We propose a novel method for template matching in unconstrained environments. Its essence is the Best-Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is based on counting the number of Best-Buddies Pairs (BBPs)-pairs of points in source and target sets that are mutual nearest neighbours, i.e., each point is the nearest neighbour of the other. BBS has several key features that make it robust against complex geometric deformations and high levels of outliers, such as those arising from background clutter and occlusions. We study these properties, provide a statistical analysis that justifies them, and demonstrate the consistent success of BBS on a challenging real-world dataset while using different types of features.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TPAMI.2017.2737424 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A Coarse-Grained Simulation Approach for Protein Molecular Conformation Dynamics.
J Phys Chem A
January 2025
Computer Modelling Group, 3710 33 St NW, Calgary, Alberta T2L 2M1, Canada.
Coarse-grained molecular dynamics simulation is widely accepted for assessment of a large complex biological system, but it may also lead to a misleading conclusion. The challenge is to simulate protein structural dynamics (such as folding-unfolding behavior) due to the lack of a necessary backbone flexibility. This study developed a standard coarse-grained model directly from the protein atomic structure and amino acid coarse-grained FF (such as MARTINI FF v2.
View Article and Find Full Text PDFDetecting somatic variants in purified brain DNA obtained from surgically implanted depth electrodes in epilepsy.
Epilepsia
January 2025
Department of Clinical Neurosciences, University of Calgary, Calgary, Alberta, Canada.
Objective: Somatic variants causing epilepsy are challenging to detect, as they are only present in a subset of brain cells (e.g., mosaic), resulting in low variant allele frequencies.
View Article and Find Full Text PDFEngineering 2D spin networks by on-surface encapsulation of azafullerene radicals in nanotemplates.
Nat Commun
January 2025
Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia.
We present an efficient strategy for on-surface engineering of organic metal-free supramolecular complexes with long-term spin protection. By vacuum deposition of azafullerene (CN) monomers on a pre-deposited template layer of [10]cycloparaphenylene ([10]CPP) nanohoops on Au(111) surface we exploit the molecular shape matching between the CN and [10]CPP for the azafullerene encapsulation with nanohoops in a guest-host complexation geometry. CN⊂[10]CPP supramolecular complexes self-assemble into an extended two-dimensional hexagonal lattice yielding a high density network of stable spin-1/2 radicals.
View Article and Find Full Text PDFCell of origin and expression profiles of pseudomyxoma peritonei derived from the appendix.
Pathol Res Pract
December 2024
Division of Clinical Genome Research, Institute of Medical Science, The University of Tokyo, Tokyo, Japan. Electronic address:
Article Synopsis
- Pseudomyxoma peritonei (PMP) is a rare condition linked to mucin-producing tumors, usually starting in the appendix, leading to mucin buildup in the abdomen.
- Researchers conducted RNA-seq analysis on ten PMP cases and their healthy tissue to reveal 32 differently expressed genes, indicating that PMP tumors arise from goblet cells.
- The study found significant associations between PMP tumors and important biological processes like epithelial-mesenchymal transition, angiogenesis, and inflammation, with further analysis highlighting distinct gene expressions in different PMP types, suggesting more aggressive traits in peritoneal mucinous adenocarcinomas (PMCA).
Associative learning of non-nestmate cues improves enemy recognition in ants.
Curr Biol
December 2024
Department of Evolutionary Biology and Ecology, Institute of Biology I, University of Freiburg, Hauptstraße 1, 79104 Freiburg, Germany. Electronic address:
Recognition protects biological systems at all scales, from cells to societies. Social insects recognize their nestmates by colony-specific olfactory labels that individuals store as neural templates in their memory. Throughout an ant's life, learning continuously shapes the nestmate recognition template to keep up with the constant changes in colony labels.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!