Abstract
This report describes our submission to the Ego4D Moment Queries Challenge 2023. Our submission extends ActionFormer, a latest method for temporal action localization. Our extension combines an improved ground-truth assignment strategy during training and a refined version of SoftNMS at inference time. Our solution is ranked 2nd on the public leaderboard with 26.62% average mAP and 45.69% Recall@1x at tIoU=0.5 on the test set, significantly outperforming the strong baseline from 2023 challenge. Our code is available at this https URL.
Abstract (translated)
本报告描述了我们向2023年Ego4D时刻查询挑战提交的方案。我们的方案扩展了ActionFormer,这是一种最新的时间行动定位方法。我们的扩展在训练期间采用了改进的真实值分配策略,并在推断期间采用了改进的SoftNMS版本。我们在测试集上的解决方案在public leaderboard上排名第二,平均mAP为26.62%,Recall@1x的精度为45.69%。在2023年挑战中强有力的基准线的显著超越表明我们的解决方案是出色的。我们的代码可在this https URL上获取。
URL
https://arxiv.org/abs/2307.02025