Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge
Autor: | Mu, Fangzhou, Mo, Sicheng, Wang, Gillian, Li, Yin |
---|---|
Rok vydání: | 2022 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | 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. Comment: 2nd place in ECCV 2022 Ego4D Moment Queries Challenge |
Databáze: | arXiv |
Externí odkaz: |