Florent Monay @ Idiap Research Institute

Now

I am currently a software developer and transfer technology officer at the Idiap research institute. The Idiap portfolio gives a good overview of the technologies that can be discussed today.

My interests cover various topics related to computer vision (Quelhas et al. 2005) (Quelhas et al. 2007), multimedia data modeling (Monay and Gatica-Perez 2007) (Grangier, Monay, and Bengio 2006) (Monay and Gatica-Perez 2004) (Monay and Gatica-Perez 2003), and more generally machine learning.

GNU/Linux is still my main working environment. Here is an old, short list of GNU/Linux related stuff.

Please drop me an to discuss any of the points above.

Previously

March 2007 - February 2008 I worked at the lts5 lab for one year after my PhD thesis. My goal was to register visual targets on the video output of a wearable eye tracking system.

August 2002 - February 2007 I conducted a PhD thesis under the supervision of Daniel Gatica-Perez in the domain of multimedia data modeling. Here is my PhD Thesis which somehow took several years to be achieved. This page describes the mam project and shows the results of an automatic annotation experiment on a set of images.

References

Grangier, David, Florent Monay, and Samy Bengio. 2006. “A Discriminative Approach for the Retrieval of Images from Text Queries.” In Machine Learning: ECML 2006, 162–73. Springer.

Monay, Florent, and Daniel Gatica-Perez. 2003. “On Image Auto-Annotation with Latent Space Models.” In Proceedings of the Eleventh ACM International Conference on Multimedia, 275–78. ACM.

Monay, Florent, and Daniel Gatica-Perez. 2004. “PLSA-Based Image Auto-Annotation: Constraining the Latent Space.” In Proceedings of the 12th Annual ACM International Conference on Multimedia, 348–51. ACM.

Monay, Florent, and Daniel Gatica-Perez. 2007. “Modeling Semantic Aspects for Cross-Media Image Indexing.” Pattern Analysis and Machine Intelligence, IEEE Transactions on 29 (10). IEEE: 1802–17.

Quelhas, Pedro, Florent Monay, J-M Odobez, Daniel Gatica-Perez, Tinne Tuytelaars, and Luc Van Gool. 2005. “Modeling Scenes with Local Descriptors and Latent Aspects.” In Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on, 1:883–90. IEEE.

Quelhas, Pedro, Florent Monay, Jean-Marc Odobez, Daniel Gatica-Perez, and Tinne Tuytelaars. 2007. “A Thousand Words in a Scene.” Pattern Analysis and Machine Intelligence, IEEE Transactions on 29 (9). IEEE: 1575–89.