Ana B. Cambra

Phd Student

Contact:

        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]

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]