Related papers: A method to align time series segments based on en…
Capturing and annotating Sign language datasets is a time consuming and costly process. Current datasets are orders of magnitude too small to successfully train unconstrained \acf{slt} models. As a result, research has turned to TV…
Anomalies (unusual patterns) in time-series data give essential, and often actionable information in critical situations. Examples can be found in such fields as healthcare, intrusion detection, finance, security and flight safety. In this…
Various alignment problems arising in cryo-electron microscopy, community detection, time synchronization, computer vision, and other fields fall into a common framework of synchronization problems over compact groups such as Z/L, U(1), or…
Irregularly sampled time series are increasingly prevalent, particularly in medical domains. While various specialized methods have been developed to handle these irregularities, effectively modeling their complex dynamics and pronounced…
Convolutional neural networks (CNN) have demonstrated their ability to segment 2D cardiac ultrasound images. However, despite recent successes according to which the intra-observer variability on end-diastole and end-systole images has been…
Detecting anomalies in time series data is a challenging task with broad relevance in many applications. Existing methods work effectively only under idealized conditions, typically focusing on point anomalies or assuming a constant…
Ordinal time series analysis is based on the idea to map time series to ordinal patterns, i.e., order relations between the values of a time series and not the values themselves, as introduced in 2002 by C. Bandt and B. Pompe. Despite a…
Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing contrastive…
Singular spectrum analysis (SSA), starting from the second half of the XX century, has been a rapidly developing method of time series analysis. Since it can be called principal component analysis for time series, SSA will definitely be a…
We propose a novel approach for change-point detection and parameter learning in multivariate non-stationary time series exhibiting oscillatory behaviour. We approximate the process through a piecewise function defined by a sum of…
Machine learning for data-driven diagnosis has been actively studied in medicine to provide better healthcare. Supporting analysis of a patient cohort similar to a patient under treatment is a key task for clinicians to make decisions with…
We study time-uniform statistical inference for parameters in stochastic approximation (SA), which encompasses a bunch of applications in optimization and machine learning. To that end, we analyze the almost-sure convergence rates of the…
Shapelets are discriminative time series subsequences that allow generation of interpretable classification models, which provide faster and generally better classification than the nearest neighbor approach. However, the shapelet discovery…
Temporal correspondence - linking pixels or objects across frames - is a fundamental supervisory signal for the video models. For the panoptic understanding of dynamic scenes, we further extend this concept to every segment. Specifically,…
Asynchronous Time Series is a multivariate time series where all the channels are observed asynchronously-independently, making the time series extremely sparse when aligning them. We often observe this effect in applications with complex…
We study the use of a time series encoder to learn representations that are useful on data set types with which it has not been trained on. The encoder is formed of a convolutional neural network whose temporal output is summarized by a…
Irregularly-sampled time series (ITS) are native to high-impact domains like healthcare, where measurements are collected over time at uneven intervals. However, for many classification problems, only small portions of long time series are…
Music genre classification is a critical component of music recommendation systems, generation algorithms, and cultural analytics. In this work, we present an innovative model for classifying music genres using attention-based temporal…
Dynamic time warping (DTW) can be used to compute the similarity between two sequences of generally differing length. We propose a modification to DTW that performs individual and independent pairwise alignment of feature trajectories. The…
Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…