Multi-class Model Fitting by Energy Minimization and Mode-Seeking

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00323974" target="_blank" >RIV/68407700:21230/18:00323974 - isvavai.cz</a>

Výsledek na webu

<a href="http://openaccess.thecvf.com/content_ECCV_2018/papers/Daniel_Barath_Multi-Class_Model_Fitting_ECCV_2018_paper.pdf" target="_blank" >http://openaccess.thecvf.com/content_ECCV_2018/papers/Daniel_Barath_Multi-Class_Model_Fitting_ECCV_2018_paper.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-01270-0_14" target="_blank" >10.1007/978-3-030-01270-0_14</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multi-class Model Fitting by Energy Minimization and Mode-Seeking

Popis výsledku v původním jazyce

We propose a general formulation, called Multi-X, for multi-class multi-instance model fitting – the problem of interpreting the input data as a mixture of noisy observations originating from multiple instances of multiple classes. We extend the commonly used α-expansion-based technique with a new move in the label space. The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization. Key optimization parameters like the bandwidth of the mode seeking are set automatically within the algorithm. Considering that a group of outliers may form spatially coherent structures in the data, we propose a cross-validation-based technique removing statistically insignificant instances. Multi-X outperforms significantly the state-of-the-art on publicly available datasets for diverse problems: multiple plane and rigid motion detection; motion segmentation; simultaneous plane and cylinder fitting; circle and line fitting.

Název v anglickém jazyce

Multi-class Model Fitting by Energy Minimization and Mode-Seeking

Popis výsledku anglicky

We propose a general formulation, called Multi-X, for multi-class multi-instance model fitting – the problem of interpreting the input data as a mixture of noisy observations originating from multiple instances of multiple classes. We extend the commonly used α-expansion-based technique with a new move in the label space. The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization. Key optimization parameters like the bandwidth of the mode seeking are set automatically within the algorithm. Considering that a group of outliers may form spatially coherent structures in the data, we propose a cross-validation-based technique removing statistically insignificant instances. Multi-X outperforms significantly the state-of-the-art on publicly available datasets for diverse problems: multiple plane and rigid motion detection; motion segmentation; simultaneous plane and cylinder fitting; circle and line fitting.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Centrum pro multi-modální interpretaci dat velkého rozsahu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ECCV2018: Proceedings of the European Conference on Computer Vision, Part XVI

ISBN

978-3-030-01269-4

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

17

Strana od-do

229-245

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Munich

Datum konání akce

8. 9. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—