Zobrazeno 1 - 10
of 364
pro vyhledávání: '"Zhang Xianchao"'
Publikováno v:
中国工程科学, Vol 26, Iss 2, Pp 245-254 (2024)
Currently, the market demand for traditional Chinese herbal medicines and prepared slices is experiencing rapid growth, rendering quality control and safety assurance even more pressing issues. Conventional testing methods for traditional Chinese her
Externí odkaz:
https://doaj.org/article/c9891bca9255438db7ce3d40ff44b5ee
Cellular-connected unmanned aerial vehicle (UAV) communications is an enabling technology to transmit control signaling or payload data for UAVs through cellular networks. Due to the line-of-sight (LoS) dominant air-to-ground channels, efficient inte
Externí odkaz:
http://arxiv.org/abs/2409.13278
Knowledge graph (KG) reasoning is a task that aims to predict unknown facts based on known factual samples. Reasoning methods can be divided into two categories: rule-based methods and KG-embedding based methods. The former possesses precise reasonin
Externí odkaz:
http://arxiv.org/abs/2407.03704
Autor:
Liu, Han, Zhao, Siyang, Zhang, Xiaotong, Zhang, Feng, Wang, Wei, Ma, Fenglong, Chen, Hongyang, Yu, Hong, Zhang, Xianchao
Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen classes t
Externí odkaz:
http://arxiv.org/abs/2405.03565
Autor:
Liu, Han, Xu, Zhi, Zhang, Xiaotong, Zhang, Feng, Ma, Fenglong, Chen, Hongyang, Yu, Hong, Zhang, Xianchao
Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this problem is still in the embryonic
Externí odkaz:
http://arxiv.org/abs/2402.01806
Autor:
Liu, Han, Huang, Xingshuo, Zhang, Xiaotong, Li, Qimai, Ma, Fenglong, Wang, Wei, Chen, Hongyang, Yu, Hong, Zhang, Xianchao
Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box adversarial att
Externí odkaz:
http://arxiv.org/abs/2310.19038
Autor:
Liu, Han, Zhang, Feng, Zhang, Xiaotong, Zhao, Siyang, Ma, Fenglong, Wu, Xiao-Ming, Chen, Hongyang, Yu, Hong, Zhang, Xianchao
Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer
Externí odkaz:
http://arxiv.org/abs/2303.16764
Autor:
Tang, Peiwang, Zhang, Xianchao
The Transformer architecture yields state-of-the-art results in many tasks such as natural language processing (NLP) and computer vision (CV), since the ability to efficiently capture the precise long-range dependency coupling between input sequences
Externí odkaz:
http://arxiv.org/abs/2301.01772
Autor:
Tang, Peiwang, Zhang, Xianchao
Large-scale self-supervised pre-training Transformer architecture have significantly boosted the performance for various tasks in natural language processing (NLP) and computer vision (CV). However, there is a lack of researches on processing multiva
Externí odkaz:
http://arxiv.org/abs/2210.02199
Autor:
Tang, Peiwang, Zhang, Xianchao
Some data from multiple sources can be modeled as multimodal time-series events which have different sampling frequencies, data compositions, temporal relations and characteristics. Different types of events have complex nonlinear relationships, and
Externí odkaz:
http://arxiv.org/abs/2209.01728