Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Zhong-Han Niu"'
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Defense Against Adversarial Attacks with Efficient Frequency-Adaptive Compression and Reconstruction
Autor:
Zhong-Han Niu, Yu-Bin Yang
Publikováno v:
Pattern Recognition. 138:109382
Publikováno v:
ICASSP
Deep neural networks have witnessed great success in Single Image Super-Resolution (SISR). However, current improvements are mainly contributed by much deeper networks, which leads to huge computation cost and limited application for mobile devices.
Publikováno v:
ICASSP
In recent years, part-based models have been verified their effectiveness for person Re-identification (Re-ID). Since they learn an embedding only by partitioning single-scale features of the highest layer in the backbone network, their performances
Publikováno v:
MultiMedia Modeling ISBN: 9783030377304
MMM (1)
MMM (1)
Deep convolutional neural networks (CNNs) have recently achieved impressive performance in image super-resolution (SR). However, they usually treat the spatial features and channel-wise features indiscriminatingly and fail to take full advantage of h
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16a307e3899ff84889d8284d546c1fa8
https://doi.org/10.1007/978-3-030-37731-1_46
https://doi.org/10.1007/978-3-030-37731-1_46
Publikováno v:
MultiMedia Modeling ISBN: 9783030057091
MMM (1)
MMM (1)
One-stage detectors are widely used in real-world computer vision applications nowadays due to their competitive accuracy and very fast speed. However, for high resolution (e.g., \(512 \times 512\)) input, most one-stage detectors run too slowly to p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c3c0b39031c07be0b5a6bc3c95ebf2d9
https://doi.org/10.1007/978-3-030-05710-7_2
https://doi.org/10.1007/978-3-030-05710-7_2
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319973036
PRICAI (1)
PRICAI (1)
Image restoration is a difficult task due to its non-uniqueness of solution. Owing to the power of Convolution Neural Networks (CNNs), we can generate images with high PSNR (Peak Signal to Noise Ratio) and SSIM (Structural SIMilarity index) by using
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36b802569a69df46261bd9f9181e0fa9
https://doi.org/10.1007/978-3-319-97304-3_10
https://doi.org/10.1007/978-3-319-97304-3_10
Publikováno v:
International Journal of Wireless and Mobile Computing. 11:100
In many data domains, especially for spatial data, clusters of data are of arbitrary shape, size and density. Traditional clustering methods often fail to identify clusters efficiently or accurately in those situations. But the need for scalable spat