Loading...
Loading...

Go to the content (press return)

Multiresolution hierarchy co-clustering for semantic segmentation in sequences with small variations

Author
Varas, D.; Alfaro, M.; Marques, F.
Type of activity
Presentation of work at congresses
Name of edition
15th IEEE International Conference on Computer Vision
Date of publication
2015
Presentation's date
2015-12
Book of congress proceedings
ICCV 2015: 2015 IEEE International Conference on Computer Vision: proceedings: 11–18 December 2015: Santiago, Chile
First page
4579
Last page
4587
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
DOI
https://doi.org/10.1109/ICCV.2015.520 Open in new window
Repository
http://hdl.handle.net/2117/91349 Open in new window
URL
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7410877 Open in new window
Abstract
This paper presents a co-clustering technique that, given a collection of images and their hierarchies, clusters nodes from these hierarchies to obtain a coherent multiresolution representation of the image collection. We formalize the co-clustering as Quadratic Semi-Assignment Problem and solve it with a linear programming relaxation approach that makes effective use of information from hierarchies. Initially, we address the problem of generating an optimal, coherent partition per image and, af...
Citation
Varas, D., Alfaro, M., Marques, F. Multiresolution hierarchy co-clustering for semantic segmentation in sequences with small variations. A: IEEE International Conference on Computer Vision. "ICCV 2015: 2015 IEEE International Conference on Computer Vision: proceedings: 11–18 December 2015: Santiago, Chile". Santiago: Institute of Electrical and Electronics Engineers (IEEE), 2015, p. 4579-4587.
Keywords
Boundary detection, Combinatorial optimization, Computer vision, Image collections, Information use, Iterative methods, Linear programming, Linear programming relaxation, Multi resolution representation, Multiresolution video, Quadratic semi-assignment problem, Semantic segmentation, Semantics, State of the art
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants