Postdoc positions at Aix-Marseille University in multimodal video
recommendation

Application deadline: 11/31/2014

Description:

The ADNVIDEO project, funded in the framework of A*MIDEX (
http://amidex.univ-amu.fr/en/home), aims at extending multimodal
analysis models. It focuses on jointly processing the audio stream, the
speech transcript, the image flow, scenes, the characterization of text
overlays and user feedback.

Using as starting point the corpus, annotations and approaches developed
during the REPERE challenge (http://defi-repere.fr), this project aims
at going beyond indexing on a single modality by incorporating
information retrieval methods, not only from broadcast television, but
more generally on video documents requiring multimodal scene
analysis. The novelty here is to combine and correlate information from
different sources to enhance the qualification of content. The
application for this project relates to the issue of recommendation
applied to videos: given a video, the system finds documents (text,
image, and video) related to this video, either on the surface level or
the meaning level. In particular, the use case considered may have, in
terms of technology transfer, significant economic benefits, regarding
automatic ad targeting: automatically find the most relevant advertising
with respect to the content of a video.

Objectives:

The candidate will participate in the development of a prototype for
videos recommendation, leading to a technology transfer towards
business:

* Extraction of multimodal low-level descriptors. These descriptors
  correspond to speech, image and sound / music.
* Extraction of multimodal high-level descriptors. These
  semantic-oriented descriptors are extracted from low-level
  descriptors.
* Aggregation of multimodal descriptors to form the multimodal footprint
  of the video.
* Matching videos and promotional material.
* Validation of the video recommendation prototype.
* Participation to the scientific life of the lab, including paper
  publication.

The allocation of tasks can be performed depending on the skills of the
candidate.

Skills:

For this project, we are looking for two candidates with a PhD degree in
the areas of information retrieval, natural language processing, machine
learning or video analysis:

* Strong programming skills (C++, Java, Python…).
* Desire to produce functioning end-to-end systems, life-scale live
  demos
* Scientific rigor
* Imagination
* Top notch publications
* Excellent communication skills
* Enjoy teamwork

Candidates must presently work outside of France.

Location:

University of Aix-Marseille, LIF (http://www.lif.univ-mrs.fr) and LSIS
laboratories (http://www.lsis.org) and the company Kalyzee
(http://www.kalyzee.com).

Contact:

sebastien.fournier@lsis.org

Candidates should email a letter of application, a detailed CV including
a complete list of publications, and source code showcasing programming
skills.