Zobrazeno 1 - 10
of 976
pro vyhledávání: '"Zhang, Yunhua"'
Low-resource settings are well-established in natural language processing, where many languages lack sufficient data for deep learning at scale. However, low-resource problems are under-explored in computer vision. In this paper, we address this gap
Externí odkaz:
http://arxiv.org/abs/2401.04716
Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive for general
Externí odkaz:
http://arxiv.org/abs/2306.12795
This paper strives to recognize activities in the dark, as well as in the day. We first establish that state-of-the-art activity recognizers are effective during the day, but not trustworthy in the dark. The main causes are the limited availability o
Externí odkaz:
http://arxiv.org/abs/2212.02053
Autor:
Zhang, Yunhua1,2,3 (AUTHOR), Mao, Kaikai4 (AUTHOR), Chen, Keyi1,2,5 (AUTHOR), Zhao, Ze1,2,5 (AUTHOR), Ju, Feng1,2,3,5 (AUTHOR) jufeng@westlake.edu.cn
Publikováno v:
Communications Biology. 9/27/2024, Vol. 7 Issue 1, p1-12. 12p.
Existing RGB-D SOD methods mainly rely on a symmetric two-stream CNN-based network to extract RGB and depth channel features separately. However, there are two problems with the symmetric conventional network structure: first, the ability of CNN in l
Externí odkaz:
http://arxiv.org/abs/2207.01172
This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint. The leading approaches reduce the shift in activity appearance by adversarial training and self-supervised learning. Differen
Externí odkaz:
http://arxiv.org/abs/2203.14240
Publikováno v:
In Science of the Total Environment 20 October 2024 948
Publikováno v:
In Journal of Environmental Chemical Engineering October 2024 12(5)
Autor:
Jiang, Jingjiao, Yang, Kun, Gong, Honghong, Ma, Jing, Hu, Xiaopeng, Zhou, Yuanhua, Zhang, Yunhua, Sun, Weiqing
Publikováno v:
In International Journal of Biological Macromolecules October 2024 277 Part 1