Sort by
Refine Your Search
-
, multi-modal continual learning, or adaptation to open-world scenarios. PROJECT PI & HOSTING GROUP The direct responsible for this post will be Dr. Joost van de Weijer, PI of the Learning and Machine
-
on developing new methods for color-specific conditional generation in multi-modal generative models. The candidate will work on exploiting the intrinsic knowledge about color within text-to-image (T2I) models
-
Vision, Language and Reading group at the Computer Vision Center (CVC), in Barcelona, Spain. The position is initially for 3 years and linked to the “European Large Open Multi-Modal Foundation Models
Searches related to multi object tracking
Enter an email to receive alerts for multi-object-tracking positions