Zobrazeno 1 - 10
of 228
pro vyhledávání: '"Zhang, Yanyi"'
Most incremental learners excessively prioritize coarse classes of objects while neglecting various kinds of states (e.g. color and material) attached to the objects. As a result, they are limited in the ability to reason fine-grained compositionalit
Externí odkaz:
http://arxiv.org/abs/2411.01739
Using Large Language Models for Humanitarian Frontline Negotiation: Opportunities and Considerations
Autor:
Ma, Zilin, Susannah, Su, Zhao, Nathan, Bieske, Linn, Bullwinkel, Blake, Zhang, Yanyi, Sophia, Yang, Luo, Ziqing, Li, Siyao, Liao, Gekai, Wang, Boxiang, Gao, Jinglun, Wen, Zihan, Bruderlein, Claude, Pan, Weiwei
Humanitarian negotiations in conflict zones, called \emph{frontline negotiation}, are often highly adversarial, complex, and high-risk. Several best-practices have emerged over the years that help negotiators extract insights from large datasets to n
Externí odkaz:
http://arxiv.org/abs/2405.20195
Attribute and object (A-O) disentanglement is a fundamental and critical problem for Compositional Zero-shot Learning (CZSL), whose aim is to recognize novel A-O compositions based on foregone knowledge. Existing methods based on disentangled represe
Externí odkaz:
http://arxiv.org/abs/2403.05924
Autor:
Zhang, Yanyi, De Smedt, Johannes
Publikováno v:
In International Review of Financial Analysis October 2024 95 Part C
Publikováno v:
In Engineering Structures 15 January 2025 323 Part A
Publikováno v:
In Computer Vision and Image Understanding December 2024 249
Autor:
Yang, Zirong, Wang, Ruidi, Hao, Dong, Wu, Kangcheng, Liang, Jinqiao, Wu, Siyuan, Ma, Minghui, Du, Qing, Zhang, Yanyi
Publikováno v:
In International Journal of Hydrogen Energy 28 August 2024 80:125-136
Publikováno v:
In Measurement 15 August 2024 236
Publikováno v:
Energy Reports, Vol 10, Iss , Pp 1943-1950 (2023)
With the rapid development of fuel cell vehicle, the testing capabilities of fuel cell vehicle and its key components are gradually improved. Therefore, the testing and evaluation technology of proton exchange membrane for fuel cell is focused on. In
Externí odkaz:
https://doaj.org/article/0d6b310668544a4fab337e2d428b233e
Autor:
Zhang, Yanyi, Li, Xinyu, Liu, Chunhui, Shuai, Bing, Zhu, Yi, Brattoli, Biagio, Chen, Hao, Marsic, Ivan, Tighe, Joseph
We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with high
Externí odkaz:
http://arxiv.org/abs/2104.11746