Home /

Research

Showing 241 - 246 / 897

Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning


Authors:  HaoyiFan, FengbinZhang, YueGao....
Published date-11/27/2020
Tasks:  RelationalReasoning, RepresentationLearning, Self-SupervisedLearning, TimeSeries, TimeSeriesClassification

Abstract: Self-supervised learning achieves superior performance in many domains by extracting useful representations from the unlabeled data. However, most of traditional self-supervised methods mainly focus on exploring the inter-sample structure while …

Efficient Information Diffusion in Time-Varying Graphs through Deep Reinforcement Learning


Authors:  MatheusR.F.Mendonça, AndréM.S.Barreto, ArturZiviani....
Published date-11/27/2020
Tasks:  GraphEmbedding

Abstract: Network seeding for efficient information diffusion over time-varying graphs~(TVGs) is a challenging task with many real-world applications. There are several ways to model this spatio-temporal influence maximization problem, but the …

Navigating the GAN Parameter Space for Semantic Image Editing


Authors:  AntonCherepkov, AndreyVoynov, ArtemBabenko....
Published date-11/27/2020
Tasks:  ImageRestoration, Image-to-ImageTranslation

Abstract: Generative Adversarial Networks (GANs) are currently an indispensable tool for visual editing, being a standard component of image-to-image translation and image restoration pipelines. Furthermore, GANs are especially useful for controllable …

Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification


Authors:  HaoChen, BenoitLagadec, FrancoisBremond....
Published date-11/27/2020
Tasks:  DomainAdaptation, PersonRe-Identification, UnsupervisedDomainAdaptation, UnsupervisedPersonRe-Identification

Abstract: The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without labor-intensive identity annotations. State-of-the-art unsupervised Re-ID methods assign pseudo labels to unlabeled images in the target domain …

Efficient Scene Compression for Visual-based Localization


Authors:  MarcelaMera-Trujillo, BenjaminSmith, VictorFragoso....
Published date-11/27/2020
Tasks:  3DReconstruction

Abstract: Estimating the pose of a camera with respect to a 3D reconstruction or scene representation is a crucial step for many mixed reality and robotics applications. Given the vast amount …

Generalized Pose-and-Scale Estimation using 4-Point Congruence Constraints


Authors:  VictorFragoso, SudiptaSinha....
Published date-11/27/2020

Abstract: We present gP4Pc, a new method for computing the absolute pose of a generalized camera with unknown internal scale from four corresponding 3D point-and-ray pairs. Unlike most pose-and-scale methods, gP4Pc …

Filter by

Categories

Tags