Zobrazeno 1 - 10
of 13
pro vyhledávání: '"ZHENGZHE LIU"'
Publikováno v:
ACM Transactions on Graphics; Apr2024, Vol. 43 Issue 2, p1-18, 18p
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2c832ceff23acaf782863344f413d383
https://doi.org/10.1109/cvpr52688.2022.00117
https://doi.org/10.1109/cvpr52688.2022.00117
Publikováno v:
IEEE transactions on neural networks and learning systems.
The performance of existing sign language recognition approaches is typically limited by the scale of training data. To address this issue, we propose a mutual enhancement network (MEN) for joint sign language recognition and education. First, a sign
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59534a859f7eb96d3f3f0f84a87a37e5
https://pubmed.ncbi.nlm.nih.gov/35613069
https://pubmed.ncbi.nlm.nih.gov/35613069
Publikováno v:
CVPR
Point cloud semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b333629fa8df88d79698f5474523336a
https://doi.org/10.1109/cvpr46437.2021.00177
https://doi.org/10.1109/cvpr46437.2021.00177
Publikováno v:
CVPR
Generative Adversarial Networks (GANs) can generate realistic fake face images that can easily fool human beings.On the contrary, a common Convolutional Neural Network(CNN) discriminator can achieve more than 99.9% accuracyin discerning fake/real ima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b23180940bd96030ecbc6c7b4a0f0b08
https://doi.org/10.1109/cvpr42600.2020.00808
https://doi.org/10.1109/cvpr42600.2020.00808
In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on top of two-stream CNNs, GeoNet++ captures the geometric relationships be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::31f8dc8eea484ad7f66b559fe0533106
Publikováno v:
ACM Multimedia
In this paper, we propose a self-boosted intelligent system for joint sign language recognition and automatic education. A novel Spatial-Temporal Net (ST-Net) is designed to exploit the temporal dynamics of localized hands for sign language recogniti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d3b7ae53f47c25460ff326bfd3b4aa42
https://doi.org/10.1145/3240508.3240530
https://doi.org/10.1145/3240508.3240530
Publikováno v:
CVPR
In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image. Building on top of two-stream CNNs, our GeoNet incorporates geometric relation between depth and surface normal via the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d70f7017d0f8363bf912778ea589ef7
https://doi.org/10.1109/cvpr.2018.00037
https://doi.org/10.1109/cvpr.2018.00037
Publikováno v:
SUI
We develop a real-time, robust and accurate sign language recognition system leveraging deep convolutional neural networks(DCNN). Our framework is able to prevent common problems such as error accumulation of existing frameworks and it outperforms st
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c8b09cf77c8e9ecc539983f46fa3c202
https://doi.org/10.1145/2983310.2989187
https://doi.org/10.1145/2983310.2989187
Publikováno v:
Computer Vision – ECCV 2016 ISBN: 9783319464831
ECCV (8)
ECCV (8)
Training neural networks for semantic segmentation is data hungry. Meanwhile annotating a large number of pixel-level segmentation masks needs enormous human effort. In this paper, we propose a framework with only image-level supervision. It unifies
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::00f39ea5d6c20d49af0e5b832b34fb9f
https://doi.org/10.1007/978-3-319-46484-8_6
https://doi.org/10.1007/978-3-319-46484-8_6