Results 81 to 90 of about 18,794 (253)
Distilling Vision Foundation Models into LiDAR Networks via Manifold-Aware Topological Alignment
LiDAR point cloud semantic segmentation is essential for autonomous driving, yet LiDAR-only methods remain constrained by sparsity and limited texture cues.
Yuchuan Yang, Xiaosu Xu
doaj +1 more source
Aligning Spatio-Temporal Signals on a Special Manifold [PDF]
We investigate the spatio-temporal alignment of videos or features/signals extracted from them. Specifically, we formally define an alignment manifold and formulate the alignment problem as an optimization procedure on this non-linear space by exploiting its intrinsic geometry.
Ruonan Li, Rama Chellappa
openaire +1 more source
This study demonstrates how optimizing laser power, scanning speed, and hatching distance in laser powder bed fusion can boost the productivity of Inconel 718 manufacturing by up to 29% while maintaining mechanical integrity. The work delivers a validated process window and cost–time analysis, offering industry‐ready guidelines for efficient additive ...
Amir Behjat +7 more
wiley +1 more source
Manifold-aware learning for robot trajectory design: Riemannian optimization on the Stiefel manifold
Many robotic applications—from drone navigation to surgical automation—require planning trajectories that respect directional constraints, which are inherently non-Euclidean.
Yinpu Ma, Cunlin Li
doaj +1 more source
Unsupervised Alignment of Image Manifolds with Centrality Measures
The re-use of available labeled samples to classify newly acquired data is a hot topic in pattern analysis and machine learning. Classification algorithms developed with data from one domain cannot be directly used in another related domain, unless the data representation or the classifier have been adapted to the new data distribution. This is crucial
Devis Tuia +2 more
openaire +2 more sources
A unified research data management framework for heterogeneous materials data is presented. The system integrates multimodal datasets using ontologies and knowledge graphs, enabling interoperability and FAIR (findable, accessible, interoperable, reusable) data principles. By linking data across scales and workflows, it supports reproducible, Artifitial
Doaa Mohamed +6 more
wiley +1 more source
A simplified thermoplastic pultrusion model is developed to predict thermal fields in glass fiber/polyethylene terephthalate (GF/PET) composites with reduced computational cost. By combining effective material homogenization, validation against literature data, and Gaussian‐process‐based optimization, the study reveals how heating limits, pulling speed,
Elder Soares +3 more
wiley +1 more source
Exploring geometry of genome space via Grassmann manifolds
Summary: It is important to understand the geometry of genome space in biology. After transforming genome sequences into frequency matrices of the chaos game representation (FCGR), we regard a genome sequence as a point in a suitable Grassmann manifold ...
Xiaoguang Li +4 more
doaj +1 more source
Phase‐field simulations coupled with dislocation‐density‐based crystal plasticity modeling reproduce γ′ rafting behavior in single‐crystal Ni‐based superalloys under varied loading conditions. The model captures both macroscopic creep and microscopic morphology evolution, with results matching high‐temperature creep experiments.
Micheal Younan +5 more
wiley +1 more source
Stabilizing brain-computer interfaces through alignment of latent dynamics
Intracortical brain-computer interfaces (iBCIs) restore motor function to people with paralysis by translating brain activity into control signals for external devices.
Brianna M. Karpowicz +12 more
doaj +1 more source

