentation method called the Mask-Pyramid Network. Existing Mask RCNN-based methods first generate a large number of box proposals and then filter them at each feature level, which requires a lot of comp
Externí odkaz:
https://doaj.org/article/d2358fc309f147ba998b8819639a8359
Publikováno v:
Acta Dermato-Venereologica, Vol 99, Iss 6, Pp 616-617 (2019)
Externí odkaz:
https://doaj.org/article/a9a2ae260b3f415ca390ee62a1bf97bb
Autor:
Yuzhi, Zhao, Lai-Man, Po, Xuehui, Wang, Kangcheng, Liu, Yujia, Zhang, Wing-Yin, Yu, Pengfei, Xian, Jingjing, Xiong
There are quite a number of photographs captured under undesirable conditions in the last century. Thus, they are often noisy, regionally incomplete, and grayscale formatted. Conventional approaches mainly focus on one point so that those restoration
Externí odkaz:
http://arxiv.org/abs/2011.11309
Autor:
Wing Yin Yu, Stephanie1, Tin-Fong Zhuang, James1, Yin Lun Edward Chu2, Kay-Cheong Teo3, Kui Kai Lau3, Chun-On Tsang, Anderson1, Wai-Man Lui4 luiwm1@ha.org.hk
Publikováno v:
Surgical Practice. Nov2023, Vol. 27 Issue 4, p232-238. 7p.
Publikováno v:
IEEE Transactions on Multimedia. 25:1019-1032
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d553ecb329b935fd8f49817c02c778e
https://doi.org/10.1109/tmm.2021.3136085
https://doi.org/10.1109/tmm.2021.3136085
Autor:
Yujia Zhang, Lai-Man Po, Xuyuan Xu, Mengyang Liu, Yexin Wang, Weifeng Ou, Yuzhi Zhao, Wing-Yin Yu
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:3380-3389
Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled instances via
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a40859f67262a1244d05843dc2627540
https://doi.org/10.1609/aaai.v36i3.20248
https://doi.org/10.1609/aaai.v36i3.20248
Publikováno v:
IEEE Transactions on Image Processing. 31:2541-2556
In this paper, we present a novel end-to-end pose transfer framework to transform a source person image to an arbitrary pose with controllable attributes. Due to the spatial misalignment caused by occlusions and multi-viewpoints, maintaining high-qua
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22c81ccde3694041fdd2f3466980ab0e
https://doi.org/10.1109/tip.2022.3157146
https://doi.org/10.1109/tip.2022.3157146
Autor:
Yuzhi Zhao, Lai-Man Po, Xuehui Wang, Qiong Yan, Wei Shen, Yujia Zhang, Wei Liu, Chun-Kit Wong, Chiu-Sing Pang, Weifeng Ou, Wing Yin Yu, Buhua Liu
The appearances of children are inherited from their parents, which makes it feasible to predict them. Predicting realistic children's faces may help settle many social problems, such as age-invariant face recognition, kinship verification, and missi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::37fadbc59ad03b0856c48ec88e07aec4
http://arxiv.org/abs/2204.09962
http://arxiv.org/abs/2204.09962
Publikováno v:
2021 IEEE International Conference on Multimedia and Expo (ICME).
Due to unreliable geometric matching and content misalignment, most conventional pose transfer algorithms fail to generate fine-trained person images. In this paper, we propose a novel framework Spatial Content Alignment GAN (SCAGAN) which aims to en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8c4143619b98e8c1d91cffa8c146902
https://doi.org/10.1109/icme51207.2021.9428146
https://doi.org/10.1109/icme51207.2021.9428146