Related papers: Universal hidden monotonic trend estimation with c…
Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…
Cross-modal contrastive learning has led the recent advances in multimodal retrieval with its simplicity and effectiveness. In this work, however, we reveal that cross-modal contrastive learning suffers from incorrect normalization of the…
Temporal anomaly detection looks for irregularities over space-time. Unsupervised temporal models employed thus far typically work on sequences of feature vectors, and much less on temporal multiway data. We focus our investigation on…
Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…
The present study proposes a novel method of trend detection and visualization - more specifically, modeling the change in a topic over time. Where current models used for the identification and visualization of trends only convey the…
This paper introduces new methodology based on the field of Topological Data Analysis for detecting anomalies in multivariate time series, that aims to detect global changes in the dependency structure between channels. The proposed…
We introduce CULT (Continual Unsupervised Representation Learning with Typicality-Based Environment Detection), a new algorithm for continual unsupervised learning with variational auto-encoders. CULT uses a simple typicality metric in the…
We develop new econometric methods for the comparison of nonparametric time trends. In many applications, practitioners are interested in whether the observed time series all have the same time trend. Moreover, they would often like to know…
Contrast pattern mining (CPM) aims to discover patterns whose support increases significantly from a background dataset compared to a target dataset. CPM is particularly useful for characterising changes in evolving systems, e.g., in…
Non-parametric approaches to test for trends in time series make use of the Mann-Kendall statistic. Based on asymptotic arguments, these tests assume that its distribution follows a Gaussian distribution, even for autocorrelated time…
Scientists aim to extract simplicity from observations of the complex world. An important component of this process is the exploration of data in search of trends. In practice, however, this tends to be more of an art than a science. Among…
Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be…
Bartholomew's trend test belongs to the broad class of isotonic regression models, specifically with a single qualitative factor, e.g. dose levels. Using the approximation of the ANOVA F-test by the maximum contrast test against grand mean…
Information on natural phenomena and engineering systems is typically contained in data. Data can be corrupted by systematic errors in models and experiments. In this paper, we propose a tool to uncover the spatiotemporal solution of the…
Given only data generated by a standard confounding graph with unobserved confounder, the Average Treatment Effect (ATE) is not identifiable. To estimate the ATE, a practitioner must then either (a) collect deconfounded data;(b) run a…
Contrastive pre-training on distant supervision has shown remarkable effectiveness in improving supervised relation extraction tasks. However, the existing methods ignore the intrinsic noise of distant supervision during the pre-training…
In this paper, we introduce a new adaptive data analysis method to study trend and instantaneous frequency of nonlinear and non-stationary data. This method is inspired by the Empirical Mode Decomposition method (EMD) and the recently…
Understanding the dynamics of time series data typically requires identifying the unique latent factors for data generation, \textit{a.k.a.}, latent processes identification. Driven by the independent assumption, existing works have made…
Time series anomaly detection plays a critical role in automated monitoring systems. Most previous deep learning efforts related to time series anomaly detection were based on recurrent neural networks (RNN). In this paper, we propose a…
The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It…