Zobrazeno 1 - 10
of 180
pro vyhledávání: '"Siwei Lyu"'
Autor:
Siwei Lyu
Publikováno v:
Organizational Cybersecurity Journal, Vol 4, Iss 1, Pp 1-18 (2024)
Purpose – Recent years have witnessed an unexpected and astonishing rise of AI-generated (AIGC), thanks to the rapid advancement of technology and the omnipresence of social media. AIGCs created to mislead are more commonly known as DeepFakes, whic
Externí odkaz:
https://doaj.org/article/27512ce254b24804ad8afe25521affc2
Publikováno v:
IEEE Access, Vol 11, Pp 65546-65558 (2023)
Learning-based image registration approaches typically learn to map from input images to a transformation matrix. Regarding the current deep-learning-based image rigid registration approaches learn a transformation matrix in a one-shot way. Our purpo
Externí odkaz:
https://doaj.org/article/f5aa9dfbdb4c409e947895167a0f27c9
Autor:
Yi Lu, Bin Kong, Feng Gao, Kunlin Cao, Siwei Lyu, Shaoting Zhang, Shu Hu, Youbing Yin, Xin Wang
Publikováno v:
Frontiers in Physics, Vol 11 (2023)
Modeling sequential information for image sequences is a vital step of various vision tasks and convolutional long short-term memory (ConvLSTM) has demonstrated its superb performance in such spatiotemporal problems. Nevertheless, the hierarchical da
Externí odkaz:
https://doaj.org/article/2e15047031aa4744ae43c9504a7a35db
Publikováno v:
IEEE Access, Vol 10, Pp 32574-32583 (2022)
Generative Adversarial Network (GAN) based techniques can generate and synthesize realistic faces that cause profound social concerns and security problems. Existing methods for detecting GAN-generated faces can perform well on limited public dataset
Externí odkaz:
https://doaj.org/article/ede2b199acd642c3a964034f3af4a80b
Publikováno v:
IEEE Access, Vol 8, Pp 21717-21727 (2020)
This work studies multi-label learning (MLL), where each instance is associated with a subset of positive labels. For each instance, a good multi-label predictor should encourage the predicted positive labels to be close to its ground-truth positive
Externí odkaz:
https://doaj.org/article/b5e0b561fd64449dadb511b669cef310
Publikováno v:
Frontiers in Applied Mathematics and Statistics, Vol 5 (2019)
Area under the ROC curve (AUC) is a standard metric that is used to measure classification performance for imbalanced class data. Developing stochastic learning algorithms that maximize AUC over accuracy is of practical interest. However, AUC maximiz
Externí odkaz:
https://doaj.org/article/bb3bedd2aade4678b9e58c7e00508360
The unprecedented spread of false and misleading information is the flip side of the Internet's promise of universal access and information democratization. This volume features original contributions from scholars working on the challenge of misinfo
Externí odkaz:
https://library.oapen.org/handle/20.500.12657/93908
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 34:2633-2646
Scene parsing, or semantic segmentation, aims at labeling all pixels in an image with the predefined categories of things and stuff. Learning a robust representation for each pixel is crucial for this task. Existing state-of-the-art (SOTA) algorithms
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b9ab28f487b06d67717bf13a577bb9ea
https://doi.org/10.1109/tnnls.2021.3107194
https://doi.org/10.1109/tnnls.2021.3107194
Publikováno v:
Pattern Recognition Letters. 161:90-98
Face synthesis is an important problem in computer vision with many applications. In this work, we describe a new method, namely LandmarkGAN, to synthesize faces based on facial landmarks as input. Facial landmarks are a natural, intuitive, and effec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6dbfdc8f5dbdd909830e3f76a00a1175
https://doi.org/10.1016/j.patrec.2022.07.004
https://doi.org/10.1016/j.patrec.2022.07.004
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:3673-3684
Face manipulation techniques improve fast with the development of powerful image generation models. Two particular face manipulation methods, namely face swap and expression reenactment attract much attention for their flexibility and ease to generat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6afc3769e1d4165c0a17e08ff0527e25
https://doi.org/10.1109/tcsvt.2021.3106047
https://doi.org/10.1109/tcsvt.2021.3106047