Departamento de Informática e
ingeniería de sistemas (DIIS)
Escuela de Ingeniería y
Arquitectura (EINA)
Universidad de Zaragoza (UZ)
C/Maria de Luna, 1
50018 Zaragoza, Spain
Phone: (+34) 897 55 50 75
Office: 1.18
Email: acambra | AT | unizar |
DOT | es
Research
How to adapt existing CNN models for new semantic segmentation tasks?
Many applications
need to learn new specific classes but do not have a lot of labeled
training data. This work addresses the problem of transferring the
knowledge from existing CNN models to different classes to those the
model has been trained for. Our work explores the two common transfer
learning approaches for the particular problem of semantic
segmentation:
1) fine-tuning existing models with the newtraining data, following a standard pipeline;
2) training a superpixel classifier combining local and context information.
A generic tool for interactive complex image editing
This work presents
an efficient interaction paradigm that approximates any per-pixel
magnitude from a few user strokes by propagating the sparse user input
to each pixel of the image. We illustrate this through three
interactive applications: depth of field simulation, dehazing and tone
mapping.
Publications
Journals
A generic tool for interactive complex image editing. A. B. Cambra, A. C.
Murillo, A. Muñoz. The Visual Computer 2017, p. 1-13. [PDF] [bibtex][Project page]
International
conferences and
workshops
How to adapt existing CNN models for new semanticsegmentation tasks?A. B. Cambra, A. Muñoz, A. C.
Murillo. Robot 2017: Thrid Iberian Robotics Conference. Sevilla, Spain. [PDF]
Dense Labeling with User Interaction: an Example for Depth-Of-Field Simulation. A. B. Cambra, A. Muñoz, J.J. Guerrero, A. C.
Murillo. BMVC 2016. York, UK. [PDF] [abstract][supplementary] [poster] [bibtex]
Towards robust and
efficient text sign
reading from a
mobile phone. A. B.
Cambra, A. C. Murillo. IEEE International Workshop on Mobile Vision,
held with ICCV 2011. [PDF]
National
conferences
Improving depth estimation using
superpixels. A. B. Cambra, A. Muñoz, A. C. Murillo, J.J.
Guerrero y D. Gutiérrez. CEIG 2014. Zaragoza, Spain. [PDF]
Poster
Presentation
Interactive depth of field simulation using
dense depth labeling estimation. A. B. Cambra, A. Muñoz, A. C.
Murillo, J.J. Guerrero y D. Gutiérrez. WiCV with CVPR 2015. Boston,
EEUU. [PDF] [video]
Improving depth estimation using
superpixels. A. B. Cambra, A. Muñoz, A. C. Murillo, J.J.
Guerrero y D. Gutiérrez. ICVSS 2014. Sicily Italy. [PDF]
Others
Reconocimiento robusto de texto en imágenes
de dispositivos móviles. A. B. Cambra. Master Thesis[PDF]
Interpretación de carteles con la cámara de
un móvil. A. B. Cambra. PFC [PDF]
I'm PhD student at Universidad de Zaragoza (Spain), advised by Prof. Ana C. Murillo and Prof. Adolfo Muñoz.
My research interests cover the fields of computer vision and graphics.