Zobrazeno 1 - 10
of 114
pro vyhledávání: '"Hu, YunQing"'
Autor:
Kenny, Eoin M., Dharmavaram, Akshay, Lee, Sang Uk, Phan-Minh, Tung, Rajesh, Shreyas, Hu, Yunqing, Major, Laura, Tomov, Momchil S., Shah, Julie A.
Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. However, the opacity of such black-box motion planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with p
Externí odkaz:
http://arxiv.org/abs/2411.18714
Parameter regularization or allocation methods are effective in overcoming catastrophic forgetting in lifelong learning. However, they solve all tasks in a sequence uniformly and ignore the differences in the learning difficulty of different tasks. S
Externí odkaz:
http://arxiv.org/abs/2304.05288
Publikováno v:
Kongzhi Yu Xinxi Jishu, Iss 2, Pp 72-80 (2024)
Open-pit mines, characterized by complicated environmental conditions and unstructured roads, pose challenges for the path planning of mine trucks, marked by inefficiency due to long-distance search and the need to adhere to the left-hand traffic rul
Externí odkaz:
https://doaj.org/article/1bee4d322ba24595b807b3db998b1d89
Autor:
Hu, Yunqing, Jin, Xuan, Zhang, Yin, Hong, Haiwen, Zhang, Jingfeng, Yan, Feihu, He, Yuan, Xue, Hui
Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of Transformer with long-range dep
Externí odkaz:
http://arxiv.org/abs/2204.10731
Publikováno v:
In Green Energy and Intelligent Transportation December 2024 3(6)
Publikováno v:
In International Journal of Refrigeration August 2024 164:143-153
Autor:
Cui, Jilai, Wu, Bin, Wang, Jingming, Jing, Ting, Jin, Jieyang, Zhao, Mingyue, Hu, Yunqing, Wu, Yi, Yu, Feng, Zhang, Na, Luo, Zhengwei, Wang, Qiang, Jiang, Hao, Schwab, Wilfried G., Song, Chuankui
Publikováno v:
In LWT 1 July 2024 203
In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of
Externí odkaz:
http://arxiv.org/abs/2107.09909
In fine-grained image recognition (FGIR), the localization and amplification of region attention is an important factor, which has been explored a lot by convolutional neural networks (CNNs) based approaches. The recently developed vision transformer
Externí odkaz:
http://arxiv.org/abs/2107.08192
Publikováno v:
Zhongguo youzhi, Vol 48, Iss 12, Pp 142-146 (2023)
旨在为鲜核桃保鲜贮藏提供理论依据,以‘温185’为测试品种,经脱青皮后在-10 ℃下低温冷冻贮藏180 d,分析其在贮藏期间的品质变化。结果表明:在贮藏期内,‘温185’脱青皮鲜核桃坚果
Externí odkaz:
https://doaj.org/article/2176e9e71f4244618e1c0005d4dad20b