Paper ID: 2206.10903

UniUD-FBK-UB-UniBZ Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2022

Alex Falcon, Giuseppe Serra, Sergio Escalera, Oswald Lanz

This report presents the technical details of our submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2022. To participate in the challenge, we designed an ensemble consisting of different models trained with two recently developed relevance-augmented versions of the widely used triplet loss. Our submission, visible on the public leaderboard, obtains an average score of 61.02% nDCG and 49.77% mAP.

Submitted: Jun 22, 2022