Spinal-Tap
发表于 2025-3-28 17:16:22
Long-Tailed Time Series Classification via Feature Space Rebalancingced Contrastive Learning (BCL), which avoids excessive intra-class compaction of tail classes by introducing a balanced supervised contrastive loss with hierarchical prototypes, resulting in a balanced feature space and better generalization. From the data perspective, we explore the effectiveness o
relieve
发表于 2025-3-28 22:37:27
http://reply.papertrans.cn/27/2635/263403/263403_42.png
paltry
发表于 2025-3-29 01:09:09
http://reply.papertrans.cn/27/2635/263403/263403_43.png
Intruder
发表于 2025-3-29 05:30:20
http://reply.papertrans.cn/27/2635/263403/263403_44.png
Minikin
发表于 2025-3-29 10:39:39
GP-HLS: Gaussian Process-Based Unsupervised High-Level Semantics Representation Learning of Multivare series. Moreover, to deal with the challenge of variable lengths of input subseries of multivariate time series, a temporal pyramid pooling (TPP) method is applied to construct input vectors with equal length. The experimental results show that our model has substantial advantages compared with ot
Ancillary
发表于 2025-3-29 12:44:17
Towards Time-Series Key Points Detection Through Self-supervised Learning and Probability Compensatiith a higher generalization ability; 2) a joint loss function providing both dynamic focal adaptation and probability compensation by extreme value theory. Extensive experiments using both real-world and benchmark datasets are conducted. The results indicate that our method outperforms our rival met
驳船
发表于 2025-3-29 17:36:39
SNN-AAD: Active Anomaly Detection Method for Multivariate Time Series with Sparse Neural Networkctive anomaly detection with the design of sample selection strategy and abnormal feature order generation algorithm, which extracts the important features of instances and reduce the cost of human intelligence. Experimental results on four real-life datasets show SNN-AAD has good detection performa
粘
发表于 2025-3-29 23:26:32
http://reply.papertrans.cn/27/2635/263403/263403_48.png
裂口
发表于 2025-3-30 03:58:45
0302-9743 D consortium papers are included. The conference presents papers on subjects such as model, graph, learning, performance, knowledge, time, recommendation, representation, attention, prediction, and network..978-3-031-30636-5978-3-031-30637-2Series ISSN 0302-9743 Series E-ISSN 1611-3349
–LOUS
发表于 2025-3-30 06:43:41
http://reply.papertrans.cn/27/2635/263403/263403_50.png