Below you can find the text describing the special session, and more
information is here: http://sisap.org/2020/specialsessions.html

Recent years have witnessed a strong renovated interest in artificial intelligence. This has been mainly due to the outstanding performance offered by deep learning methods, thanks to the innovative architecture, the availability of huge quantities of training data, and the high computing power provided by GPU architectures.

There are noteworthy relationships between methods of artificial intelligence and similarity search. For example, similarity search is more often executed on features (for instance image features) extracted using artificial intelligence methods, rather than hand-crafted methods. This poses new challenges, given that such features have generally much higher (intrinsic) dimensionality than hand-crafted features. Artificial intelligence has also been used as an instrument for building efficient and effective methods for similarity search. Consider for instance methods of metric learning, learning to index, and learning to hash. In this case, artificial intelligence is used as an alternative to hand-crafted structures and data coding to obtain efficient and effective similarity search algorithms. In addition, consider that what is generally behind many machine learning methods is the possibility of comparing, judging relationships, and estimating similarity among objects or entities in order to classify, recognize, and take decisions.

In this special session, we seek contributions where artificial intelligence and similarity evaluation/searching is either exploited in synergy or supporting one the other. Both mature research papers and position papers are welcome.

Topics include, but are not limited to:

• AI-based feature extraction and similarity
• Clustering methods
• Machine learning methods and similarity
• Metric learning
• Learning to index
• Learning to hash

• Submissions must follow the regular paper submission and author guidelines of SISAP 2020 (guidelines)
• Submit your paper through EasyChair (link); please be sure to select “Special Session: Artificial Intelligence and Similarity” in the appropriate field of the submission form.