Zobrazeno 1 - 10
of 643
pro vyhledávání: '"Liu, Anfeng"'
Autor:
Wang, Yi, Wang, Jiaze, Guo, Ziyu, Zhang, Renrui, Zhou, Donghao, Chen, Guangyong, Liu, Anfeng, Heng, Pheng-Ann
Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to perturbations a
Externí odkaz:
http://arxiv.org/abs/2411.14744
Autor:
Fan, Kejia, Li, Jiaxu, Lai, Songning, Lv, Linpu, Liu, Anfeng, Tang, Jianheng, Song, Houbing Herbert, Yue, Yutao, Zhuang, Huiping
Class-incremental pattern recognition in time series is a significant problem, which aims to learn from continually arriving streaming data examples with incremental classes. A primary challenge in this problem is catastrophic forgetting, where the i
Externí odkaz:
http://arxiv.org/abs/2410.15954
Autor:
Ren, Yingying, Li, Qiuli, Guo, Yangyang, Pedrycz, Witold, Xing, Lining, Liu, Anfeng, Song, Yanjie
With the rapid development of the satellite industry, the information transmission network based on communication satellites has gradually become a major and important part of the future satellite ground integration network. However, the low transmis
Externí odkaz:
http://arxiv.org/abs/2408.16300
Autor:
Wang, Jiaze, Wang, Yi, Guo, Ziyu, Zhang, Renrui, Zhou, Donghao, Chen, Guangyong, Liu, Anfeng, Heng, Pheng-Ann
We introduce MM-Mixing, a multi-modal mixing alignment framework for 3D understanding. MM-Mixing applies mixing-based methods to multi-modal data, preserving and optimizing cross-modal connections while enhancing diversity and improving alignment acr
Externí odkaz:
http://arxiv.org/abs/2405.18523
Autor:
Wang, Yi, Wang, Jiaze, Li, Jinpeng, Zhao, Zixu, Chen, Guangyong, Liu, Anfeng, Heng, Pheng-Ann
Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is relatively limited. While mixing-based augmentation has shown
Externí odkaz:
http://arxiv.org/abs/2303.06678
Autor:
Tang, Jianheng, Fan, Kejia, Xie, Wenxuan, Zeng, Luomin, Han, Feijiang, Huang, Guosheng, Wang, Tian, Liu, Anfeng, Zhang, Shaobo
Publikováno v:
Computer Communications, 2023, 206: 85-100
The recruitment of trustworthy and high-quality workers is an important research issue for MCS. Previous studies either assume that the qualities of workers are known in advance, or assume that the platform knows the qualities of workers once it rece
Externí odkaz:
http://arxiv.org/abs/2301.08563
Autor:
Han, Yaohui, Zhao, Mingyang, Shan, Nuanqiao, Liu, Anfeng, Wang, Tian, Song, Houbing, Zhang, Shaobo
Publikováno v:
In Expert Systems With Applications 15 November 2024 254
Autor:
Guo, Qianxue, He, Yasha, Li, Qian, Liu, Anfeng, Xiong, Neal N., He, Qian, Yang, Qiang, Zhang, Shaobo
Publikováno v:
In Future Generation Computer Systems February 2025 163
Publikováno v:
In Future Generation Computer Systems February 2025 163
Publikováno v:
In Future Generation Computer Systems August 2024 157:145-163