Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Zhang Juan"'
Self-attention-based networks have achieved remarkable performance in sequential recommendation tasks. A crucial component of these models is positional encoding. In this study, we delve into the learned positional embedding, demonstrating that it of
Externí odkaz:
http://arxiv.org/abs/2407.02793
CDR (Cross-Domain Recommendation), i.e., leveraging information from multiple domains, is a critical solution to data sparsity problem in recommendation system. The majority of previous research either focused on single-target CDR (STCDR) by utilizin
Externí odkaz:
http://arxiv.org/abs/2407.00909
In this work, we investigate [110] symmetric tilt FCC grain boundaries (GBs) by a recently developed approach for quasiperiodic interfaces using the Landau-Brazovskii model. On special tilt angles associated with quadratic algebraic numbers, quasiper
Externí odkaz:
http://arxiv.org/abs/2406.03023
Autor:
Yang, Yuguang, Guo, Runtang, Wu, Sheng, Wang, Yimi, Yang, Linlin, Fan, Bo, Zhong, Jilong, Zhang, Juan, Zhang, Baochang
Interpreting complex deep networks, notably pre-trained vision-language models (VLMs), is a formidable challenge. Current Class Activation Map (CAM) methods highlight regions revealing the model's decision-making basis but lack clear saliency maps an
Externí odkaz:
http://arxiv.org/abs/2405.18882
Autor:
Zhang, Juan, Xun, Wenlu
We have introduced the generalized alternating direction implicit iteration (GADI) method for solving large sparse complex symmetric linear systems and proved its convergence properties. Additionally, some numerical results have demonstrated the effe
Externí odkaz:
http://arxiv.org/abs/2404.12160
Autor:
Zhang, Juan, Xun, Wenlu
This paper proposes an effective low-rank alternating direction doubling algorithm (R-ADDA) for computing numerical low-rank solutions to large-scale sparse continuous-time algebraic Riccati matrix equations. The method is based on the alternating di
Externí odkaz:
http://arxiv.org/abs/2404.12155
Autor:
Dong, Wenhao, Zhu, Haodong, Lin, Shaohui, Luo, Xiaoyan, Shen, Yunhang, Liu, Xuhui, Zhang, Juan, Guo, Guodong, Zhang, Baochang
Cross-modality fusing complementary information from different modalities effectively improves object detection performance, making it more useful and robust for a wider range of applications. Existing fusion strategies combine different types of ima
Externí odkaz:
http://arxiv.org/abs/2404.09146
In this study, our main objective is to address the challenge of solving elliptic equations with quasiperiodic coefficients. To achieve accurate and efficient computation, we introduce the projection method, which enables the embedding of quasiperiod
Externí odkaz:
http://arxiv.org/abs/2404.06841
Autor:
Zhang, Juan, Luo, Yiyi
This paper introduces a preconditioned method designed to comprehensively address the saddle point system with the aim of improving convergence efficiency. In the preprocessor construction phase, a technical approach for solving the approximate inver
Externí odkaz:
http://arxiv.org/abs/2404.06061
Autor:
Zhang, Juan, Xun, Wenlu
This paper presents an effective low-rank generalized alternating direction implicit iteration (R-GADI) method for solving large-scale sparse and stable Lyapunov matrix equations and continuous-time algebraic Riccati matrix equations. The method is b
Externí odkaz:
http://arxiv.org/abs/2404.06034