Related papers: Multi-Faceted Representation Learning with Hybrid …

Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn…

Satellite image time series, bolstered by their growing availability, are at the forefront of an extensive effort towards automated Earth monitoring by international institutions. In particular, large-scale control of agricultural parcels…

The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very…

In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition. Specifically, we design a new model called Deep Reconstruction-Classification Network (DRCN), which jointly…

We introduce a temporal feature encoding architecture called Time Series Representation Model (TSRM) for multivariate time series forecasting and imputation. The architecture is structured around CNN-based representation layers, each…

We present a novel architecture, residual attention net (RAN), which merges a sequence architecture, universal transformer, and a computer vision architecture, residual net, with a high-way architecture for cross-domain sequence modeling.…

Change detection is one of the central problems in earth observation and was extensively investigated over recent decades. In this paper, we propose a novel recurrent convolutional neural network (ReCNN) architecture, which is trained to…

Many methods aim to enhance time series forecasting by decomposing the series through intricate model structures and prior knowledge, yet they are inevitably limited by computational complexity and the robustness of the assumptions. Our…

Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly…

Quantum machine learning models for sequential data face scalability challenges with complex multivariate signals. We introduce the Hybrid Quantum Temporal Convolutional Network (HQTCN), which combines classical temporal windowing with a…

The time-series forecasting (TSF) problem is a traditional problem in the field of artificial intelligence. Models such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and GRU (Gate Recurrent Units) have contributed to…

Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification…

As industrial systems become more complex and monitoring sensors for everything from surveillance to our health become more ubiquitous, multivariate time series prediction is taking an important place in the smooth-running of our society. A…

Self-supervised representation learning of Multivariate Time Series (MTS) is a challenging task and attracts increasing research interests in recent years. Many previous works focus on the pretext task of self-supervised learning and…

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of…

In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target.…

Deep learning has made significant advances in creating efficient representations of time series data by automatically identifying complex patterns. However, these approaches lack interpretability, as the time series is transformed into a…

Time series analysis remains a major challenge due to its sparse characteristics, high dimensionality, and inconsistent data quality. Recent advancements in transformer-based techniques have enhanced capabilities in forecasting and…

Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous…

Recent studies have shown great promise in unsupervised representation learning (URL) for multivariate time series, because URL has the capability in learning generalizable representation for many downstream tasks without using inaccessible…