ESANN 2012 Special Session on Multimedia

I am organizing a special session with Philippe Gosselin at this year's ESANN conference.

Machine Learning for multimedia applications
David Picard , ETIS – ENSEA, Philippe-Henri Gosselin , INRIA Rennes (France)

In recent years, many multimedia applications have shown very successful improvements by leveraging machine learning techniques. These applications include image and video classification, object recognition, image and video retrieval, or event detection.

However, these multimedia applications also uncover new machine learning problems in areas such as mid-level features learning, distance learning, feature combination, and so on.

This special session is intended to research papers that combine machine learning for multimedia problems. The following topics are of particular interest:

  • Mid-level features learning, Deep learning
  • Feature combination, Multiple kernel learning
  • Kernel methods, Kernel learning, Distance learning
  • Machine learning methods specially adapted to image classification, image and video retrieval, object or event recognition, etc.
Important Dates:
Submission of full paper: November 30, 2012
Notification of acceptance: February 1, 2013

GeoDiff Workshop at VISIGRAPP

My fellow colleague Aymeric Histace is organizing a workshop at VISIGRAPP following our work on the GeoDiff projet. The key topic is the study of complex diffusion processes by variational approaches and multi-agent systems. I'll be part of the committee to give some help. This workshop is totally open to contributions, so I hope we will have many interesting papers to review. We already have programmed some nice tutorials on MAS.

Here is the scope:
The main aim of this special session is to bring together researchers who are interested in variational methods and by multi agent system in order to (i) reflect on a state-of- the-art on their abilities to model reaction-­-diffusion processes, and (ii) to discuss potential new applications since these two different types of tools are not generally 3 associated with each other whereas such a joint applications can be of primary interest to model complex diffusion process at different scales of the phenomenon.
A second objective of this special session, but not necessarily less important than the first one, is to imagine through this particular application context new tools that will find future applicability in image processing (image restoration or inpainting mainly).

And the important dates:
Paper Submission: November 8, 2012
Authors Notification: December 6, 2012
Final Paper Submission and Registration: December 18, 2012

JKernelMachines 1.3

New version of my pure Java ML library. It seems I'm working a lot on it these days. The main novel item is the introduction of a multiclass classifier compatible will all binary classifier thanks to Java Generics. I also made a class for N-Fold cross-validation, and add a package for generating toys data. As usual, there is also some bug fixes.

The updated entry is on mloss.

JKernelMachines 1.2

Short update on JKernelMachines with few news features (new non-convex SVM algorithm, customizable MKL regarding internal SVM solver), many bug fixes, and a more complete example usable as a standalone application.

The reference page can be found on mloss.

Paper accepted at ICPR 2012

We have a paper on image categorization accepted at ICPR next November. This is the other part of the Work Romain Negrel has been doing with VLAT. This time it's about efficiency in image classification. We tried to put every tricks of latest image categorization techniques (like dense sampling, spatial pyramid, and so on) into our VLAT while still retaining small size signatures.

All in all, we managed to achieve 61.5% mAP on VOC2007, which is not bad at all considering we used a single feature and a linear classifier (a stochastic gradient descent from Leon Bottou). Actually, if you put the throttle a bit further, you can expect better results, but then it becomes very heavy computationally speaking. As usual, some code is available here, although it's only for the Holydays dataset right now. At least you can produce the features and then use your own machine learning library (or mine, of course!).

page 1 of 4next»