arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.14005cs.CVcs.AI
收藏

面向人物交互分类的类别查询学习

Category Query Learning for Human-Object Interaction Classification

Tongji University(同济大学);MEGVII Technology(旷视科技);Shanghai Jiao Tong University(上海交通大学)

Chi Xie, Fangao Zeng, Yue Hu, Shuang Liang, Yichen Wei

AI总结:

本文提出类别查询学习方法,通过transformer解码器将交互类别查询转换为图像特定表示,并利用辅助分类任务训练,首次应用于HOI分类,在多个基线和基准上取得最优效果。

摘要:

与以往大多数专注于学习更优人物特征的HOI方法不同,我们提出了一种新颖且互补的方法,称为类别查询学习。此类查询显式地与交互类别相关联,通过transformer解码器转换为图像特定的类别表示,并通过辅助的图像级分类任务进行学习。这一想法源于早期的一种多标签图像分类方法,但首次应用于具有挑战性的人物交互分类任务。我们的方法简单、通用且有效。在三个具有代表性的HOI基线上进行了验证,并在两个基准上取得了新的最先进结果。

英文摘要:

Unlike most previous HOI methods that focus on learning better human-object features, we propose a novel and complementary approach called category query learning. Such queries are explicitly associated to interaction categories, converted to image specific category representation via a transformer decoder, and learnt via an auxiliary image-level classification task. This idea is motivated by an earlier multi-label image classification method, but is for the first time applied for the challenging human-object interaction classification task. Our method is simple, general and effective. It is validated on three representative HOI baselines and achieves new state-of-the-art results on two benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑