Abstract: Instance-level Image Retrieval (IIR), or simply Instance Retrieval, deals with the problem of finding all the images within an dataset that contain a query instance (e.g. an object). This ...

In this work, we will investigate the SetCon model from 'Learning Object-Centric Video Models by Contrasting Sets' by Löwe et al. The SetCon model has been published in November 2020 by the Google ...

This is the source code for the paper "Influence beyond similarity: a Contrastive Learning approach to Object Influence Retrieval", published as a EKAW conference paper. We introduce an approach to ...

To enhance communication between humans and robots, it is essential to improve the ability of robots to comprehend the meaning of ambiguous natural language (ANL) used by humans. Artificial ...

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we ...

The recent success in self-supervised models can be attributed in the renewed interest of the researchers in exploring contrastive learning, a paradigm of self-supervised learning. For instance, ...

Conducting text retrieval in a dense learned representation space has many intriguing advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires combination with ...