Related papers: Time Series Representation Learning with Supervise…

Bootstrap-based Self-Supervised Learning (SSL) has achieved remarkable progress in audio understanding. However, existing methods typically operate at a single level of granularity, limiting their ability to model the diverse temporal and…

Recently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segmentation (HMS). These approaches leverage prior knowledge from…

Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment. While significant progress has been achieved with expensive LiDAR point clouds, it poses a great challenge for…

While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose…

There has been a recent surge of interest in time series modeling using the Transformer architecture. However, forecasting multivariate time series with Transformer presents a unique challenge as it requires modeling both temporal…

The analysis of physiological processes over time are often given by spectrometric or gene expression profiles over time with only few time points but a large number of measured variables. The analysis of such temporal sequences is…

This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial…

We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a…

Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online interactions. However, real-world data collected from sensors or…

Unsupervised sentence representation learning aims to transform input sentences into fixed-length vectors enriched with intricate semantic information while obviating the reliance on labeled data. Recent strides within this domain have been…

We are interested in representation learning from labeled or unlabeled data. Inspired by recent success of self-supervised learning (SSL), we develop a non-contrastive representation learning method that can exploit additional knowledge.…

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…

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…

Place recognition is an important component for autonomous vehicles to achieve loop closing or global localization. In this paper, we tackle the problem of place recognition based on sequential 3D LiDAR scans obtained by an onboard LiDAR…

Detailed mobile sensing data from phones, watches, and fitness trackers offer an unparalleled opportunity to quantify and act upon previously unmeasurable behavioral changes in order to improve individual health and accelerate responses to…

Recently, there have been efforts to improve the performance in sign language recognition by designing self-supervised learning methods. However, these methods capture limited information from sign pose data in a frame-wise learning manner,…

Time series anomaly detection is a critical task across various industrial domains. However, capturing temporal dependencies and multivariate correlations within patch-level representation learning remains underexplored, and reliance on…

Multi-object tracking (MOT) is critical in numerous real-world applications, including surveillance, autonomous driving, and robotics. Accurately predicting object motion is fundamental to MOT, but current methods struggle with the…

Change-point detection (CPD) in high-dimensional, large-volume time series is challenging for statistical consistency, scalability, and interpretability. We introduce TimePred, a self-supervised framework that reduces multivariate CPD to…

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…