Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge
This work improves temporal action localization for ego-centric video analysis, though it is incremental as it builds on existing methods.
The paper tackled the Ego4D Moment Queries Challenge by combining ActionFormer with multiple video features, achieving 21.76% average mAP and 42.54% Recall@1x at tIoU=0.5, outperforming baselines and competitors.
This report describes our submission to the Ego4D Moment Queries Challenge 2022. Our submission builds on ActionFormer, the state-of-the-art backbone for temporal action localization, and a trio of strong video features from SlowFast, Omnivore and EgoVLP. Our solution is ranked 2nd on the public leaderboard with 21.76% average mAP on the test set, which is nearly three times higher than the official baseline. Further, we obtain 42.54% Recall@1x at tIoU=0.5 on the test set, outperforming the top-ranked solution by a significant margin of 1.41 absolute percentage points. Our code is available at https://github.com/happyharrycn/actionformer_release.