Zobrazeno 1 - 10
of 27 336
pro vyhledávání: '"SUN, LI"'
Autor:
Yu, Xiaoyan, Wei, Yifan, Zhou, Shuaishuai, Yang, Zhiwei, Sun, Li, Peng, Hao, Zhu, Liehuang, Yu, Philip S.
The vast, complex, and dynamic nature of social message data has posed challenges to social event detection (SED). Despite considerable effort, these challenges persist, often resulting in inadequately expressive message representations (ineffective)
Externí odkaz:
http://arxiv.org/abs/2412.10712
Probabilistic embeddings have several advantages over deterministic embeddings as they map each data point to a distribution, which better describes the uncertainty and complexity of data. Many works focus on adjusting the distribution constraint und
Externí odkaz:
http://arxiv.org/abs/2412.08841
This paper shows how an uncertainty-aware, deep neural network can be trained to detect, recognise and localise objects in 2D RGB images, in applications lacking annotated train-ng datasets. We propose a self-supervising teacher-student pipeline, in
Externí odkaz:
http://arxiv.org/abs/2411.03082
Graph neural networks (GNNs) have become the dominant solution for learning on graphs, the typical non-Euclidean structures. Conventional GNNs, constructed with the Artificial Neuron Network (ANN), have achieved impressive performance at the cost of
Externí odkaz:
http://arxiv.org/abs/2410.17941
This paper addresses the open problem of conducting change-point analysis for interval-valued time series data using the maximum likelihood estimation (MLE) framework. Motivated by financial time series, we analyze data that includes daily opening (O
Externí odkaz:
http://arxiv.org/abs/2410.09884
In StyleGAN, convolution kernels are shaped by both static parameters shared across images and dynamic modulation factors $w^+\in\mathcal{W}^+$ specific to each image. Therefore, $\mathcal{W}^+$ space is often used for image inversion and editing. Ho
Externí odkaz:
http://arxiv.org/abs/2410.06104
Autor:
Yu, Xiaoyan, Wei, Yifan, Li, Pu, Zhou, Shuaishuai, Peng, Hao, Sun, Li, Zhu, Liehuang, Yu, Philip S.
Training social event detection models through federated learning (FedSED) aims to improve participants' performance on the task. However, existing federated learning paradigms are inadequate for achieving FedSED's objective and exhibit limitations i
Externí odkaz:
http://arxiv.org/abs/2409.00614
Unsupervised anomaly detection in time series is essential in industrial applications, as it significantly reduces the need for manual intervention. Multivariate time series pose a complex challenge due to their feature and temporal dimensions. Tradi
Externí odkaz:
http://arxiv.org/abs/2408.13082
Autor:
Duan, Jiarui, Li, Haoling, Zhang, Haofei, Jiang, Hao, Xue, Mengqi, Sun, Li, Song, Mingli, Song, Jie
Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). However, the absence of consistent configurations and systematic invest
Externí odkaz:
http://arxiv.org/abs/2407.19471
Autor:
Peng, Kun, Jiang, Lei, Li, Qian, Li, Haoran, Yu, Xiaoyan, Sun, Li, Sun, Shuo, Bi, Yanxian, Peng, Hao
Cross-domain Aspect Sentiment Triplet Extraction (ASTE) aims to extract fine-grained sentiment elements from target domain sentences by leveraging the knowledge acquired from the source domain. Due to the absence of labeled data in the target domain,
Externí odkaz:
http://arxiv.org/abs/2407.21052