Related papers: Spatial-Temporal Cross-View Contrastive Pre-traini…

Predicting diverse human motions given a sequence of historical poses has received increasing attention. Despite rapid progress, existing work captures the multi-modal nature of human motions primarily through likelihood-based sampling,…

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Medical vision-language pre-training methods mainly leverage the correspondence between paired medical images and radiological reports. Although multi-view spatial images and temporal sequences of image-report pairs are available in…

Representing the movements of objects (trips) over a network in a compact way while retaining the capability of exploiting such data effectively is an important challenge of real applications. We present a new Compact Trip Representation…

Given an object of interest, visual navigation aims to reach the object's location based on a sequence of partial observations. To this end, an agent needs to 1) learn a piece of certain knowledge about the relations of object categories in…

Although dynamic scene reconstruction has long been a fundamental challenge in 3D vision, the recent emergence of 3D Gaussian Splatting (3DGS) offers a promising direction by enabling high-quality, real-time rendering through explicit…

Contrastive language-audio pretraining, which aims to unify multimodal representations in a shared embedding space, serves as a cornerstone for building a wide range of applications, from cross-modal retrieval to cutting-edge multimodal…

Learning representations of stochastic processes is an emerging problem in machine learning with applications from meta-learning to physical object models to time series. Typical methods rely on exact reconstruction of observations, but…

In this paper we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR). While most SBIR approaches focus on extracting low- and mid-level descriptors for direct feature matching, recent…

Point cloud videos capture dynamic 3D motion while reducing the effects of lighting and viewpoint variations, making them highly effective for recognizing subtle and continuous human actions. Although Selective State Space Models (SSMs)…

Click-Through Rate (CTR) prediction, a core task in recommendation systems, estimates user click likelihood using historical behavioral data. Modeling user behavior sequences as text to leverage Language Models (LMs) for this task has…

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips…

Sequential recommender systems (SRS) could capture dynamic user preferences by modeling historical behaviors ordered in time. Despite effectiveness, focusing only on the \textit{collaborative signals} from behaviors does not fully grasp…

Human Motion Segmentation (HMS), which aims to partition videos into non-overlapping human motions, has attracted increasing research attention recently. Existing approaches for HMS are mainly dominated by subspace clustering methods, which…

Vast quantities of person-generated health data (wearables) are collected but the process of annotating to feed to machine learning models is impractical. This paper discusses ways in which self-supervised approaches that use contrastive…

Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. It has recently emerged as one of the leading learning paradigms in the absence of labels…

Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled…

In this paper, we propose a hierarchical contrastive learning framework, HiCL, which considers local segment-level and global sequence-level relationships to improve training efficiency and effectiveness. Traditional methods typically…

Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved. For example, most of the previous methods model the representations of skeleton sequences without abundant spatial structure…

Adapting machine learning models to medical time series across different domains remains a challenge due to complex temporal dependencies and dynamic distribution shifts. Current approaches often focus on isolated feature representations,…