|
|
|
Chih-Chung Hsu, Yi-Xiu Zhuang and Chia-Yen Lee
Generative adversarial networks (GANs) can be used to generate a photo-realistic image from a low-dimension random noise. Such a synthesized (fake) image with inappropriate content can be used on social media networks, which can cause severe problems. Wi...
ver más
|
|
|
|
|
|
|
Viacheslav Moskalenko, Vyacheslav Kharchenko, Alona Moskalenko and Sergey Petrov
Modern trainable image recognition models are vulnerable to different types of perturbations; hence, the development of resilient intelligent algorithms for safety-critical applications remains a relevant concern to reduce the impact of perturbation on m...
ver más
|
|
|
|
|
|
|
Linkai Peng, Yingming Gao, Rian Bao, Ya Li and Jinsong Zhang
As an indispensable module of computer-aided pronunciation training (CAPT) systems, mispronunciation detection and diagnosis (MDD) techniques have attracted a lot of attention from academia and industry over the past decade. To train robust MDD models, t...
ver más
|
|
|
|
|
|
|
Fei Yan, Hui Zhang, Yaogen Li, Yongjia Yang and Yinping Liu
Raw image classification datasets generally maintain a long-tailed distribution in the real world. Standard classification algorithms face a substantial issue because many labels only relate to a few categories. The model learning processes will tend tow...
ver más
|
|
|
|
|
|
|
Achintya Kumar Sarkar and Zheng-Hua Tan
Deep representation learning has gained significant momentum in advancing text-dependent speaker verification (TD-SV) systems. When designing deep neural networks (DNN) for extracting bottleneck (BN) features, the key considerations include training targ...
ver más
|
|
|
|
|
|
|
Tomas Iesmantas, Agne Paulauskaite-Taraseviciene and Kristina Sutiene
(1) Background: The segmentation of cell nuclei is an essential task in a wide range of biomedical studies and clinical practices. The full automation of this process remains a challenge due to intra- and internuclear variations across a wide range of ti...
ver más
|
|
|
|
|
|
|
Jie Wang, Jie Yang, Jiafan He and Dongliang Peng
Semi-supervised learning has been proven to be effective in utilizing unlabeled samples to mitigate the problem of limited labeled data. Traditional semi-supervised learning methods generate pseudo-labels for unlabeled samples and train the classifier us...
ver más
|
|
|
|
|
|
|
Sizhe Luo, Weiming Zeng and Bowen Sun
With the increasing popularity of automatic identification system AIS devices, mining latent vessel motion patterns from AIS data has become a hot topic in water transportation research. Trajectory similarity computation is a fundamental issue to many ma...
ver más
|
|
|
|
|
|
|
Yubo Zheng, Yingying Luo, Hengyi Shao, Lin Zhang and Lei Li
Contrastive learning, as an unsupervised technique, has emerged as a prominent method in time series representation learning tasks, serving as a viable solution to the scarcity of annotated data. However, the application of data augmentation methods duri...
ver más
|
|
|
|
|
|
|
Wenjin Hu, Yukun Chen, Lifang Wu, Ge Shi and Meng Jian
Hamming space retrieval is a hot area of research in deep hashing because it is effective for large-scale image retrieval. Existing hashing algorithms have not fully used the absolute boundary to discriminate the data inside and outside the Hamming ball,...
ver más
|
|
|
|
|
|
|
Feng Zhu, Jieyu Zhao and Zhengyi Cai
At present, the unsupervised visual representation learning of the point cloud model is mainly based on generative methods, but the generative methods pay too much attention to the details of each point, thus ignoring the learning of semantic information...
ver más
|
|
|
|