Language-Guided Multi-Granularity Context Aggregation for Temporal Sentence Grounding

doi:10.1109/TMM.2022.3222664

Language-Guided Multi-Granularity Context Aggregation for Temporal Sentence Grounding

2023-01-01

4

PRE

AI

DOI：10.1109/TMM.2022.3222664

原文链接

原文求助

摘要

En 中文

Temporal sentence grounding in videos is a crucial task in vision-language learning. Its goal is retrieving a video segment from an untrimmed video that semantically corresponds to a natural language query. A video usually contains multiple semantic events, which are rarely isolated. They tend to be temporally ordered and semantically correlated (e.g., some event is often the precursor of another event). To precisely localize a semantic moment from a video, it is critical to effectively extract and aggregate multi-granularity contextual information, including the fine-grained local context around the moment-related video segment (in short snippet-level) and coarse-grained semantic correlation (in segment-level). Additionally, a second main insight in this work is that the above context aggregation should be favorably guided by the queries, rather than fully query-agnostic. Putting above ideas together, we here present a new network that does language-guided multi-granularity context aggregation. It is comprised of two major modules. The core of the first module is a novel language-guided temporal adaptive convolution (LTAC) devised to extract fine-grained information over video snippets around the ground-truth video segment. It decomposes a convolution into two channel-oriented / temporal-oriented ones. In particular, the convolutional channels are supposed to be more susceptible to queries, thus we learn to generate a dynamic channel-oriented kernel with respect to the querying sentence. As a second module, we propose a language-guided global relation block (LGRB) that extracts video-level context. It augments the contextual feature by using a multi-scale temporal attention that tackles the scale variation of ground-truth video segments, and a multi-modal semantic attention that relies on syntactic of the query. For the validation purpose, we have conducted comprehensive experiments on two popularly-adopted video benchmarks (i.e., ActivityNet Captions and Charades-STA). All experimental results and ablation studies have clearly corroborated the effectiveness of our model designs, outstripping prior state-of-the-art methods in terms of major performance metrics for the task.

Keyword:

Videos

Proposals

Grounding

Semantics

Location awareness

Convolution

Task analysis

Vision-language learning

video understanding

temporal sentence grounding

multi-modality learning

Language-Guided Multi-Granularity Context Aggregation for Temporal Sentence Grounding

摘要

期刊

机构

引用论文