4.7 Article

Multi-Source Video Domain Adaptation With Temporal Attentive Moment Alignment Network

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2023.3234307

关键词

Multi-source; video domain adaptation; action recognition; moment alignment; dataset

向作者/读者索取更多资源

Multi-Source Domain Adaptation (MSDA) is a more practical scenario that relaxes the assumption in conventional Unsupervised Domain Adaptation (UDA). The existence of different domain shifts makes MSDA more challenging, especially in video domain where spatial-temporal features can cause negative transfer. To address this problem, TAMAN is proposed to dynamically align spatial and temporal feature moments for effective feature transfer.
Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios, which relaxes the assumption in conventional Unsupervised Domain Adaptation (UDA) that source data are sampled from a single domain and match a uniform data distribution. The MSDA is more challenging due to the existence of different domain shifts between distinct domain pairs. When considering videos, the negative transfer would be provoked by spatial-temporal features and can be formulated into a more challenging Multi-Source Video Domain Adaptation (MSVDA) problem. In this paper, we address the MSVDA problem by proposing a novel Temporal Attentive Moment Alignment Network (TAMAN) which aims for effective feature transfer by dynamically aligning both spatial and temporal feature moments. The TAMAN further constructs robust global temporal features by attending to dominant domain-invariant local temporal features with high local classification confidence and low disparity between global and local feature discrepancies. To facilitate future research on the MSVDA problem, we introduce comprehensive benchmarks, covering extensive MSVDA scenarios. Empirical results demonstrate a superior performance of the proposed TAMAN across multiple MSVDA benchmarks.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据