Related papers: SCINet: Time Series Modeling and Forecasting with …

We develop a framework to track the structure of temporal networks with a signal processing approach. The method is based on the duality between networks and signals using a multidimensional scaling technique. This enables a study of the…

Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to…

Cascaded architectures have brought significant performance improvement in object detection and instance segmentation. However, there are lingering issues regarding the disparity in the Intersection-over-Union (IoU) distribution of the…

A time series represents a set of observations collected over time. Typically, these observations are captured with a uniform sampling frequency (e.g. daily). When data points are observed in uneven time intervals the time series is…

Spiking neural networks (SNNs) can be used in low-power and embedded systems (such as emerging neuromorphic chips) due to their event-based nature. Also, they have the advantage of low computation cost in contrast to conventional artificial…

End-to-end learning models using raw waveforms as input have shown superior performances in many audio recognition tasks. However, most model architectures are based on convolutional neural networks (CNN) which were mainly developed for…

An important feature of all real-world networks is that the network structure changes over time. Due to this dynamic nature, it becomes difficult to propose suitable growth models that can explain the various important characteristic…

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise.…

In order to enhance the real-time performance of convolutional neural networks(CNNs), more and more researchers are focusing on improving the efficiency of CNN. Based on the analysis of some CNN architectures, such as ResNet, DenseNet,…

This paper aims to unify spatial dependency and temporal dependency in a non-Euclidean space while capturing the inner spatial-temporal dependencies for traffic data. For spatial-temporal attribute entities with topological structure, the…

Many real-world relational systems, such as social networks and biological systems, contain dynamic interactions. When learning dynamic graph representation, it is essential to employ sequential temporal information and geometric structure.…

Increasing amounts of data are available on temporal, or time-varying, networks. There have been various representations of temporal network data each of which has different advantages for downstream tasks such as mathematical analysis,…

In this paper, we present a new deep learning architecture for addressing the problem of supervised learning with sparse and irregularly sampled multivariate time series. The architecture is based on the use of a semi-parametric…

Objects at different spatial positions in an image exhibit different scales. Adaptive receptive fields are expected to capture suitable ranges of context for accurate pixel level semantic prediction. Recently, atrous convolution with…

Shapelet-based algorithms are widely used for time series classification because of their ease of interpretation, but they are currently outperformed by recent state-of-the-art approaches. We present a new formulation of time series…

Efficiency is an important issue in designing video architectures for action recognition. 3D CNNs have witnessed remarkable progress in action recognition from videos. However, compared with their 2D counterparts, 3D convolutions often…

Network representations can help reveal the behavior of complex systems. Useful information can be derived from the network properties and invariants, such as components, clusters or cliques, as well as from their changes over time. The…

Temporal networks are suitable for modeling complex evolving systems. It has a wide range of applications, such as social network analysis, recommender systems, and epidemiology. Recently, modeling such dynamic systems has drawn great…

Time series foundation models have recently gained a lot of attention due to their ability to model complex time series data encompassing different domains including traffic, energy, and weather. Although they exhibit strong average…

Systems are commonly monitored for health and security through collection and streaming of multivariate time series. Advances in time series forecasting due to adoption of multilayer recurrent neural network architectures make it possible…