Innovative Query Modes for Audiovisual Content Search Engines using Deep Learning

Description

This research will advance the technology of search engines for audiovisual content such as pictures, videos, 3D. Although text remains the dominant mode for querying search engines, new research indicate that it will become possible in the future to also trigger searches using other modes (such as formulating what you are looking for by drawing it, through sounds, or even directly through other memories, etc…). This research will focus on using computer vision, machine learning (deep learning) and neuromorphic approaches to design such innovative interfaces and query modes, as well as instantaneous search thanks to associative memories and efficient inverted indexes. It will allow the candidate to develop a unique and transferable expertise in advanced machine learning, AI and Big Data. The researcher will be integrated within a significant group of deep learning researchers involved in regional and international collaboration with world-leading labs in the area.