Sort by
Refine Your Search
-
-Language Models (VLMs). The postdoctoral researcher will explore how advanced generative and multimodal models can be designed, adapted, and applied to challenging vision tasks such as image understanding
-
to identify, map, and measure in airborne and satellite images of the Earth, the natural and socio-environmental hazards and risks studied in IRIMA(earthquakes, tsunamis, volcanic eruptions, landslides
-
(particularly Deep Learning), will also make it possible to leverage the collected data to enrich knowledge of ovine behavior. The candidate will join a dynamic research group within the Image/Vision team
-
, they must ensure a sufficiently high level of accuracy to guarantee the reliability required for systems demanding high durability, reliability, and safety. The scientific vision of DuraSyS-PAC is to address
-
vision and robotics (collaborative robot arm, humanoid robot) to enable the dynamic handover of an object from a person to a robot and carry it together to move it. - Activity 1: Substantive work focused