This technical report describes the EgoTask Translation approach that explores relations among a set of egocentric video tasks in the Ego4D challenge. To improve the primary task of interest, we propose to leverage existing models developed for other related tasks and design a task translator that learns to ''translate'' auxiliary task features to the primary task. With no modification to the baseline architectures, our proposed approach achieves competitive performance on two Ego4D challenges, ranking the 1st in the talking to me challenge and the 3rd in the PNR keyframe localization challenge.
翻译:本技术报告描述了在Ego4D挑战赛中探索一组自我中心视频任务间关系的EgoTask转换方法。为提升目标任务性能,我们提出利用为其他相关任务开发的现有模型,并设计一个任务转换器,学习将辅助任务特征“转换”至目标任务。在不修改基线架构的前提下,我们的方法在两个Ego4D挑战赛中获得竞争力表现,在“是否与我对话”挑战赛排名第一,在PNR关键帧定位挑战赛排名第三。