[Comp-neuro] Postdoc Position in Face Recognition with Attributes, at the University of Caen, France

Frederic Jurie frederic.jurie at unicaen.fr
Wed Nov 19 11:37:08 CET 2014

Postdoc Position in Face Recognition with Attributes, at the University of Caen, France

The Computer Vision group of the University of Caen (France) is opening a PhD position starting on the 1st of February 2015.

Topic:  We are interested in forensic investigation scenarios in which some persons of interest have to be identified using verbal descriptions provided by witnesses (e.g. gender, race, age, etc.). It is well known that, in general, variations in  pose, illumination, occlusions, or expression makes face recognition in unconstraint environments very challenging.  In this context, we aim at addressing simultaneously the two issues (searching subject by verbal description and building robust face description) by building semantic visual features of a face images that are insensitive to the aforementioned imaging variations and can be used for verbal searches. More precisely, we will investigate potential extensions of the recent works on this topic, such a [1,2,3,4,5,6]. This research will be carried within the context of the ANR/PHYSIONOMIE project; scientific collaborations with the MORPHO company as well as the INRIA/LEAR group are expected.

Start date: the 1st of February 2015.

Location: The position will be located at the Computer Vision group at the University of Caen.

Contacts: Prof. Frederic Jurie (frederic.jurie at unicaen.fr)

* Recent Master (preferably in Computer Science, computer vision, machine learning or Applied Mathematics)
* Solid programming skills; the project involves programming in Matlab and C++
* Solid mathematics knowledge (especially linear algebra and statistics)
* Creative and highly motivated
* Fluent in English, both written and spoken
Prior knowledge in the areas of computer vision (in particular face recognition or visual attributes), machine learning or data mining is a plus

Please send applications via email, including:
* a complete CV including a list of publications
* graduation marks as well as rank
* the name and email address of three references

Applications should be sent to Frederic Jurie (frederic.jurie at unicaen.fr). Applicants can be asked to do a short assignment in order to demonstrate their research abilities.


[1]  Neeraj Kumar, Alexander C. Berg, Peter N. Belhumeur, and Shree K. Nayar. Describable visual attributes for face verification and image search. IEEE PAMI, 33(10):1962–1977, 2011. 

[2]  Amir Sadovnik, Andrew Gallagher, and Tsuhan Chen. It’s not polite to point: Describing people with uncertain attributes. IEEE CVPR, 2013. 

[3]  Fengyi Song, Xiaoyang Tan, and Songcan Chen. Exploiting relationship between attributes for improved face verification. Computer Vision and Image Understanding, 122:143–154, 2014. 

[4]  Ziheng Wang, Yongqiang Li, Shangfei Wang, and Qiang Ji. Capturing global semantic relation-ships for facial action unit recognition. ICCV, 2013. 

[5]  Lingyun Wen and G. D. Guo. Dual attributes for face verification robust to facial cosmetics. Journal of Computer Vision and Image Processing, 3(1):63–73, 2013. 

[6]  Michael J. Wilber, Ethan Rudd, Brian Heflin, Yui-Man . M. Lui, and Terrance E. Boult. Exemplar codes for facial attributes and tattoo recognition. In Applications of Computer Vision (WACV), 2014 IEEE Winter Conference on, 2014. 

More information about the Comp-neuro mailing list