Výsledky vyhledávání - "Keywords: Algorithm performance"

Assessing the accuracy of blending Landsat–MODIS surface reflectances in two landscapes with contrasting spatial and temporal dynamics: A framework for algorithm selection

Autoři: Emelyanova, Irina V. McVicar, Tim R Van Niel, Thomas G. a další

Zdroj: Remote Sensing of Environment. 133:193-209

Témata: Landforms, Errors, Radiometers, 0211 other engineering and technologies, 0207 environmental engineering, Keywords: Algorithm performance, 02 engineering and technology, 15. Life on land, Benchmarking algorithm, Blending, Spatial-temporal variance, Algorithm selection, Spatial temporals, Benchmarking, Spatial and temporal variances, ESTARFM, Surface reflectance, accuracy ass ESTARFM, STARFM, Landsat-MODIS blending, Fusion, Fusion reactions, Algorithms

Přístupová URL adresa: https://openresearch-repository.anu.edu.au/bitstream/1885/64685/2/01_Emelyanova_Assessing_the_accuracy_of_2013.pdf
https://ui.adsabs.harvard.edu/abs/2013RSEnv.133..193E/abstract
https://openresearch-repository.anu.edu.au/handle/1885/64685?mode=full
https://pubag.nal.usda.gov/catalog/876427
https://digitalcollections.anu.edu.au/handle/1885/64685
https://www.sciencedirect.com/science/article/pii/S0034425713000473
https://cir.nii.ac.jp/en/crid/1370005905772920577

Optimization of Robust Loss Functions for Weakly-Labeled Image Taxonomies

Autoři: McAuley, Julian J. Ramisa Ayats, Arnau Caetano, Tibério S.

Zdroj: Digital.CSIC. Repositorio Institucional del CSIC
instname
Recercat. Dipósit de la Recerca de Catalunya
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

Témata: image taxonomies, Multi-label problems, Image classification, Imatges -- Processament -- Informàtica, Image Processing, 0211 other engineering and technologies, Keywords: Algorithm performance, Computer-Assisted -- methods, 02 engineering and technology, State-of-the-art methods, computer vision, object recognition, Image taxonomy, image labeling [optimisation paraules autor], Image labeling, structured learning, Image Processing, Computer-Assisted -- methods, 0202 electrical engineering, electronic engineering, information engineering, Binary classification, Image taxonomies, Learning systems, image tagging, Image tagging, Optimization Image labeling, optimisation paraules autor: image labeling, Structured learning, Taxonomies, image classification

Popis souboru: application/pdf

Přístupová URL adresa: http://i.stanford.edu/~julian/pdfs/emmcvpr11.pdf
http://hdl.handle.net/10261/96434
http://hdl.handle.net/2117/20202

Optimization of Robust Loss Functions for Weakly-Labeled Image Taxonomies

Autoři: McAuley, Julian Ramisa, Amau Caetano, Tiberio

Zdroj: International Journal of Computer Vision

Témata: Keywords: Algorithm performance; Binary classification; Image labeling; Image tagging; Image taxonomy; Multi-label problems; State-of-the-art methods; Structured learning; Image classification; Learning systems; Taxonomies; Optimization Image labeling; Image tagging; Image taxonomies; Structured learning, Journal article

URL: http://hdl.handle.net/1885/66482

Optimization of Robust Loss Functions for Weakly-Labeled Image Taxonomies: An ImageNet Case Study

Autoři: McAuley, Julian Ramisa, Amau Caetano, Tiberio

Zdroj: Optimization of Robust Loss Functions for Weakly-Labeled Image Taxonomies: An ImageNet Case Study

Témata: Keywords: Algorithm performance; Binary classifiers; Data sets; Empirical evidence; Evaluation measures; Image taxonomy; Input features; Latent variable; Learning methods; Learning techniques; Loss functions; Multi-label; Multiple objects; Object classification; Pe, Conference paper

URL: http://hdl.handle.net/1885/36037
Energy Minimization Methods in Computer Vision and Pattern Recognition