A Visual Memory Network for Scene Understanding
AVENUE is an ANR project that aims to improve computer vision systems through a visual memory network for human-like interpretation of scenes. To this end, we focus on three research themes. The first is to learn a network representation of image, video and text data collections, to leverage their inherent diverse cues. The second is to depart from supervised learning paradigms, without compromising on the performance, e.g., through self-supervised approaches. The third one is to perform inference with the learnt network, e.g., to estimate physical and functional properties of objects.
This webpage presents a summary of the work, i.e., publications, software and datasets, done since the project started in April 2019.