论文标题
蒙面的自动编码器,用于以Egentric视频理解 @ ego4d挑战2022
Masked Autoencoders for Egocentric Video Understanding @ Ego4D Challenge 2022
论文作者
论文摘要
在本报告中,我们介绍了在两个以Egentric的视频理解任务中应用蒙版自动编码器的方法和经验结果,即EGO4D挑战2022的对象状态变化分类和PNR时间定位。作为THESSVL,我们在这两个任务中均排名第二。我们的代码将提供。
In this report, we present our approach and empirical results of applying masked autoencoders in two egocentric video understanding tasks, namely, Object State Change Classification and PNR Temporal Localization, of Ego4D Challenge 2022. As team TheSSVL, we ranked 2nd place in both tasks. Our code will be made available.