Temporal Language Grounding seeks to localize video moments that semantically
correspond to a natural language query. Recent advances employ the attention
mechanism to learn the relations between video moments and the text query.
However, naive attention might not be able to appropriately capture such
relations, resulting in ineffective distributions where target video moments
are difficult to separate from the remaining ones. To resolve the issue, we
propose an energy-based model framework to explicitly learn moment-query
distributions. Moreover, we propose DemaFormer, a novel Transformer-based
architecture that utilizes exponential moving average with a learnable damping
factor to effectively encode moment-query inputs. Comprehensive experiments on
four public temporal language grounding datasets showcase the superiority of
our methods over the state-of-the-art baselines.

时序语言定位是为了找出语义上与自然语言查询相对应的视频片段。该研究提出了一种基于能量的模型框架和 DemaFormer，一种新颖的基于 Transformer 的架构，用于有效地学习时序语言定位。实验证明我们的方法在四个公开的时序语言定位数据集上优于最先进的基线方法。