Zobrazeno 1 - 10
of 17 354
pro vyhledávání: '"feng, Yan"'
Autor:
Wang, Jinpeng, Lian, Niu, Li, Jun, Wang, Yuting, Feng, Yan, Chen, Bin, Zhang, Yongbing, Xia, Shu-Tao
Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capabilities, they often suffer from computational and memory inefficiencie
Externí odkaz:
http://arxiv.org/abs/2412.14518
Bidirectional privacy-preservation federated learning is crucial as both local gradients and the global model may leak privacy. However, only a few works attempt to achieve it, and they often face challenges such as excessive communication and comput
Externí odkaz:
http://arxiv.org/abs/2412.11737
Langevin dynamical simulations are performed to investigate the formation of clusters and voids of a two-dimensional-periodic-substrate (2DPS) modulated two-dimensional dusty plasma (2DDP) driven by an oscillatory force. It is discovered that, as the
Externí odkaz:
http://arxiv.org/abs/2411.17647
Autor:
Yang, Weiqin, Chen, Jiawei, Xin, Xin, Zhou, Sheng, Hu, Binbin, Feng, Yan, Chen, Chun, Wang, Can
Softmax Loss (SL) is widely applied in recommender systems (RS) and has demonstrated effectiveness. This work analyzes SL from a pairwise perspective, revealing two significant limitations: 1) the relationship between SL and conventional ranking metr
Externí odkaz:
http://arxiv.org/abs/2411.00163
Predicting pedestrian behavior is challenging yet crucial for applications such as autonomous driving and smart city. Recent deep learning models have achieved remarkable performance in making accurate predictions, but they fail to provide explanatio
Externí odkaz:
http://arxiv.org/abs/2410.12195
Autor:
Wang, Zhe, Zhao, Tianjian, Zhang, Zhen, Chen, Jiawei, Zhou, Sheng, Feng, Yan, Chen, Chun, Wang, Can
Dynamic Graph Neural Networks (DyGNNs) have garnered increasing research attention for learning representations on evolving graphs. Despite their effectiveness, the limited expressive power of existing DyGNNs hinders them from capturing important evo
Externí odkaz:
http://arxiv.org/abs/2410.01367
Let $\Gamma$ be a connected $7$-valent symmetric Cayley graph on a finite non-abelian simple group $G$. If $\Gamma$ is not normal, Li {\em et al.} [On 7-valent symmetric Cayley graphs of finite simple groups, J. Algebraic Combin. 56 (2022) 1097-1118]
Externí odkaz:
http://arxiv.org/abs/2409.19225
Extending the well-studied concept of graphical regular representations to bipartite graphs, a Haar graphical representation (HGR) of a group $G$ is a bipartite graph whose automorphism group is isomorphic to $G$ and acts semiregularly with the orbit
Externí odkaz:
http://arxiv.org/abs/2409.18716
Pedestrian action prediction is of great significance for many applications such as autonomous driving. However, state-of-the-art methods lack explainability to make trustworthy predictions. In this paper, a novel framework called MulCPred is propose
Externí odkaz:
http://arxiv.org/abs/2409.09446
Autor:
Wang, Bohao, Liu, Feng, Zhang, Changwang, Chen, Jiawei, Wu, Yudi, Zhou, Sheng, Lou, Xingyu, Wang, Jun, Feng, Yan, Chen, Chun, Wang, Can
Sequential Recommenders generate recommendations based on users' historical interaction sequences. However, in practice, these collected sequences are often contaminated by noisy interactions, which significantly impairs recommendation performance. A
Externí odkaz:
http://arxiv.org/abs/2408.08208