In this report we describe the technical details of our submission to the EPIC-Kitchens Action Recognition 2020 Challenge. To participate in the challenge we deployed spatio-temporal feature extraction and aggregation models we have developed recently: Gate-Shift Module (GSM) [1] and EgoACO, an extension of Long Short-Term Attention (LSTA) [2]. We design an ensemble of GSM and EgoACO model families with different backbones and pre-training to generate the prediction scores. Our submission, visible on the public leaderboard with team name FBK-HUPBA, achieved a top-1 action recognition accuracy of 40.0% on S1 setting, and 25.71% on S2 setting, using only RGB.
@article{arxiv.2006.13725,
title = {FBK-HUPBA Submission to the EPIC-Kitchens Action Recognition 2020 Challenge},
author = {Swathikiran Sudhakaran and Sergio Escalera and Oswald Lanz},
journal= {arXiv preprint arXiv:2006.13725},
year = {2020}
}
Comments
Ranked 3rd in the EPIC-Kitchens action recognition challenge @ CVPR 2020