3.8 Proceedings Paper

Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos

出版社

ASSOC COMPUTING MACHINERY
DOI: 10.1145/3331184.3331235

关键词

Query-based moment retrieval; syntactic GCN; multi-head self-attention; multi-stage cross-modal interaction

资金

  1. National Natural Science Foundation of China [61602405, 61751209, 61836002]
  2. Joint Research Program of ZJU

向作者/读者索取更多资源

Query-based moment retrieval aims to localize the most relevant moment in an untrimmed video according to the given natural language query. Existing works often only focus on one aspect of this emerging task, such as the query representation learning, video context modeling or multi-modal fusion, thus fail to develop a comprehensive system for further performance improvement. In this paper, we introduce a novel Cross-Modal Interaction Network (CMIN) to consider multiple crucial factors for this challenging task, including (1) the syntactic structure of natural language queries; (2) long-range semantic dependencies in video context and (3) the sufficient cross-modal interaction. Specifically, we devise a syntactic GCN to leverage the syntactic structure of queries for fine-grained representation learning, propose a multi-head self-attention to capture long-range semantic dependencies from video context, and next employ a multi-stage cross-modal interaction to explore the potential relations of video and query contents. The extensive experiments demonstrate the effectiveness of our proposed method.

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

3.8
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