Zobrazeno 1 - 10
of 149
pro vyhledávání: '"Pengchuan Zhang"'
Autor:
Kerlan-Stephens, Anne
Publikováno v:
Revue Bibliographique de Sinologie, 2001 Jan 01. 19, 286-286.
Externí odkaz:
https://www.jstor.org/stable/24580945
Autor:
Elisseeff, D.
Publikováno v:
Revue Bibliographique de Sinologie, 1983 Jan 01. 1, 99-99.
Externí odkaz:
https://www.jstor.org/stable/24617114
Autor:
Elisseeff, D.
Publikováno v:
Revue Bibliographique de Sinologie, 1985 Jan 01. 3, 118-119.
Externí odkaz:
https://www.jstor.org/stable/24618288
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d55aa8a9db87e6cc248262e756669cec
https://doi.org/10.1109/iccv48922.2021.00298
https://doi.org/10.1109/iccv48922.2021.00298
Autor:
Pengchuan Zhang, Yejin Choi, Xiaowei Hu, Lei Zhang, Jianfeng Gao, Xiujun Li, Jianwei Yang, Lijuan Wang
Publikováno v:
CVPR
This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used \emph{bottom
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::07409cb73679167c11b8338b0450132a
https://doi.org/10.1109/cvpr46437.2021.00553
https://doi.org/10.1109/cvpr46437.2021.00553
Publikováno v:
Computational Mechanics. 64:395-408
Deep generative networks have achieved great success in high dimensional density approximation, especially for applications in natural images and language. In this paper, we investigate their approximation capability in capturing the posterior distri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::904c19e98a29aadc176c3df9ec112940
https://doi.org/10.1007/s00466-019-01739-7
https://doi.org/10.1007/s00466-019-01739-7
Publikováno v:
Journal of Biomedical Science and Engineering. 12:514-521
Objective: To study an anti resistance active exercise training method which is consistent with the principle of “transcendental goal power” to promote the plasticity change of central nervous system (CNS) in order to recover the motor function a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fff4c3729d84cce3e7c98742dd18a27b
https://doi.org/10.4236/jbise.2019.1212042
https://doi.org/10.4236/jbise.2019.1212042
This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques. The first is the multi-scale
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d051960dc609ed1a88a953f8e627a1c9
Autor:
Yiwu Zhong, Jianwei Yang, Pengchuan Zhang, Chunyuan Li, Noel Codella, Liunian Harold Li, Luowei Zhou, Xiyang Dai, Lu Yuan, Yin Li, Jianfeng Gao
Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::baf81302823ab6fbd4fe95c90cc52665
Autor:
Pengchuan Zhang, Wenbo Li, Yi Wei, Jianfeng Gao, Lei Zhang, Zhe Gan, Ming-Ching Chang, Siwei Lyu
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695378
ACCV (4)
ACCV (4)
We present Mask-guided Generative Adversarial Network (MagGAN) for high-resolution face attribute editing, in which semantic facial masks from a pre-trained face parser are used to guide the fine-grained image editing process. With the introduction o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::12a95f1ab9540e2124f309ad7242c598
https://doi.org/10.1007/978-3-030-69538-5_40
https://doi.org/10.1007/978-3-030-69538-5_40