Results 101 to 110 of about 48,305 (299)
A scalable dual approach to semidefinite metric learning
Distance metric learning plays an important role in many vision problems. Previous work of quadratic Maha-lanobis metric learning usually needs to solve a semidef- inite programming (SDP) problem.
Junae Kim +5 more
core +1 more source
We investigate the prospect of reconstructing the “cosmic distance ladder” of the Universe using a novel deep learning framework called LADDER —Learning Algorithm for Deep Distance Estimation and Reconstruction.
Rahul Shah +4 more
doaj +1 more source
Comparison of Triply Periodic Minimal Surface Energy Absorbers Under Uniaxial Compressive Loading
This study investigates LCD 3D printed Triply Periodic Minimal Surface (TPMS) structures as mechanical energy absorbers. By comparing various base designs and layered combinations under uniaxial compression, it identifies that a Diamond‐Gyroid sandwich structure offers superior performance.
Sergej Grednev +2 more
wiley +1 more source
A framework for reducing ink-bleed in old documents
10.1109/CVPR.2008.458782026th IEEE Conference on Computer Vision and Pattern Recognition ...
Xu, D. +8 more
core +1 more source
Fast sparse gaussian processes learning for man-made structure classification [PDF]
©2007 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any ...
Suter, D. +3 more
core +1 more source
Liquid‐phase transmission electron microscopy enables direct observation of nucleation and growth processes in solution. This review is dedicated to the remembrance of Helmut Cölfen and highlights recent studies on complex materials—oxides, biominerals, organic–inorganic crystals—which were central to his research activity. It summarizes key milestones,
Charles Sidhoum +5 more
wiley +1 more source
BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
Instance segmentation is one of the fundamental vision tasks. Recently, fully convolutional instance segmentation methods have drawn much attention as they are often simpler and more efficient than two-stage approaches like Mask R-CNN.
Kunyang Sun +11 more
core +1 more source
Non-sparse linear representations for visual tracking with online reservoir metric learning [PDF]
Most sparse linear representation-based trackers need to solve a computationally expensive ℓ₁-regularized optimization problem. To address this problem, we propose a visual tracker based on non-sparse linear representations, which admit an efficient ...
Qinfeng Shi +9 more
core +1 more source
Wafer‐scale two‐dimensioanl In2Se3 oxidized into InOx on sodium‐embedded beta‐alumina enables multifunctional reconfigurable electronics. Sodium ions accumulate within distinct spatial distribution under drain‐controlle and gate‐controlled operation. Drain‐control operation gives controllability of ultraviolet‐driven optoelectronic synaptic conductance
Jinhong Min +13 more
wiley +1 more source
Reduced Graphene Oxide Transparent Electrodes Enabling Compact Soft Tunable Lenses
By spray‐coating an elastomeric membrane with reduced graphene oxide (rGO) at various surface densities, elastomeric actuators are manufactured. Electro‐mechano‐optical characterizations show the suitability of rGO as an effective material for compliant, semi‐transparent electrodes, enabling soft electrically tunable lenses with a compact form factor ...
Giacomo Sasso +4 more
wiley +1 more source

