Home /

Research

Showing 37 - 42 / 897

PlueckerNet: Learn to Register 3D Line Reconstructions


Authors:  LiuLiu, HongdongLi, HaodongYao....
Published date-12/02/2020

Abstract: Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve correspondences and relative pose between line reconstructions. This paper proposes a neural network …

Top-1 CORSMAL Challenge 2020 Submission: Filling Mass Estimation Using Multi-modal Observations of Human-robot Handovers


Authors:  VladimirIashin, FrancescaPalermo, GökhanSolak....
Published date-12/02/2020

Abstract: Human-robot object handover is a key skill for the future of human-robot collaboration. CORSMAL 2020 Challenge focuses on the perception part of this problem: the robot needs to estimate the …

PatchmatchNet: Learned Multi-View Patchmatch Stereo


Authors:  FangjinhuaWang, SilvanoGalliani, ChristophVogel....
Published date-12/02/2020

Abstract: We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for high-resolution multi-view stereo. With high computation speed and low memory requirement, PatchmatchNet can process higher resolution imagery and …

Partially Shared Semi-supervised Deep Matrix Factorization with Multi-view Data


Authors:  HaonanHuang, NaiyaoLiang, WeiYan....
Published date-12/02/2020
Tasks:  MULTI-VIEWLEARNING

Abstract: Since many real-world data can be described from multiple views, multi-view learning has attracted considerable attention. Various methods have been proposed and successfully applied to multi-view learning, typically based on …

Policy Supervectors: General Characterization of Agents by their Behaviour


Authors:  AnssiKanervisto, TomiKinnunen, VilleHautamäki....
Published date-12/02/2020
Tasks:  DecisionMaking, ImitationLearning

Abstract: By studying the underlying policies of decision-making agents, we can learn about their shortcomings and potentially improve them. Traditionally, this has been done either by examining the agent's implementation, its …

Algebraically-Informed Deep Networks (AIDN): A Deep Learning Approach to Represent Algebraic Structures


Authors:  MustafaHajij, GhadaZamzmi, MatthewDawson....
Published date-12/02/2020

Abstract: One of the central problems in the interface of deep learning and mathematics is that of building learning systems that can automatically uncover underlying mathematical laws from observed data. In …

Filter by

Categories

Tags