Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Multiscale combinatorial grouping

Autor
Arbelaez, P.; Pont, J.; Barron, J.; Marques, F.; Malik, J.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2014
Any de l'edició
2014
Data de presentació
2014-06
Llibre d'actes
2014 IEEE Conference on Computer Vision and Pattern Recognition, 23-28 June 2014, Columbus, Ohio: proceedings
Pàgina inicial
328
Pàgina final
335
Editor
Institute of Electrical and Electronics Engineers (IEEE)
DOI
https://doi.org/10.1109/CVPR.2014.49 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/26949 Obrir en finestra nova
URL
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909443 Obrir en finestra nova
Resum
We propose a unified approach for bottom-up hierarchical image segmentation and object candidate generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm. We then propose a high-performance hierarchical segmenter that makes effective use of multiscale information. Finally, we propose a grouping strategy that combines our multiscale regions into highly-accurate object candidates by exploring efficiently their c...
Citació
Arbelaez, P. [et al.]. Multiscale combinatorial grouping. A: IEEE Conference on Computer Vision and Pattern Recognition. "2014 IEEE Conference on Computer Vision and Pattern Recognition, 23-28 June 2014, Columbus, Ohio: proceedings". Columbus, Ohio: Institute of Electrical and Electronics Engineers (IEEE), 2014, p. 328-335.
Paraules clau
Image Segmentation, Object Candidates
Grup de recerca
GPI - Grup de Processament d'Imatge i Vídeo

Participants

  • Arbelaez, Pablo Andres  (autor ponent)
  • Pont Tuset, Jordi  (autor ponent)
  • Barron, Jonathan  (autor ponent)
  • Marques Acosta, Fernando  (autor ponent)
  • Malik, Jitendra  (autor ponent)

Arxius