Eduardo Valle’s Blog

Technology, Science, Teaching

Archive for June, 2009

Tutorial Accepted on SIBGRAPI 2009

Posted by eduardovalle on Wednesday, June 24, 2009

My tutorial proposal “Advanced Techniques in CBIR: Local Descriptors, Visual Dictionaries and Bags of Features” has been accepted on the Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2009), which will be held at the Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio), Brazil between October 11th and 14th, 2009. The tutorial itself will probably happen on October 11th.

Here’s the abstract:

“Local descriptors have been extensively used in CBIR systems, where their robustness to intense geometric and photometric transformations allows the identification of a target object/image with great reliability. However, due to their excessive discriminating power, their application to the retrieval of complex categories is challenging. The introduction of the technique of ‘visual dictionaries’ (also known as ‘dictionary of visual terms’) is an important step towards the conciliation between the robustness of local descriptors and the flexibility of generalization needed by complex queries. As a bonus, we become able to employ advanced retrieval techniques which were so far available only for textual data.

The importance of local descriptors in the current practice of CBIR can hardly be overestimated, and the introduction of the ‘visual dictionary’ technique has allowed to employ them on complex category search, a context where they were previously considered too discriminating to work effectively. In this tutorial we will address all the conceptual components of a powerful framework — the CBIR system architecture itself, the local descriptors and the techniques which allow their advanced application. At the end, the audience will have a good idea of the current state of art, the most promising research trends and the challenges still faced by the technology.”

The tutorial will take 3 hours and will be given either in English or Portuguese, according to the composition of the classroom.

EDIT 11/11/2009: The tutorial survey is available on my publications page.

Posted in publications | Tagged: , , , | Leave a Comment »

Cooperations, developments, projects: taming the complexity of research

Posted by eduardovalle on Tuesday, June 2, 2009

In the last days I’ve been working round the clock — I’ve given my kNN search talk twice and several call-for-papers deadlines went by (or are coming), which meant that I was always in hurry for one reason or another.

This has been especially stressful, because for some time I had been getting everything done days ahead of the deadlines. But this month I went back to the classic regime of “crossing fingers and hitting the submit button at (literally) the last minute”.

As I move towards more complex research involving several labs, many students and audacious experimental designs I feel increasingly the need of using more formal management tools. But techniques created for Business (or even Engineering) do not seem to translate well to Academic research.

For example: I’ve tried to use Gantt charts in Microsoft Project to keep track of complex tasks and their dependencies. But I’ve found that as the work progresses, the list of tasks changes often and significantly, as some research directions reveal to be more fruitful than others. This ends up rendering the initial planning (and any chronogram based on it) useless.

Maybe is it the case of using an adapted “Spiral Model“, where risks are minimised from iteration to iteration, and creating detailed chronograms only for the lifetime of an iteration?  Or are there specific management models for research projects? How the most efficient R&D labs manage their projects? How to adapt their experience to Brazilian public research?

Unfortunately, so far, I seem to have more questions than answers. I’ve bought this interesting book “Managing Science: Management for R&D Laboratories“, which is biased towards Particle Physics labs, but has (hopefully) useful concepts for all areas of experimental research and will help me to get an initial handle on the subject.

Posted in career | Tagged: , , , , | 2 Comments »