New opening for a PhD position on "Face and person attribute recognition from multimedia sources"

Context: We are looking for a highly motivated candidate for a doctoral position in computer vision and multimedia retrieval.

The work will take place in the context of the EUMSSI project funded by the European Community, whose main goal is to leverage multimodal content analysis (audio/speech/video/text) along with social media data to address contextual media retrieval and recommendation tasks. The project involves academic partners in Spain, France and Germany as well as a news agency and a video content managing company. Idiap will address the extraction of people and related concepts from ultimedia information, and their use in the envisioned application.

Position: The research topic will address the recognition and characterization of faces and people in broadcasted data In particular, the scaling of existing methods and improvements of face and attribute representation will be investigated, as well as the exploitation of complementary media (like speech transcripts, links with other media, e.g. traditional news media like le monde') to perform the fast curating of large video database.

The ideal PhD candidate is expected to have a Master in Computer Science or Electrical Engineering, with experience in one or more of the following topics: multimedia indexing and retrieval, computer vision, machine learning. The applicant should have strong programming skills and be familiar with C/C++ and the Linux environment.

To apply for this position, click on the following link : Face and person attribute recognition from multimedia sources