Mind-the-Gap! Unsupervised Domain Adaptation for Text-Video Retrieval
Mind-the-Gap! Unsupervised Domain Adaptation for Text-Video Retrieval
复制标题
DOI：
10.1609/aaai.v35i2.16192
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Qingchao Chen;Yang Liu;Samuel Albanie
中科院分区：
文献类型：
--
作者：
Qingchao Chen;Yang Liu;Samuel Albanie
我们什么时候才能期望文本视频检索系统能够有效地处理与其训练领域不同的数据集？在这项工作中，我们通过无监督域适应的角度来研究这个问题，其中的目标是在查询时存在域转移的情况下匹配自然语言查询和视频内容。此类系统具有重要的实际应用，因为它们能够推广到新的数据源而不需要相应的文本注释。我们做出以下贡献：（1）我们提出了 UDAVR（视频检索无监督域适应）基准，并用它来研究存在域转移的文本视频检索的性能。 （2）我们提出了概念感知伪查询（CAPQ），这是一种学习区分性和可转移特征的方法，可以弥合这些跨域差异，从而使用源域监督实现有效的目标域检索。 (3) 我们表明 CAPQ 优于 UDAVR 上的替代域适应策略。
When can we expect a text-video retrieval system to work effectively on datasets that differ from its training domain? In this work, we investigate this question through the lens of unsupervised domain adaptation in which the objective is to match natural language queries and video content in the presence of domain shift at query-time. Such systems have significant practical applications since they are capable generalising to new data sources without requiring corresponding text annotations. We make the following contributions: (1) We propose the UDAVR (Unsupervised Domain Adaptation for Video Retrieval) benchmark and employ it to study the performance of text-video retrieval in the presence of domain shift. (2) We propose Concept-Aware-Pseudo-Query (CAPQ), a method for learning discriminative and transferable features that bridge these cross-domain discrepancies to enable effective target domain retrieval using source domain supervision. (3) We show that CAPQ outperforms alternative domain adaptation strategies on UDAVR.