Zobrazeno 1 - 10
of 274
pro vyhledávání: '"Nie, Xiushan"'
Federated domain generalization (FedDG) aims to improve the global model generalization in unseen domains by addressing data heterogeneity under privacy-preserving constraints. A common strategy in existing FedDG studies involves sharing domain-speci
Externí odkaz:
http://arxiv.org/abs/2411.10063
Meta-learning methods typically follow a two-loop framework, where each loop potentially suffers from notorious overfitting, hindering rapid adaptation and generalization to new tasks. Existing schemes solve it by enhancing the mutual-exclusivity or
Externí odkaz:
http://arxiv.org/abs/2306.08460
Autor:
Wang, Ruifeng, Zhang, Guang, Xi, Xiaoming, Xu, Longsheng, Nie, Xiushan, Nie, Jianhua, Meng, Xianjing, Zhang, Yanwei, Chen, Xinjian, Yin, Yilong
Publikováno v:
In Pattern Recognition December 2024 156
Publikováno v:
In Pattern Recognition November 2024 155
Non-linear activation functions, e.g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs). Due to the complex non-linear characteristic of samples, the objective of those activation functions is to project samples from thei
Externí odkaz:
http://arxiv.org/abs/2203.11700
Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos. While a great progress has been observed, most of the existing SPS approac
Externí odkaz:
http://arxiv.org/abs/2203.09736
Predicting the future price trends of stocks is a challenging yet intriguing problem given its critical role to help investors make profitable decisions. In this paper, we present a collaborative temporal-relational modeling framework for end-to-end
Externí odkaz:
http://arxiv.org/abs/2107.14033
Publikováno v:
In Knowledge-Based Systems 7 June 2024 293
Publikováno v:
In Image and Vision Computing April 2024 144
Natural language video localization (NLVL), which aims to locate a target moment from a video that semantically corresponds to a text query, is a novel and challenging task. Toward this end, in this paper, we present a comprehensive survey of the NLV
Externí odkaz:
http://arxiv.org/abs/2104.00234