Giuseppe Passino

Contact Details

Research Group: Multimedia and Vision Research Group

Supervisor: Prof Ebroul Izquierdo

Second Supervisor: Dr Ioannis Patras

Research Topic: Patch-based Semantic Labelling of Images

Research Scope:

The research project involves the study of models capable to analyse the structure of an image in terms of relationships among building parts, or patches. This process is aimed at discriminating the relevant clues that allow to pair specific low-level patches appearances with high-level semantic "concepts". In this context, the reasoning can dramatically benefit from the availability of structural data, i.e., information associated to the copresence and relative location of patches. The main challenge is how to take into account this information avoiding the complexity explosion associated to the intrinsic high dimensionality of the problem. Graphical models can provide a theoretical framework to build a learning paradigm able to efficiently infer relevant clues and to use them to ultimately derive the class of the objects depicted within a collection of images.

Research interests: Image classification, object detection, pattern recognition, machine learning, graphical probabilistic models

Biography

I was born in Cagliari (Italy) in 1981. In 2002 I took a BSc in Electronic Engineering at the University of Cagliari (with honours), where in March 2005 I took a MSc in Electronic Engineering (with honours). I had a research collaboration within the University of Cagliari for six month, until September 2005. I worked as a software engineer in Abbeynet for one year, from September 2005 to September 2006, as a software developer / designer. Since October 2006 I am a PhD student at Queen Mary, University of London, working on part-based image retrieval systems.

Publications:

Journals

• G. Passino, I. Patras, and E. Izquierdo, "Aspect Coherence for Graph-Based Semantic Image Labelling," IET Computer Vision, accepted.

Conferences

• G. Passino, I. Patras, and E. Izquierdo, "Pyramidal Model for Image Semantic Segmentation," in International Conference on Pattern Recognition, 2010.
• G. Passino, I. Patras, and E. Izquierdo, "Context Awareness in Graph-based Image Semantic Segmentation via Visual Word Distributions," in International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), 2009.
• G. Passino, T. Piatrik, I. Patras, and E. Izquierdo, "A Multimedia Content Semantics Extraction Framework for Enhanced Social Interaction," in EuroITV 2009 workshop on Enhancing Social Communication and Belonging by Integrating TV Narrativity and Game-Play, 2009.
• G. Passino, I. Patras, and E. Izquierdo, "Latent Semantics Local Distribution for CRF-based Image Semantic Segmentation," in British Machine Vision Conference, 2009.
• G. Passino, I. Patras, and E. Izquierdo, "On the Role of Structure in Part-based Object Detection," in 2008 IEEE International Conference on Image Processing (ICIP), 2008.
• G. Passino, I. Patras, and E. Izquierdo, "Aspect Coherence for Graph-Based Image Labelling," in 2008 International Conference on Visual Information Engineering (VIE), 2008, pp. 94–99.
• G. Passino and E. Izquierdo, "Patch-based Image Classification through Conditional Random Field Model," in MobiMedia 2007, 2007.
• G. Passino and E. Izquierdo, "Conditional Random Fields for High-Level Part Correlation Analysis in Images," in International Conference in Semantic and Digital Media Technologies (SAMT), 2007.